System

Abstract

A system is provided.SOLUTION: A system comprising: a supply-data collecting means for collecting and organizing information on goods produced and shipped in a local area; a demand-data collecting means for collecting and organizing information on WEB retrieval histories, news articles, social media posts, retrieval trends, and global situations; a means for constructing a supply-data database and a demand-data database; a means for matching the supply-data database and the demand-data database in a generation AI and finding and proposing goods to be entered; and a means for displaying a proposed result.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] The development of local specialty products and famous local products is important for regional revitalization, but challenges exist, such as labor shortages, lack of capital, and a lack of trends. It is particularly difficult to develop products that make the most of a region's characteristics and respond promptly to consumer trends. Traditional methods make it difficult to determine in a timely manner which specialty products match demand, resulting in delays or failure in the development of specialty products. A new system is needed to resolve these challenges and enable regions and companies to efficiently develop specialty products. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes a supply data collection means for collecting and organizing data on goods produced and shipped in a region, a demand data collection means for collecting and organizing data on web search history, news articles, social media posts, search trends, and world affairs, a means for constructing a supply database and a demand database, a means for matching the supply database and the demand database with a generation AI to discover and propose products that should be introduced, and a means for displaying the proposal results.

[0006] The supply database includes information on services provided in the region, tourism resources, specialty products, and past industry data, while the demand database includes information on multiple categories such as health-consciousness, ecology, technology, gourmet food, and travel, making it possible to efficiently propose new specialty products that respond to regional characteristics and consumer trends. This allows regions and companies to quickly and effectively develop specialty products.

[0007] "Supply Data" refers to goods produced and shipped in the region, services provided, tourist resources, local specialties, and historical industry data.

[0008] "Demand Data" refers to web search history, news articles, social media posts, search trends, and information about world events.

[0009] "Supply data collection means" refers to means for collecting and organizing data on goods produced and shipped in the region.

[0010] "Demand data collection methods" refers to methods for collecting and organizing data on web search history, news articles, social media posts, search trends, and world events.

[0011] "Supply Database" refers to a database that centrally manages collected supply data and classifies it by region.

[0012] "Demand database" refers to a database that centrally manages collected demand data and classifies it by category.

[0013] "Generative AI" refers to artificial intelligence that compares supply and demand databases, extracts highly relevant data, and discovers and suggests products that should be marketed.

[0014] "Proposal results" refer to new product ideas for entry that are generated from the results of matching supply data and demand data.

[0015] The "display means" refers to a means for displaying the generated proposal results to the user.

[0016] "Geographic area" means a specific geographic area and includes information related to goods produced or shipped or services provided within that area.

[0017] "Product" refers to the new goods or services that will be developed and sold as a result of the proposal. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This system collects supply data such as goods produced and shipped in the region and services provided, organizes it, and stores it in a supply database. It also collects demand data such as web search history, news articles, social media posts, search trends, and world events, organizes it, and stores it in a demand database. It matches these two databases using generative AI to discover and suggest products that should be marketed.

[0040] Program processing flow

[0041] 1. Collecting and organizing supply data

[0042] Server: Collects data for distribution

[0043] The server collects production and shipping data via data provision APIs from local governments and companies.

[0044] The server uses scraping technology to obtain information from publicly available databases and websites.

[0045] Server: Organizing the data provided

[0046] The server categorizes the collected data by region, attaches detailed information (e.g., production volume, quality, price) and stores it in a supply database.

[0047] 2. Collecting and organizing demand data

[0048] Server: Collects demand data

[0049] The server uses APIs from search engines and social media platforms to collect trending information.

[0050] The server uses crawling technology to obtain the latest information from news sites and blogs.

[0051] Server: Organizing demand data

[0052] The server classifies the collected data by category (e.g., health foods, ecology, technology) and stores it in a demand database.

[0053] 3. Data matching and proposals

[0054] Server: Data matching process by generative AI

[0055] The generative AI on the server compares the supply database with the demand database and extracts highly relevant data.

[0056] Generative AI uses past success stories and trend-prediction algorithms to predict potential hit products.

[0057] Server: Generates proposal results

[0058] The server concretizes product ideas based on the AI ​​matching results and generates proposals that include details such as product concept, target market, and sales plan.

[0059] 4. Displaying the proposed results

[0060] Device: Display of suggested results

[0061] The user's (local government or company's) terminal receives the proposal results from the server and displays detailed information (product concept, target market, sales plan).

[0062] Users can create development plans for new specialty products based on these proposals.

[0063] Specific examples

[0064] For example, here is a specific example from Shizuoka Prefecture:

[0065] Supply Data Collection

[0066] Region: Shizuoka Prefecture

[0067] Items: Green tea, mandarin oranges, wasabi

[0068] Tourist attractions: hot springs, historical buildings

[0069] Demand data collection

[0070] Recent search trends: Healthy food, detox, low calorie

[0071] News article: As health consciousness grows, attention is focused on the benefits of green tea

[0072] Proposal example

[0073] 1. The server stores information about Shizuoka Prefecture's specialty products, green tea and mandarin oranges, in a supply database.

[0074] 2. The server stores in the demand database that "health foods" and "detox" are trending.

[0075] 3. The server's generation AI matches the detoxifying effects of green tea with trend information to generate new product ideas.

[0076] 4. The server generates a recommendation for a "detox drink using green tea" and sends it to the device.

[0077] 5. The user creates a development plan for a green tea drink based on the received proposal results.

[0078] In this way, the present invention efficiently proposes new specialty products that optimally match regional characteristics with consumer trends, enabling local governments and businesses to rapidly and effectively develop products.

[0079] The processing flow will be explained below.

[0080] Step 1: Gather supply data

[0081] Server: Collects production and shipping data from local governments and companies using APIs.

[0082] Server: Information is obtained from public databases and websites using scraping technology.

[0083] Server: Removes duplicates from the collected data and standardizes the data format.

[0084] Step 2: Organize and store supply data

[0085] Server: Classifies collected supply data by region and organizes goods, services, tourist resources, specialty products, and historical industry data.

[0086] Server: Attaches detailed information (e.g. production volume, quality, price) to each data item and stores it in a supply database.

[0087] Server: Creates indexes for stored data and optimizes search speed.

[0088] Step 3: Collect demand data

[0089] Server: Uses APIs of search engines and social media platforms to collect trend information.

[0090] Server: Obtains the latest information from news sites and blogs using crawling technology.

[0091] Server: Removes duplicates from the collected data and standardizes the data format.

[0092] Step 4: Organize and store demand data

[0093] Server: Classifies the collected demand data by category (e.g., health foods, ecology, technology).

[0094] Server: Attach detailed information (e.g., number of searches, frequency of mentions) to each piece of data and store it in the demand database.

[0095] Server: Creates indexes for stored data and optimizes search speed.

[0096] Step 5: Matching the data

[0097] Server: Uses generative AI to match supply and demand databases, automatically extracting relevant data.

[0098] Server: Generative AI analyzes data based on past successes and trend prediction algorithms to predict potential hit products.

[0099] Server: Organizes the matching results from AI and extracts product ideas that should be marketed.

[0100] Step 6: Generate proposal results

[0101] Server: Materializes the product ideas obtained from the matching results and generates detailed proposals (product concept, target market, sales plan).

[0102] Server: Compiles the generated proposal results into a report format for local governments and businesses.

[0103] Step 7: Viewing the Suggestion Results

[0104] Terminal: Receives the proposal results provided by the server.

[0105] Terminal: The proposal results are displayed so that users can view them. Detailed information (product concept, target market, sales plan) can be confirmed.

[0106] User: Based on the received proposals, a development plan for a new specialty product can be created.

[0107] Example 1

[0108] 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."

[0109] Currently, many regions and companies are struggling to effectively market their specialty products and services. One reason for this is that matching supply and demand takes time and effort, preventing appropriate product proposals from being made quickly. Furthermore, with global conditions and consumer trends constantly changing, it is difficult to determine which areas to focus on. In these circumstances, a system is needed that effectively integrates local characteristics with global trends and allows for fast and efficient product proposals.

[0110] 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.

[0111] In this invention, the server includes: a supply data collection means for collecting and organizing data on goods produced and shipped in the region; a demand data collection means for collecting and organizing data on web search history, news articles, information sharing platform posts, search trends, and international affairs; a means for constructing a supply database and a demand database; a means for matching the supply database and the demand database using generation AI and making new product proposals; a means for displaying the proposal results; a means for classifying supply data by region and storing it in the supply database with detailed information attached; a means for collecting trend information using the API of a search engine or information sharing platform; and a means for concretizing product ideas based on the matching process and generating proposal content such as a product concept, target market, and sales plan, thereby enabling fast and efficient product proposals for local specialty products and services through supply and demand matching.

[0112] "Supply data collection means" refers to a means for collecting and organizing data on goods produced and shipped in the region.

[0113] "Demand data collection means" refers to means for collecting and organizing data on web search history, news articles, posts on information sharing platforms, search trends, and international affairs.

[0114] The "supply database" is a database for storing and managing data on goods produced and shipped in the region.

[0115] A "demand database" is a database for storing and managing data related to demand.

[0116] "Generative AI" is a system that uses artificial intelligence technology to analyze data and perform matching and new product suggestions.

[0117] The "matching means" is a means for comparing the supply database and the demand database using generation AI to make new product proposals.

[0118] The "means for displaying proposal results" is a means for displaying the proposal results made by the generation AI to the user.

[0119] The "supply data classification means" is a means for classifying collected supply data by region, attaching detailed information, and storing the data in the supply database.

[0120] "Trend data collection means" refers to a means for collecting trend information using the APIs of search engines and information sharing platforms.

[0121] The "product idea realization means" is a means for realizing a product idea based on a matching process and generating proposal contents such as a product concept, target market, and sales plan.

[0122] This invention is a system that uses AI to match supply data, such as goods produced and shipped in a region and services provided, with demand data, such as web search history, news articles, posts on information sharing platforms, search trends, and international affairs, to discover and suggest products that should be marketed. This system is implemented using the following hardware and software.

[0123] 1. Collecting and organizing supply data

[0124] Server: Use of data provision API

[0125] The server uses a data provision API to collect supply data from local governments and companies. Specifically, it periodically obtains production and shipping data. The data is provided in JSON format and can be collected using an API client (e.g., an HTTP library).

[0126] Example: A server collects data on green tea production volume and quality from the Shizuoka Prefecture Agricultural Cooperative API.

[0127] Server: Use of scraping technology

[0128] The server obtains supply data from the public websites of local businesses using scraping techniques, for example, using an HTML parsing library to extract product pricing information and availability from specialty product pages.

[0129] Example: A server parses HTML from a company's specialties page to obtain pricing information for green tea.

[0130] Server: Classification of collected data

[0131] The server categorizes the collected data by region, attaches detailed information and stores it in a supply database, using a database management system (e.g., MySQL or PostgreSQL) for this process.

[0132] 2. Collecting and organizing demand data

[0133] Server: API collection of trend data

[0134] The server uses the Google Trends API and Twitter API to collect search trend information, which is then analyzed and stored in a demand database.

[0135] Example: The server uses the Google Trends API to collect search volume data for keywords related to "health foods" and "detox."

[0136] Server: Use of crawling techniques

[0137] The server crawls news sites and blogs to obtain the latest demand information, analyzes the information, categorizes it, and stores it in a demand database.

[0138] Example: A server crawls health-related articles from news sites and stores them in a demand database.

[0139] 3. Data matching and proposals

[0140] Server: Matching process by generation AI

[0141] A server-based generation AI (e.g., GPT-4) is used to match the supply database with the demand database, extracting highly relevant data based on keyword matches and correlations.

[0142] Example: Generative AI matches green tea supply data with "health food" trend information.

[0143] Server: Proposal generation

[0144] The server then creates a new product proposal based on the relevant data extracted by the generative AI, including details such as the product concept, target market, and sales plan.

[0145] Example: Generative AI generates product ideas for a "green tea detox drink" and creates a detailed sales plan.

[0146] 4. Displaying the proposed results

[0147] Terminal: Receiving and displaying the proposed results

[0148] The user's device receives the recommendation results from the server and displays detailed information. A dashboard-style UI is used, allowing the user to easily check the details of the recommended products.

[0149] Example: The user's terminal receives the proposal results from the server and displays the new product concept, target market, and sales plan.

[0150] Prompt Sentence Examples

[0151] An example of a prompt sentence input to a generative AI model:

[0152] "The supply data includes green tea and mandarin oranges produced in Shizuoka Prefecture. The current demand data includes health foods and detoxes, which are trending. Please use this data to propose new product ideas."

[0153] By efficiently matching supply and demand data, the system enables local specialties and services to enter the market quickly and effectively.

[0154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0155] Step 1: Gather supply data

[0156] Server: Use of data provision API

[0157] The server uses a data provision API to collect supply data from local governments and companies. The server periodically sends requests to the API endpoint and obtains production volume and quality information in JSON format.

[0158] Input: API request

[0159] Output: JSON formatted supply data

[0160] Specifically, the server sends an HTTP request and analyzes the data obtained as a response.

[0161] Step 2: Scrape supply data

[0162] Server: Use of scraping technology

[0163] The server obtains supply data from publicly available websites of local businesses using scraping techniques, for example, using HTML parsing libraries to extract product pricing information and availability from specialty product pages.

[0164] Input: Webpage URL

[0165] Output: Extracted feed data

[0166] Specifically, the server accesses the web page, analyzes the HTML, and extracts the necessary data.

[0167] Step 3: Classify and store supply data

[0168] Server: Classification of collected data

[0169] The server categorizes the collected data by region and stores it in a supply database along with detailed information (production volume, quality, price).

[0170] Input: Supply data before classification

[0171] Output: Data to be inserted into the supply database

[0172] Specifically, the server classifies the data based on the region name and inserts a new record into the database.

[0173] Step 4: Collect demand data

[0174] Server: API collection of trend data

[0175] The server uses the Google Trends API and Twitter API to collect search trend information, which is then analyzed and stored in a demand database.

[0176] Input: API request

[0177] Output: Demand data in JSON format

[0178] Specifically, the server sends an API request and obtains trend information in JSON format.

[0179] Step 5: Crawl for demand data

[0180] Server: Use of crawling techniques

[0181] The server crawls news sites and blogs to obtain the latest demand information. The analyzed information is categorized and stored in a demand database.

[0182] Input: Website URL

[0183] Output: Retrieved demand data

[0184] Specifically, the server accesses the news site, analyzes the HTML, and extracts demand data.

[0185] Step 6: Classify and store demand data

[0186] Server: Classification of collected data

[0187] The server classifies the collected demand data into categories (healthy foods, ecology, technology, etc.) and stores them in a demand database.

[0188] Input: Demand data before classification

[0189] Output: Data to be inserted into the demand database

[0190] Specifically, the server categorizes the data based on the category name and inserts a new record into the database.

[0191] Step 7: Matching the data

[0192] Server: Matching by generative AI

[0193] The server-based AI compares the supply and demand databases to extract relevant data, then analyzes the data based on keyword matches and correlations.

[0194] Input: Supply data, Demand data

[0195] Output: Matching results

[0196] Specifically, the server uses generative AI to analyze supply and demand data and extract highly relevant pairs.

[0197] Step 8: Generate proposals

[0198] Server: Creating a concrete proposal

[0199] The server then uses the relevant data extracted by the generative AI to create new product ideas, including details such as the product concept, target market, and sales plan.

[0200] Input: Matching results

[0201] Output: Specific product suggestions

[0202] Specifically, the server analyzes the output of the generative AI and converts the product ideas into detailed proposal documents.

[0203] Step 9: Viewing the Suggestion Results

[0204] Terminal: Receiving and displaying the proposed results

[0205] The user's terminal receives the proposal results sent from the server and displays the detailed information.

[0206] Input: Proposal result data

[0207] Output: Display of proposal results

[0208] Specifically, the device receives data from the server and displays it on a dashboard-style UI.

[0209] Step 10: Use the proposal

[0210] User: Product development based on received results

[0211] The user makes a product development plan based on the received proposal results.

[0212] Input: Suggestion results

[0213] Output: Product development plan

[0214] Specifically, the user analyzes the proposal and provides feedback to the product development department.

[0215] (Application example 1)

[0216] 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."

[0217] Conventional systems were unable to effectively match data on locally produced and shipped goods and services provided with demand data, making it particularly difficult to utilize proposal results in real time. This meant that product proposals and inventory management in physical stores could not be carried out quickly, leading to the issue of being unable to respond promptly to customer needs.

[0218] 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.

[0219] In this invention, the server includes a supply data collection means for collecting and organizing data on goods produced and shipped in the region, a demand data collection means for collecting and organizing data on web search history, news articles, social media posts, search trends, and world affairs, a means for building a supply database and a demand database, a means for matching the supply database and the demand database with a generation AI to discover and propose products to be introduced, a means for displaying the proposal results, and a means for providing access to the proposal results in real time using a smart device.This enables product proposals and inventory management in physical stores to be carried out quickly and effectively, making it possible to respond to customer needs immediately.

[0220] "Supply data collection means" refers to a device or system that collects and organizes data on goods produced and shipped in a region.

[0221] "Demand data collection means" refers to a device or system that collects and organizes data on web search history, news articles, social media posts, search trends, and world events.

[0222] "Supply Database" refers to a database that stores collected supply data and stores detailed information categorized by region.

[0223] A "demand database" is a database that classifies collected demand data by category and stores trend information.

[0224] "Generative AI" is an artificial intelligence system that matches supply databases with demand databases to discover and propose products that should be marketed.

[0225] "Means for displaying proposal results" refers to a device or system for displaying proposals obtained by the generation AI to the user.

[0226] A "smart device" is a device that can connect to the Internet, such as a smartphone, smart glasses, or a head-mounted display.

[0227] "Means for providing real-time access to recommendation results" refers to a device or system that enables real-time access to the recommendation results of the generative AI using a smart device.

[0228] This invention collects supply data on goods produced and shipped in the region and services provided, and demand data such as web search history, news articles, social media posts, search trends, and world affairs, and organizes and stores them in a supply database and a demand database. This allows the generation AI to match the two databases, making it possible to efficiently discover and propose new products and services that should be introduced.

[0229] Program Overview

[0230] The server collects supply and demand data and uses AI to collate it, while smart devices (such as smartphones or smart glasses) display real-time recommendations, helping in-store operations.

[0231] Hardware and Software Used

[0232] Hardware: Servers, smart devices (smartphones, smart glasses, head-mounted displays)

[0233] software:

[0234] Python: Used for data collection and processing

[0235] Requests: Used to retrieve data from the API

[0236] JSON: A Data Interchange Format

[0237] Generative AI models: used to match data and generate recommendations

[0238] Data processing flow

[0239] The server uses APIs and crawling technology to collect supply data on goods produced and shipped in the region, as well as various demand data for services provided. The collected data is stored in a supply database and a demand database. A generative AI model compares these databases to generate relevant product and service recommendations. The results are delivered to smart devices in real time, enabling store employees to quickly make product recommendations to customers.

[0240] Specific examples

[0241] For example, consider a case where a customer wants health-conscious products at a brick-and-mortar store in Shizuoka Prefecture. The server collects supply data for green tea and mandarin oranges produced in Shizuoka Prefecture and stores it in a supply database. At the same time, it collects demand data on the trending health foods and detox products and stores it in a demand database. The generative AI matches these data and suggests a detox drink made with green tea. This suggestion is displayed in real time to employees through smart glasses, allowing them to provide immediate advice to the customer.

[0242] Prompt Sentence Examples

[0243] Based on local products and current trends, please suggest products to promote in-store. Please use the following data:

[0244] Supply data:

[0245] Green Tea

[0246] mandarin orange

[0247] Demand Data:

[0248] health food

[0249] Detox

[0250] Example output format:

[0251] Item: Green tea

[0252] Trend: Detoxification

[0253] Recommended action: Recommend this item in store

[0254] In this way, the present invention can optimally match regional characteristics with consumer trends, thereby realizing efficient product proposals and inventory management in physical stores.

[0255] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0256] Step 1:

[0257] The server collects data on goods produced and shipped in the region via data provision APIs from local governments and companies. It receives supply data from the API as input and obtains it as output. This obtained data includes production volume, quality, price, etc. Specifically, it calls the API to obtain data and then formats it.

[0258] Step 2:

[0259] The server collects data on web search history, news articles, social media posts, search trends, and world affairs. It receives demand data as input using each platform's API and web crawling technology, and obtains demand data as output. Specifically, it uses search engine APIs to collect trend information and crawls news sites for the latest information.

[0260] Step 3:

[0261] The server organizes the collected supply data and stores it in a supply database. It receives supply data as input and stores the formatted supply data as output in the supply database. Specifically, it classifies the data by region and attaches detailed information such as production volume and quality.

[0262] Step 4:

[0263] The server organizes the collected demand data and stores it in the demand database. It receives demand data as input and stores the formatted demand data as output in the demand database. Specifically, it classifies the data by category (e.g., health, ecology, technology) and stores it in the demand database.

[0264] Step 5:

[0265] The generative AI model on the server compares the supply and demand databases to extract highly relevant data. It receives the supply and demand databases as input and generates matching results as output. Specifically, it analyzes the supply and demand data based on prompt statements to identify highly relevant products and services.

[0266] Step 6:

[0267] The server concretizes product ideas based on the matching results of the generative AI model. It receives the matching results as input and generates a product concept, target market, and sales plan as output. Specifically, it creates detailed proposals by referring to past success stories and trends.

[0268] Step 7:

[0269] The smart device (e.g., smart glasses) receives the proposal results from the server and displays them to the user. It receives the proposal results from the server as input and displays them in the user's field of view as output. Specifically, it downloads data via the network and overlays the proposal results in the user's field of view.

[0270] Step 8:

[0271] The user (e.g., a store employee) proposes product details to the customer based on the proposal results displayed on the smart device. The user receives the proposal results on the smart device as input and makes product proposals to the customer as output. Specific operations include checking the displayed information and explaining the benefits and features of specific products to the customer.

[0272] 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.

[0273] This system collects supply data, such as goods produced and shipped locally and services provided, and organizes and stores it in a supply database. It also collects demand data, such as web search history, news articles, social media posts, search trends, and world events, and organizes and stores it in a demand database. It matches these two databases using generative AI to discover and recommend products that should be marketed. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it can optimize recommendation results based on the user's emotional data.

[0274] Program processing flow

[0275] 1. Collecting and organizing supply data

[0276] Server: Collects data for distribution

[0277] The server uses an API to collect production and shipping data from local governments and companies.

[0278] The server uses scraping technology to obtain information from publicly available databases and websites.

[0279] Server: Organizing the data provided

[0280] The server categorizes the collected data by region, attaches detailed information (e.g., production volume, quality, price) and stores it in a supply database.

[0281] The server standardizes the data format and deletes duplicate data.

[0282] 2. Collecting and organizing demand data

[0283] Server: Collects demand data

[0284] The server uses APIs from search engines and social media platforms to collect trending information.

[0285] The server uses crawling technology to obtain the latest information from news sites and blogs.

[0286] Server: Organizing demand data

[0287] The server classifies the collected data into categories (e.g., health foods, ecology, technology).

[0288] The server attaches detailed information (e.g., number of searches, frequency of mentions) to each piece of data and stores it in a demand database.

[0289] 3. Collecting and analyzing user emotion data

[0290] Server: Collects user emotion data

[0291] The server uses an emotion engine installed on the user's device to collect emotion data from the user's voice, facial expressions, input data, etc.

[0292] The server analyzes the collected emotion data in real time.

[0293] Server: Emotion data organization

[0294] The server organizes the emotion data by time axis and situation and stores it as an emotion database.

[0295] The server uses each user's past emotional data to create a foundation for optimizing future proposal results.

[0296] 4. Data matching and suggestions

[0297] Server: Data matching process by generative AI

[0298] The generative AI on the server compares the supply database with the demand database and automatically extracts highly relevant data.

[0299] Generative AI analyzes data based on past successes and trend-prediction algorithms to predict potential hit products.

[0300] Server: Generates proposal results taking into account user emotion data

[0301] The server combines the matching results of the generation AI with the user's emotional data to extract the optimal product ideas.

[0302] The server generates a proposal that includes details such as the product concept, target market, and sales plan.

[0303] 5. Displaying the proposed results

[0304] Device: Display of suggested results

[0305] The user's (local government or company's) terminal receives the proposal results from the server and displays detailed information (product concept, target market, sales plan).

[0306] Users can create development plans for new specialty products based on these proposals.

[0307] Specific examples

[0308] For example, here is a specific example from Shizuoka Prefecture:

[0309] Supply Data Collection

[0310] Region: Shizuoka Prefecture

[0311] Items: Green tea, mandarin oranges, wasabi

[0312] Tourist attractions: hot springs, historical buildings

[0313] Demand data collection

[0314] Recent search trends: Healthy food, detox, low calorie

[0315] News article: As health consciousness grows, attention is focused on the benefits of green tea

[0316] Collecting user emotion data

[0317] The emotion engine collects facial expressions and voice in real time while the user is reading a presented article related to green tea, and recognizes "positive" emotions.

[0318] Proposal example

[0319] 1. The server stores information about Shizuoka Prefecture's specialty products, green tea and mandarin oranges, in a supply database.

[0320] 2. The server stores in the demand database that "health foods" and "detox" are trending.

[0321] 3. Based on the emotion engine's recognition of the user's emotion as "positive," the server's generative AI matches the detoxifying effects of green tea with trend information to generate new product ideas.

[0322] 4. The server generates a recommendation for a "detox drink using green tea" and sends it to the device.

[0323] 5. The user creates a development plan for a green tea drink based on the received proposal results.

[0324] In this way, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to advance product development quickly and effectively.

[0325] The processing flow will be explained below.

[0326] Step 1: Gather supply data

[0327] Server: Uses API to collect production and shipping data from local governments and companies. Collected data includes product type, production volume, quality, price, etc.

[0328] Server: Uses scraping technology to obtain information from public databases and websites, including information on tourist attractions and local specialties.

[0329] Step 2: Organize and store supply data

[0330] Server: Categorizes the collected supply data by region and attaches detailed information, such as green tea, mandarin oranges, and wasabi in Shizuoka Prefecture.

[0331] Server: Standardize data formats and remove duplicate data.

[0332] Server: Stores the organized data in a serving database and indexes it to optimize search speed.

[0333] Step 3: Collect demand data

[0334] Server: Uses APIs of search engines and social media platforms to collect trending information, including search counts, mention frequency, and hot topics.

[0335] Server: Uses crawling technology to obtain the latest information from news sites and blogs, including information on health foods and ecology.

[0336] Step 4: Organize and store demand data

[0337] Server: Categorizes the collected demand data into categories, such as health foods, ecology, technology, etc.

[0338] Server: Standardize data formats and remove duplicate data.

[0339] Server: Stores organized data in a demand database and indexes it to optimize search speed.

[0340] Step 5: Collect and analyze user sentiment data

[0341] Server: Using the emotion engine installed on the user's device, it collects emotion data from the user's voice, facial expressions, input data, etc. For example, the user's facial expressions and voice are recognized through a camera or microphone.

[0342] Server: Analyzes collected emotion data in real time and identifies positive or negative emotions.

[0343] Server: Organizes emotion data by time axis and situation and stores it in an emotion database.

[0344] Step 6: Matching the data

[0345] Server: Uses generative AI to match supply and demand databases, automatically extracting relevant data.

[0346] Server: Generative AI analyzes data based on past successes and trend prediction algorithms to predict potential hit products, such as combining the detoxifying effects of green tea with current trends.

[0347] Step 7: Generate proposals taking into account user emotion data

[0348] Server: Combines the matching results of the generation AI with the user's emotional data to extract optimal product ideas. If the user shows "positive" emotions, this tendency is reflected.

[0349] Server: Generates proposals that include details such as product concept, target market, and sales plan.

[0350] Step 8: Viewing the Suggestion Results

[0351] Terminal: Receives the proposal results provided by the server.

[0352] User: View the proposal results and check detailed information (product concept, target market, sales plan).

[0353] User: Based on the received proposal, create a development plan for a new local specialty product. For example, start product development based on the received proposal for a "green tea detox drink."

[0354] Through the above steps, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to develop products quickly and effectively.

[0355] Example 2

[0356] 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."

[0357] Efficiently linking information on locally produced goods and services with demand information on the Internet and proposing new products and services that should be introduced is a difficult task for existing systems. Furthermore, making optimal proposals that take user emotions into account requires the collection and analysis of real-time, accurate emotional data. However, a system that can integrate this data and provide optimal proposals for each user has yet to be developed.

[0358] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting and organizing data on goods produced and shipped in a region, a means for collecting and organizing data on internet search history, news articles, social network posts, search trends, and world affairs, a means for matching a supply database and a demand database using artificial intelligence to discover and propose products that should be introduced, a means for collecting, analyzing, and organizing user emotion data, a means for optimizing proposal results based on the emotion data, and a means for displaying the proposal results. This enables effective and accurate product proposals by combining regional characteristics with real-time user emotion data.

[0359] "Supply data" refers to information including goods, services, tourism resources, and historical industry data produced and shipped in the region.

[0360] "Demand Data" is information including internet search history, news articles, social network posts, search trends, and world affairs data.

[0361] "Supply database" refers to a database that organizes and stores supply data.

[0362] A "demand database" is a database that organizes and stores demand data.

[0363] "Artificial intelligence" refers to algorithms and software that match supply and demand databases to discover and propose products that should be marketed.

[0364] "Emotion data" refers to emotional information collected from the user's voice, facial expression, input data, and the like.

[0365] The "emotion engine" is software for collecting, analyzing, and organizing user emotional data.

[0366] "Proposal results" are the specific products that AI has discovered and proposed for the market.

[0367] "Search trends" refers to data about the frequency and fluctuations of keywords and phrases that users search for on the Internet.

[0368] "Social network posts" are data that include user posts on social media platforms.

[0369] MODE FOR CARRYING OUT THE INVENTION

[0370] This invention is a system that collects supply data, such as goods produced and shipped in a region and services provided, and organizes and stores it in a supply database. It also collects demand data, such as internet search history, news articles, social network posts, search trends, and world events, and organizes and stores it in a demand database. These two databases are matched using artificial intelligence (AI) to discover and recommend products that should be marketed. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize recommendation results based on the user's emotional data.

[0371] Hardware and Software Configuration

[0372] The server uses the following hardware and software to implement this system:

[0373] Data collection module: This module periodically obtains production and shipping data from local governments and companies via API. Specifically, it uses HTTP requests.

[0374] Scraping tools: scraping data from public databases and websites using scraping techniques, using libraries such as BeautifulSoup and Scrapy.

[0375] Crawling tools: Crawling demand data from news sites and blogs, for example, using tools such as Selenium or Puppeteer.

[0376] Generative AI model: Used to match supply and demand databases and discover potential hit products. This is a model that applies natural language processing (NLP) technology, such as OpenAI's GPT model.

[0377] Emotion engine: Collects and analyzes emotional data in real time from the user's voice, facial expressions, input data, etc. For example, using Microsoft Azure Cognitive Services.

[0378] Database management system: A database for storing supply data and demand data, for example, MySQL or PostgreSQL.

[0379] Specific examples

[0380] For example, here is a specific example from Shizuoka Prefecture:

[0381] Supply data collection:

[0382] The server uses an API to collect production data on local specialties such as green tea, mandarin oranges, and wasabi from local governments and companies in Shizuoka Prefecture, and stores that information in a supply database.

[0383] In addition, information on green tea production volume and quality will be collected from publicly available databases and websites through scraping and stored in a supply database in a unified format.

[0384] Demand data collection:

[0385] The server uses an API to obtain the number of searches for keywords such as "health benefits of green tea" from search engines and stores the information in a demand database.

[0386] In addition, articles about health-consciousness are collected by crawling from news sites and blogs, categorized into "healthy foods," and stored in a demand database.

[0387] Collecting and analyzing sentiment data:

[0388] The server uses an emotion engine installed on the user's device to analyze the user's voice and facial expressions in real time while they are reading an article about green tea, and recognizes "positive" emotions.

[0389] Generative AI suggestions:

[0390] The server's generation AI matches green tea data from the supply database with health food trend data from the demand database to generate an idea for a new product: a "green tea drink with detoxifying effects."

[0391] Furthermore, based on the user's emotional data, the system generates optimal product concepts, target markets, and sales plans as proposals.

[0392] Viewing Suggested Results:

[0393] The user's device displays the proposal results received from the server, and the user can check details such as the product concept and sales plan for the "Green Tea Detox Drink."

[0394] Prompt Sentence Examples

[0395] "Please propose a new product idea that uses green tea, a specialty of Shizuoka Prefecture, and is in line with the health food trend. Please take into account user sentiment data and optimize the proposal results."

[0396] This enables the system to combine regional characteristics with real-time user emotional data to make effective and accurate product recommendations.

[0397] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0398] Step 1:

[0399] Supply Data Collection

[0400] The server uses an API to obtain production and shipping data from local governments and companies. For example, it obtains green tea production data for Shizuoka Prefecture through an HTTP request and saves it as a CSV file. It also uses scraping technology to collect data from publicly available databases and websites. The input is raw data obtained from the API or webpage, and the output is a list of the various types of collected data.

[0401] Step 2:

[0402] Supply data organization

[0403] The server classifies the collected data by region and standardizes the format. For example, it classifies green tea data into the "Shizuoka Prefecture" category and standardizes the weight unit to kg. It deletes any duplicate data and stores the organized data in the supply database. The input is the collected raw data, and the output is an organized, consistent dataset.

[0404] Step 3:

[0405] Demand data collection

[0406] The server collects demand data via APIs of search engines and social media platforms. For example, it obtains the number of searches for a specific keyword (e.g., "green tea health benefits") and saves this as trend data. At the same time, it also collects data from news sites and blogs by crawling. The input is trend data on the Internet, and the output is a list of the collected demand data.

[0407] Step 4:

[0408] Organizing demand data

[0409] The server categorizes the collected demand data by category and standardizes the format. For example, it stores the data in categories such as "healthy foods" and "ecology" and attaches search and mention frequency information. The input is raw data, and the output is an organized demand dataset.

[0410] Step 5:

[0411] Collecting user emotion data

[0412] The server uses an emotion engine installed on the user's device to collect emotion data in real time from the user's voice and facial expressions. For example, a camera captures the user's facial expression while reading an article about green tea and recognizes the emotion as "positive." The input is the user's real-time emotion data, and the output is classified emotion data.

[0413] Step 6:

[0414] Analyzing and organizing emotion data

[0415] The server organizes the collected emotional data by timeline and situation, and creates a basis for optimizing future proposals by referring to past data. For example, it stores data such as "positive reaction after reading an article about green tea at 10:30 on October 15, 2023." The input is emotional data collected in real time, and the output is an analyzed and organized emotional dataset.

[0416] Step 7:

[0417] Data matching by generative AI

[0418] The server's generation AI compares the supply database with the demand database and extracts highly relevant data. For example, it matches "green tea" information from the supply database with "health food trends" information from the demand database. The input is supply data and demand data, and the output is a new product idea as a result of the matching.

[0419] Step 8:

[0420] Generating proposal results taking into account user emotion data

[0421] The server combines the matching results of the generation AI with the user's emotional data to extract optimal product ideas. For example, if the user expresses positive feelings toward green tea, it generates a suggestion for "green tea detox drink." The input is the matching results and emotional data, and the output is a detailed suggestion.

[0422] Step 9:

[0423] Sending the proposal results to the device

[0424] The server sends the generated proposal results to the user's device. For example, it sends the proposal document in JSON format to the device and makes it viewable. The input is the generated proposal results, and the output is the transmitted data.

[0425] Step 10:

[0426] Displaying the proposed results

[0427] The user's terminal displays the proposal results received from the server. For example, a specific product concept or sales plan is displayed on the screen. The input is the proposal results sent from the server, and the output is the displayed information.

[0428] (Application example 2)

[0429] 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."

[0430] Existing product development platforms are limited to simply matching supply and demand data and do not take user sentiment into account. This makes it difficult to propose products that accurately reflect consumers' latent needs. It is also difficult to maximize the appeal of local specialties and develop products that respond to trends in real time. This hinders improvements in sales efficiency and the rapid launch of new products.

[0431] 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.

[0432] In this invention, the server includes a supply data collection means for collecting and organizing data on goods produced and shipped in the region; a demand data collection means for collecting and organizing data on web search history, news articles, social media posts, search trends, and world affairs; a means for building a supply database and a demand database; a means for matching the supply database and the demand database using generative AI to discover and propose products to be introduced; an emotion data collection means for collecting and analyzing user emotion data in real time; a means for optimizing proposal results taking into account the collected emotion data; and a means for displaying the proposal results. This enables accurate product proposals that take into account user emotion in addition to matching supply data and demand data. Furthermore, it is possible to maximize the appeal of regional specialty products and quickly bring new products that are in line with trends to market, which is expected to improve sales efficiency.

[0433] "Supply data collection means" refers to a means for collecting and organizing data on goods produced and shipped in the region.

[0434] "Demand data collection methods" are methods for collecting and organizing data on web search history, news articles, social media posts, search trends, and world events.

[0435] A "supply database" is a database for storing and managing collected supply data.

[0436] A "demand database" is a database for storing and managing collected demand data.

[0437] "Generative AI" is artificial intelligence that collates supply and demand databases and analyzes relevant data.

[0438] The "emotion data collection means" is a means for collecting emotion data from the user's voice, facial expression, input data, etc., and analyzing it in real time.

[0439] The "means for displaying the proposed results" is a means for displaying to the user the product information proposed as a result of analysis by the generation AI.

[0440] A system for implementing the present invention collects supply data, such as goods produced and shipped in a region and services provided, and organizes and stores it in a supply database. It also collects demand data, such as web search history, news articles, social media posts, search trends, and world events, and organizes and stores it in a demand database. The system matches these two databases using generative AI to discover and recommend products that should be marketed. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it can optimize recommendation results based on the user's emotion data.

[0441] System Configuration

[0442] 1. Hardware to be used

[0443] Server (operation of database and generative AI)

[0444] Smartphones and tablets (for the user interface)

[0445] 2. Software to be used

[0446] Database management systems (e.g., MySQL, PostgreSQL)

[0447] Crawling tools for collecting data from news sites, etc. (e.g., Scrapy)

[0448] Emotion engine libraries (e.g., Microsoft Azure Emotion API, Google Cloud Vision API)

[0449] Machine learning libraries (e.g. TensorFlow, PyTorch)

[0450] Web development frameworks (e.g., Django, Flask)

[0451] Program processing flow

[0452] The server uses supply data collection tools to collect production and shipping data from local governments and companies. It also uses scraping technology to obtain information from publicly available databases and websites. The collected data is categorized by region, and detailed information is stored in the supply database.

[0453] Next, the server uses demand data collection means to collect trend information using APIs of search engines and social media platforms, and also obtains data from the latest news sites and blogs using crawling technology, categorizes each piece of information, and stores the detailed information in a demand database.

[0454] Users' emotional data is collected using an emotion engine in an application on a smartphone or tablet. The engine collects users' voices, facial expressions, input data, etc. in real time, analyzes and organizes the emotional data, and stores it in an emotion database.

[0455] The server uses generative AI to match supply and demand databases and automatically extract relevant data. It analyzes the data based on past successes and trend prediction algorithms to predict potential hit products. By taking into account emotional data, it extracts optimal product ideas based on user sentiment and generates proposals that include details such as product concept, target market, and sales plan.

[0456] The proposal results are displayed on the user's smartphone or tablet, and the user can use these results to develop new products and sales strategies.

[0457] Specific examples

[0458] For example, here is a specific example from Shizuoka Prefecture:

[0459] When collecting supply data, information on Shizuoka Prefecture's specialty products, green tea, mandarin oranges, and wasabi, is stored in the supply database. When collecting demand data, the fact that health foods and detoxes are trending is stored in the demand database. When the emotion engine recognizes the user's emotion as "positive," the server's generation AI matches the detox effects of green tea with trend information to generate new product ideas.

[0460] The server generates a proposal for a "detox drink using green tea" and sends it to the user's device. The user can then create a development plan for the green tea drink based on the proposal received.

[0461] Example prompt sentence:

[0462] Please propose new product ideas based on the following supply and demand data. The supply data includes green tea, mandarin oranges, and wasabi from Shizuoka Prefecture. The demand data includes "healthy food," "detox," and "low calorie." Users indicate positive sentiment. Extract the best product ideas and propose a product concept, target market, and sales plan.

[0463] In this way, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to advance product development quickly and effectively.

[0464] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0465] Step 1:

[0466] The server collects production and shipping data provided by local governments and companies using supply data collection methods. Specifically, it obtains data using APIs and collects information from public databases and web pages using scraping technology. The collected data is categorized by region and stored in a supply database.

[0467] Input: Production and shipping data from local governments and companies, information from public databases

[0468] Data processing: Classification by region, removal of duplicate data, unification of format

[0469] Output: Supply database

[0470] Step 2:

[0471] The server collects data on web search history, news articles, social media posts, search trends, and world affairs using demand data collection methods. Specifically, it obtains trend information using search engine and social media APIs, and collects data from news sites and blogs using crawling technology. The collected data is categorized and stored in a demand database.

[0472] Input: Web search history, news articles, social media posts, search trends, world events

[0473] Data processing: Classification by category, addition of detailed information (number of searches, frequency of mentions)

[0474] Output: Demand database

[0475] Step 3:

[0476] An emotion engine is used in an application installed on the user's device to collect the user's emotional data. Specifically, voice, facial expressions, and input data are collected and analyzed in real time and stored in an emotion database. The emotional data is organized by time axis and situation.

[0477] Input: User's voice, facial expressions, input data

[0478] Data calculation: Real-time analysis of emotional data, organizing it by time axis and situation

[0479] Output: Emotion database

[0480] Step 4:

[0481] The server uses generative AI to match supply and demand databases and automatically extract relevant data. Specifically, it compares supply and demand data and analyzes the data based on trend prediction algorithms, thereby predicting potential hit products.

[0482] Input: Supply database, Demand database

[0483] Data calculation: Matching supply and demand, data analysis using trend prediction algorithms

[0484] Output: A list of potential hits

[0485] Step 5:

[0486] The server uses the collected emotional data to extract optimal product ideas based on the matching results of the generative AI. Specifically, it adds the emotional data to the analysis results of the generative AI to generate proposals that include details such as the product concept, target market, and sales plan.

[0487] Input: sentiment database, list of potential hit products

[0488] Data calculation: Generate product ideas that reflect emotional data and create detailed proposals

[0489] Output: Optimal product ideas and proposals

[0490] Step 6:

[0491] The proposal results are displayed on the user's device. Specifically, the product ideas and proposal content generated by the server are sent to a smartphone or tablet application and visually displayed to the user. The user can then formulate new product development and sales strategies based on these proposal results.

[0492] Input: Optimal product ideas and proposals

[0493] Action: Sends suggestions and displays them on smartphones and tablets

[0494] Output: Displayed suggestion results

[0495] This series of processes not only optimally matches regional characteristics with consumer trends, but also combines user emotional data to provide more accurate proposal results, enabling local governments and companies to develop products quickly and effectively.

[0496] 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.

[0497] 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.

[0498] 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.

[0499] [Second embodiment]

[0500] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0501] 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.

[0502] 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).

[0503] 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.

[0504] 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.

[0505] 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).

[0506] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0507] 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.

[0508] 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.

[0509] 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.

[0510] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0511] 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."

[0512] This system collects supply data such as goods produced and shipped in the region and services provided, organizes it, and stores it in a supply database. It also collects demand data such as web search history, news articles, social media posts, search trends, and world events, organizes it, and stores it in a demand database. It matches these two databases using generative AI to discover and suggest products that should be marketed.

[0513] Program processing flow

[0514] 1. Collecting and organizing supply data

[0515] Server: Collects data for distribution

[0516] The server collects production and shipping data via data provision APIs from local governments and companies.

[0517] The server uses scraping technology to obtain information from publicly available databases and websites.

[0518] Server: Organizing the data provided

[0519] The server categorizes the collected data by region, attaches detailed information (e.g., production volume, quality, price) and stores it in a supply database.

[0520] 2. Collecting and organizing demand data

[0521] Server: Collects demand data

[0522] The server uses APIs from search engines and social media platforms to collect trending information.

[0523] The server uses crawling technology to obtain the latest information from news sites and blogs.

[0524] Server: Organizing demand data

[0525] The server classifies the collected data by category (e.g., health foods, ecology, technology) and stores it in a demand database.

[0526] 3. Data matching and proposals

[0527] Server: Data matching process by generative AI

[0528] The generative AI on the server compares the supply database with the demand database and extracts highly relevant data.

[0529] Generative AI uses past success stories and trend-prediction algorithms to predict potential hit products.

[0530] Server: Generates proposal results

[0531] The server concretizes product ideas based on the AI ​​matching results and generates proposals that include details such as product concept, target market, and sales plan.

[0532] 4. Displaying the proposed results

[0533] Device: Display of suggested results

[0534] The user's (local government or company's) terminal receives the proposal results from the server and displays detailed information (product concept, target market, sales plan).

[0535] Users can create development plans for new specialty products based on these proposals.

[0536] Specific examples

[0537] For example, here is a specific example from Shizuoka Prefecture:

[0538] Supply Data Collection

[0539] Region: Shizuoka Prefecture

[0540] Items: Green tea, mandarin oranges, wasabi

[0541] Tourist attractions: hot springs, historical buildings

[0542] Demand data collection

[0543] Recent search trends: Healthy food, detox, low calorie

[0544] News article: As health consciousness grows, attention is focused on the benefits of green tea

[0545] Proposal example

[0546] 1. The server stores information about Shizuoka Prefecture's specialty products, green tea and mandarin oranges, in a supply database.

[0547] 2. The server stores in the demand database that "health foods" and "detox" are trending.

[0548] 3. The server's generation AI matches the detoxifying effects of green tea with trend information to generate new product ideas.

[0549] 4. The server generates a recommendation for a "detox drink using green tea" and sends it to the device.

[0550] 5. The user creates a development plan for a green tea drink based on the received proposal results.

[0551] In this way, the present invention efficiently proposes new specialty products that optimally match regional characteristics with consumer trends, enabling local governments and businesses to rapidly and effectively develop products.

[0552] The processing flow will be explained below.

[0553] Step 1: Gather supply data

[0554] Server: Collects production and shipping data from local governments and companies using APIs.

[0555] Server: Information is obtained from public databases and websites using scraping technology.

[0556] Server: Removes duplicates from the collected data and standardizes the data format.

[0557] Step 2: Organize and store supply data

[0558] Server: Classifies collected supply data by region and organizes goods, services, tourist resources, specialty products, and historical industry data.

[0559] Server: Attaches detailed information (e.g. production volume, quality, price) to each data item and stores it in a supply database.

[0560] Server: Creates indexes for stored data and optimizes search speed.

[0561] Step 3: Collect demand data

[0562] Server: Uses APIs of search engines and social media platforms to collect trend information.

[0563] Server: Obtains the latest information from news sites and blogs using crawling technology.

[0564] Server: Removes duplicates from the collected data and standardizes the data format.

[0565] Step 4: Organize and store demand data

[0566] Server: Classifies the collected demand data by category (e.g., health foods, ecology, technology).

[0567] Server: Attach detailed information (e.g., number of searches, frequency of mentions) to each piece of data and store it in the demand database.

[0568] Server: Creates indexes for stored data and optimizes search speed.

[0569] Step 5: Matching the data

[0570] Server: Uses generative AI to match supply and demand databases, automatically extracting relevant data.

[0571] Server: Generative AI analyzes data based on past successes and trend prediction algorithms to predict potential hit products.

[0572] Server: Organizes the matching results from AI and extracts product ideas that should be marketed.

[0573] Step 6: Generate proposal results

[0574] Server: Materializes the product ideas obtained from the matching results and generates detailed proposals (product concept, target market, sales plan).

[0575] Server: Compiles the generated proposal results into a report format for local governments and businesses.

[0576] Step 7: Viewing the Suggestion Results

[0577] Terminal: Receives the proposal results provided by the server.

[0578] Terminal: The proposal results are displayed so that users can view them. Detailed information (product concept, target market, sales plan) can be confirmed.

[0579] User: Based on the received proposals, a development plan for a new specialty product can be created.

[0580] Example 1

[0581] 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."

[0582] Currently, many regions and companies are struggling to effectively market their specialty products and services. One reason for this is that matching supply and demand takes time and effort, preventing appropriate product proposals from being made quickly. Furthermore, with global conditions and consumer trends constantly changing, it is difficult to determine which areas to focus on. In these circumstances, a system is needed that effectively integrates local characteristics with global trends and allows for fast and efficient product proposals.

[0583] 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.

[0584] In this invention, the server includes: a supply data collection means for collecting and organizing data on goods produced and shipped in the region; a demand data collection means for collecting and organizing data on web search history, news articles, information sharing platform posts, search trends, and international affairs; a means for constructing a supply database and a demand database; a means for matching the supply database and the demand database using generation AI and making new product proposals; a means for displaying the proposal results; a means for classifying supply data by region and storing it in the supply database with detailed information attached; a means for collecting trend information using the API of a search engine or information sharing platform; and a means for concretizing product ideas based on the matching process and generating proposal content such as a product concept, target market, and sales plan, thereby enabling fast and efficient product proposals for local specialty products and services through supply and demand matching.

[0585] "Supply data collection means" refers to a means for collecting and organizing data on goods produced and shipped in the region.

[0586] "Demand data collection means" refers to means for collecting and organizing data on web search history, news articles, posts on information sharing platforms, search trends, and international affairs.

[0587] The "supply database" is a database for storing and managing data on goods produced and shipped in the region.

[0588] A "demand database" is a database for storing and managing data related to demand.

[0589] "Generative AI" is a system that uses artificial intelligence technology to analyze data and perform matching and new product suggestions.

[0590] The "matching means" is a means for comparing the supply database and the demand database using generation AI to make new product proposals.

[0591] The "means for displaying proposal results" is a means for displaying the proposal results made by the generation AI to the user.

[0592] The "supply data classification means" is a means for classifying collected supply data by region, attaching detailed information, and storing the data in the supply database.

[0593] "Trend data collection means" refers to a means for collecting trend information using the APIs of search engines and information sharing platforms.

[0594] The "product idea realization means" is a means for realizing a product idea based on a matching process and generating proposal contents such as a product concept, target market, and sales plan.

[0595] This invention is a system that uses AI to match supply data, such as goods produced and shipped in a region and services provided, with demand data, such as web search history, news articles, posts on information sharing platforms, search trends, and international affairs, to discover and suggest products that should be marketed. This system is implemented using the following hardware and software.

[0596] 1. Collecting and organizing supply data

[0597] Server: Use of data provision API

[0598] The server uses a data provision API to collect supply data from local governments and companies. Specifically, it periodically obtains production and shipping data. The data is provided in JSON format and can be collected using an API client (e.g., an HTTP library).

[0599] Example: A server collects data on green tea production volume and quality from the Shizuoka Prefecture Agricultural Cooperative API.

[0600] Server: Use of scraping technology

[0601] The server obtains supply data from the public websites of local businesses using scraping techniques, for example, using an HTML parsing library to extract product pricing information and availability from specialty product pages.

[0602] Example: A server parses HTML from a company's specialties page to obtain pricing information for green tea.

[0603] Server: Classification of collected data

[0604] The server categorizes the collected data by region, attaches detailed information and stores it in a supply database, using a database management system (e.g., MySQL or PostgreSQL) for this process.

[0605] 2. Collecting and organizing demand data

[0606] Server: API collection of trend data

[0607] The server uses the Google Trends API and Twitter API to collect search trend information, which is then analyzed and stored in a demand database.

[0608] Example: The server uses the Google Trends API to collect search volume data for keywords related to "health foods" and "detox."

[0609] Server: Use of crawling techniques

[0610] The server crawls news sites and blogs to obtain the latest demand information, analyzes the information, categorizes it, and stores it in a demand database.

[0611] Example: A server crawls health-related articles from news sites and stores them in a demand database.

[0612] 3. Data matching and proposals

[0613] Server: Matching process by generation AI

[0614] A server-based generation AI (e.g., GPT-4) is used to match the supply database with the demand database, extracting highly relevant data based on keyword matches and correlations.

[0615] Example: Generative AI matches green tea supply data with "health food" trend information.

[0616] Server: Proposal generation

[0617] The server then creates a new product proposal based on the relevant data extracted by the generative AI, including details such as the product concept, target market, and sales plan.

[0618] Example: Generative AI generates product ideas for a "green tea detox drink" and creates a detailed sales plan.

[0619] 4. Displaying the proposed results

[0620] Terminal: Receiving and displaying the proposed results

[0621] The user's device receives the recommendation results from the server and displays detailed information. A dashboard-style UI is used, allowing the user to easily check the details of the recommended products.

[0622] Example: The user's terminal receives the proposal results from the server and displays the new product concept, target market, and sales plan.

[0623] Prompt Sentence Examples

[0624] An example of a prompt sentence input to a generative AI model:

[0625] "The supply data includes green tea and mandarin oranges produced in Shizuoka Prefecture. The current demand data includes health foods and detoxes, which are trending. Please use this data to propose new product ideas."

[0626] By efficiently matching supply and demand data, the system enables local specialties and services to enter the market quickly and effectively.

[0627] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0628] Step 1: Gather supply data

[0629] Server: Use of data provision API

[0630] The server uses a data provision API to collect supply data from local governments and companies. The server periodically sends requests to the API endpoint and obtains production volume and quality information in JSON format.

[0631] Input: API request

[0632] Output: JSON formatted supply data

[0633] Specifically, the server sends an HTTP request and analyzes the data obtained as a response.

[0634] Step 2: Scrape supply data

[0635] Server: Use of scraping technology

[0636] The server obtains supply data from publicly available websites of local businesses using scraping techniques, for example, using HTML parsing libraries to extract product pricing information and availability from specialty product pages.

[0637] Input: Webpage URL

[0638] Output: Extracted feed data

[0639] Specifically, the server accesses the web page, analyzes the HTML, and extracts the necessary data.

[0640] Step 3: Classify and store supply data

[0641] Server: Classification of collected data

[0642] The server categorizes the collected data by region and stores it in a supply database along with detailed information (production volume, quality, price).

[0643] Input: Supply data before classification

[0644] Output: Data to be inserted into the supply database

[0645] Specifically, the server classifies the data based on the region name and inserts a new record into the database.

[0646] Step 4: Collect demand data

[0647] Server: API collection of trend data

[0648] The server uses the Google Trends API and Twitter API to collect search trend information, which is then analyzed and stored in a demand database.

[0649] Input: API request

[0650] Output: Demand data in JSON format

[0651] Specifically, the server sends an API request and obtains trend information in JSON format.

[0652] Step 5: Crawl for demand data

[0653] Server: Use of crawling techniques

[0654] The server crawls news sites and blogs to obtain the latest demand information. The analyzed information is categorized and stored in a demand database.

[0655] Input: Website URL

[0656] Output: Retrieved demand data

[0657] Specifically, the server accesses the news site, analyzes the HTML, and extracts demand data.

[0658] Step 6: Classify and store demand data

[0659] Server: Classification of collected data

[0660] The server classifies the collected demand data into categories (healthy foods, ecology, technology, etc.) and stores them in a demand database.

[0661] Input: Demand data before classification

[0662] Output: Data to be inserted into the demand database

[0663] Specifically, the server categorizes the data based on the category name and inserts a new record into the database.

[0664] Step 7: Matching the data

[0665] Server: Matching by generative AI

[0666] The server-based AI compares the supply and demand databases to extract relevant data, then analyzes the data based on keyword matches and correlations.

[0667] Input: Supply data, Demand data

[0668] Output: Matching results

[0669] Specifically, the server uses generative AI to analyze supply and demand data and extract highly relevant pairs.

[0670] Step 8: Generate proposals

[0671] Server: Creating a concrete proposal

[0672] The server then uses the relevant data extracted by the generative AI to create new product ideas, including details such as the product concept, target market, and sales plan.

[0673] Input: Matching results

[0674] Output: Specific product suggestions

[0675] Specifically, the server analyzes the output of the generative AI and converts the product ideas into detailed proposal documents.

[0676] Step 9: Viewing the Suggestion Results

[0677] Terminal: Receiving and displaying the proposed results

[0678] The user's terminal receives the proposal results sent from the server and displays the detailed information.

[0679] Input: Proposal result data

[0680] Output: Display of proposal results

[0681] Specifically, the device receives data from the server and displays it on a dashboard-style UI.

[0682] Step 10: Use the proposal

[0683] User: Product development based on received results

[0684] The user makes a product development plan based on the received proposal results.

[0685] Input: Suggestion results

[0686] Output: Product development plan

[0687] Specifically, the user analyzes the proposal and provides feedback to the product development department.

[0688] (Application example 1)

[0689] 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."

[0690] Conventional systems were unable to effectively match data on locally produced and shipped goods and services provided with demand data, making it particularly difficult to utilize proposal results in real time. This meant that product proposals and inventory management in physical stores could not be carried out quickly, leading to the issue of being unable to respond promptly to customer needs.

[0691] 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.

[0692] In this invention, the server includes a supply data collection means for collecting and organizing data on goods produced and shipped in the region, a demand data collection means for collecting and organizing data on web search history, news articles, social media posts, search trends, and world affairs, a means for building a supply database and a demand database, a means for matching the supply database and the demand database with a generation AI to discover and propose products to be introduced, a means for displaying the proposal results, and a means for providing access to the proposal results in real time using a smart device.This enables product proposals and inventory management in physical stores to be carried out quickly and effectively, making it possible to respond to customer needs immediately.

[0693] "Supply data collection means" refers to a device or system that collects and organizes data on goods produced and shipped in a region.

[0694] "Demand data collection means" refers to a device or system that collects and organizes data on web search history, news articles, social media posts, search trends, and world events.

[0695] "Supply Database" refers to a database that stores collected supply data and stores detailed information categorized by region.

[0696] A "demand database" is a database that classifies collected demand data by category and stores trend information.

[0697] "Generative AI" is an artificial intelligence system that matches supply databases with demand databases to discover and propose products that should be marketed.

[0698] "Means for displaying proposal results" refers to a device or system for displaying proposals obtained by the generation AI to the user.

[0699] A "smart device" is a device that can connect to the Internet, such as a smartphone, smart glasses, or a head-mounted display.

[0700] "Means for providing real-time access to recommendation results" refers to a device or system that enables real-time access to the recommendation results of the generative AI using a smart device.

[0701] This invention collects supply data on goods produced and shipped in the region and services provided, and demand data such as web search history, news articles, social media posts, search trends, and world affairs, and organizes and stores them in a supply database and a demand database. This allows the generation AI to match the two databases, making it possible to efficiently discover and propose new products and services that should be introduced.

[0702] Program Overview

[0703] The server collects supply and demand data and uses AI to collate it, while smart devices (such as smartphones or smart glasses) display real-time recommendations, helping in-store operations.

[0704] Hardware and Software Used

[0705] Hardware: Servers, smart devices (smartphones, smart glasses, head-mounted displays)

[0706] software:

[0707] Python: Used for data collection and processing

[0708] Requests: Used to retrieve data from the API

[0709] JSON: A Data Interchange Format

[0710] Generative AI models: used to match data and generate recommendations

[0711] Data processing flow

[0712] The server uses APIs and crawling technology to collect supply data on goods produced and shipped in the region, as well as various demand data for services provided. The collected data is stored in a supply database and a demand database. A generative AI model compares these databases to generate relevant product and service recommendations. The results are delivered to smart devices in real time, enabling store employees to quickly make product recommendations to customers.

[0713] Specific examples

[0714] For example, consider a case where a customer wants health-conscious products at a brick-and-mortar store in Shizuoka Prefecture. The server collects supply data for green tea and mandarin oranges produced in Shizuoka Prefecture and stores it in a supply database. At the same time, it collects demand data on the trending health foods and detox products and stores it in a demand database. The generative AI matches these data and suggests a detox drink made with green tea. This suggestion is displayed in real time to employees through smart glasses, allowing them to provide immediate advice to the customer.

[0715] Prompt Sentence Examples

[0716] Based on local products and current trends, please suggest products to promote in-store. Please use the following data:

[0717] Supply data:

[0718] Green Tea

[0719] mandarin orange

[0720] Demand Data:

[0721] health food

[0722] Detox

[0723] Example output format:

[0724] Item: Green tea

[0725] Trend: Detoxification

[0726] Recommended action: Recommend this item in store

[0727] In this way, the present invention can optimally match regional characteristics with consumer trends, thereby realizing efficient product proposals and inventory management in physical stores.

[0728] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0729] Step 1:

[0730] The server collects data on goods produced and shipped in the region via data provision APIs from local governments and companies. It receives supply data from the API as input and obtains it as output. This obtained data includes production volume, quality, price, etc. Specifically, it calls the API to obtain data and then formats it.

[0731] Step 2:

[0732] The server collects data on web search history, news articles, social media posts, search trends, and world affairs. It receives demand data as input using each platform's API and web crawling technology, and obtains demand data as output. Specifically, it uses search engine APIs to collect trend information and crawls news sites for the latest information.

[0733] Step 3:

[0734] The server organizes the collected supply data and stores it in a supply database. It receives supply data as input and stores the formatted supply data as output in the supply database. Specifically, it classifies the data by region and attaches detailed information such as production volume and quality.

[0735] Step 4:

[0736] The server organizes the collected demand data and stores it in the demand database. It receives demand data as input and stores the formatted demand data as output in the demand database. Specifically, it classifies the data by category (e.g., health, ecology, technology) and stores it in the demand database.

[0737] Step 5:

[0738] The generative AI model on the server compares the supply and demand databases to extract highly relevant data. It receives the supply and demand databases as input and generates matching results as output. Specifically, it analyzes the supply and demand data based on prompt statements to identify highly relevant products and services.

[0739] Step 6:

[0740] The server concretizes product ideas based on the matching results of the generative AI model. It receives the matching results as input and generates a product concept, target market, and sales plan as output. Specifically, it creates detailed proposals by referring to past success stories and trends.

[0741] Step 7:

[0742] The smart device (e.g., smart glasses) receives the proposal results from the server and displays them to the user. It receives the proposal results from the server as input and displays them in the user's field of view as output. Specifically, it downloads data via the network and overlays the proposal results in the user's field of view.

[0743] Step 8:

[0744] The user (e.g., a store employee) proposes product details to the customer based on the proposal results displayed on the smart device. The user receives the proposal results on the smart device as input and makes product proposals to the customer as output. Specific operations include checking the displayed information and explaining the benefits and features of specific products to the customer.

[0745] 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.

[0746] This system collects supply data, such as goods produced and shipped locally and services provided, and organizes and stores it in a supply database. It also collects demand data, such as web search history, news articles, social media posts, search trends, and world events, and organizes and stores it in a demand database. It matches these two databases using generative AI to discover and recommend products that should be marketed. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it can optimize recommendation results based on the user's emotional data.

[0747] Program processing flow

[0748] 1. Collecting and organizing supply data

[0749] Server: Collects data for distribution

[0750] The server uses an API to collect production and shipping data from local governments and companies.

[0751] The server uses scraping technology to obtain information from publicly available databases and websites.

[0752] Server: Organizing the data provided

[0753] The server categorizes the collected data by region, attaches detailed information (e.g., production volume, quality, price) and stores it in a supply database.

[0754] The server standardizes the data format and deletes duplicate data.

[0755] 2. Collecting and organizing demand data

[0756] Server: Collects demand data

[0757] The server uses APIs from search engines and social media platforms to collect trending information.

[0758] The server uses crawling technology to obtain the latest information from news sites and blogs.

[0759] Server: Organizing demand data

[0760] The server classifies the collected data into categories (e.g., health foods, ecology, technology).

[0761] The server attaches detailed information (e.g., number of searches, frequency of mentions) to each piece of data and stores it in a demand database.

[0762] 3. Collecting and analyzing user emotion data

[0763] Server: Collects user emotion data

[0764] The server uses an emotion engine installed on the user's device to collect emotion data from the user's voice, facial expressions, input data, etc.

[0765] The server analyzes the collected emotion data in real time.

[0766] Server: Emotion data organization

[0767] The server organizes the emotion data by time axis and situation and stores it as an emotion database.

[0768] The server uses each user's past emotional data to create a foundation for optimizing future proposal results.

[0769] 4. Data matching and suggestions

[0770] Server: Data matching process by generative AI

[0771] The generative AI on the server compares the supply database with the demand database and automatically extracts highly relevant data.

[0772] Generative AI analyzes data based on past successes and trend-prediction algorithms to predict potential hit products.

[0773] Server: Generates proposal results taking into account user emotion data

[0774] The server combines the matching results of the generation AI with the user's emotional data to extract the optimal product ideas.

[0775] The server generates a proposal that includes details such as the product concept, target market, and sales plan.

[0776] 5. Displaying the proposed results

[0777] Device: Display of suggested results

[0778] The user's (local government or company's) terminal receives the proposal results from the server and displays detailed information (product concept, target market, sales plan).

[0779] Users can create development plans for new specialty products based on these proposals.

[0780] Specific examples

[0781] For example, here is a specific example from Shizuoka Prefecture:

[0782] Supply Data Collection

[0783] Region: Shizuoka Prefecture

[0784] Items: Green tea, mandarin oranges, wasabi

[0785] Tourist attractions: hot springs, historical buildings

[0786] Demand data collection

[0787] Recent search trends: Healthy food, detox, low calorie

[0788] News article: As health consciousness grows, attention is focused on the benefits of green tea

[0789] Collecting user emotion data

[0790] The emotion engine collects facial expressions and voice in real time while the user is reading a presented article related to green tea, and recognizes "positive" emotions.

[0791] Proposal example

[0792] 1. The server stores information about Shizuoka Prefecture's specialty products, green tea and mandarin oranges, in a supply database.

[0793] 2. The server stores in the demand database that "health foods" and "detox" are trending.

[0794] 3. Based on the emotion engine's recognition of the user's emotion as "positive," the server's generative AI matches the detoxifying effects of green tea with trend information to generate new product ideas.

[0795] 4. The server generates a recommendation for a "detox drink using green tea" and sends it to the device.

[0796] 5. The user creates a development plan for a green tea drink based on the received proposal results.

[0797] In this way, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to advance product development quickly and effectively.

[0798] The processing flow will be explained below.

[0799] Step 1: Gather supply data

[0800] Server: Uses API to collect production and shipping data from local governments and companies. Collected data includes product type, production volume, quality, price, etc.

[0801] Server: Uses scraping technology to obtain information from public databases and websites, including information on tourist attractions and local specialties.

[0802] Step 2: Organize and store supply data

[0803] Server: Categorizes the collected supply data by region and attaches detailed information, such as green tea, mandarin oranges, and wasabi in Shizuoka Prefecture.

[0804] Server: Standardize data formats and remove duplicate data.

[0805] Server: Stores the organized data in a serving database and indexes it to optimize search speed.

[0806] Step 3: Collect demand data

[0807] Server: Uses APIs of search engines and social media platforms to collect trending information, including search counts, mention frequency, and hot topics.

[0808] Server: Uses crawling technology to obtain the latest information from news sites and blogs, including information on health foods and ecology.

[0809] Step 4: Organize and store demand data

[0810] Server: Categorizes the collected demand data into categories, such as health foods, ecology, technology, etc.

[0811] Server: Standardize data formats and remove duplicate data.

[0812] Server: Stores organized data in a demand database and indexes it to optimize search speed.

[0813] Step 5: Collect and analyze user sentiment data

[0814] Server: Using the emotion engine installed on the user's device, it collects emotion data from the user's voice, facial expressions, input data, etc. For example, the user's facial expressions and voice are recognized through a camera or microphone.

[0815] Server: Analyzes collected emotion data in real time and identifies positive or negative emotions.

[0816] Server: Organizes emotion data by time axis and situation and stores it in an emotion database.

[0817] Step 6: Matching the data

[0818] Server: Uses generative AI to match supply and demand databases, automatically extracting relevant data.

[0819] Server: Generative AI analyzes data based on past successes and trend prediction algorithms to predict potential hit products, such as combining the detoxifying effects of green tea with current trends.

[0820] Step 7: Generate proposals taking into account user emotion data

[0821] Server: Combines the matching results of the generation AI with the user's emotional data to extract optimal product ideas. If the user shows "positive" emotions, this tendency is reflected.

[0822] Server: Generates proposals that include details such as product concept, target market, and sales plan.

[0823] Step 8: Viewing the Suggestion Results

[0824] Terminal: Receives the proposal results provided by the server.

[0825] User: View the proposal results and check detailed information (product concept, target market, sales plan).

[0826] User: Based on the received proposal, create a development plan for a new local specialty product. For example, start product development based on the received proposal for a "green tea detox drink."

[0827] Through the above steps, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to develop products quickly and effectively.

[0828] Example 2

[0829] 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."

[0830] Efficiently linking information on locally produced goods and services with demand information on the Internet and proposing new products and services that should be introduced is a difficult task for existing systems. Furthermore, making optimal proposals that take user emotions into account requires the collection and analysis of real-time, accurate emotional data. However, a system that can integrate this data and provide optimal proposals for each user has yet to be developed.

[0831] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting and organizing data on goods produced and shipped in a region, a means for collecting and organizing data on internet search history, news articles, social network posts, search trends, and world affairs, a means for matching a supply database and a demand database using artificial intelligence to discover and propose products that should be introduced, a means for collecting, analyzing, and organizing user emotion data, a means for optimizing proposal results based on the emotion data, and a means for displaying the proposal results. This enables effective and accurate product proposals by combining regional characteristics with real-time user emotion data.

[0832] "Supply data" refers to information including goods, services, tourism resources, and historical industry data produced and shipped in the region.

[0833] "Demand Data" is information including internet search history, news articles, social network posts, search trends, and world affairs data.

[0834] "Supply database" refers to a database that organizes and stores supply data.

[0835] A "demand database" is a database that organizes and stores demand data.

[0836] "Artificial intelligence" refers to algorithms and software that match supply and demand databases to discover and propose products that should be marketed.

[0837] "Emotion data" refers to emotional information collected from the user's voice, facial expression, input data, and the like.

[0838] The "emotion engine" is software for collecting, analyzing, and organizing user emotional data.

[0839] "Proposal results" are the specific products that AI has discovered and proposed for the market.

[0840] "Search trends" refers to data about the frequency and fluctuations of keywords and phrases that users search for on the Internet.

[0841] "Social network posts" are data that include user posts on social media platforms.

[0842] MODE FOR CARRYING OUT THE INVENTION

[0843] This invention is a system that collects supply data, such as goods produced and shipped in a region and services provided, and organizes and stores it in a supply database. It also collects demand data, such as internet search history, news articles, social network posts, search trends, and world events, and organizes and stores it in a demand database. These two databases are matched using artificial intelligence (AI) to discover and recommend products that should be marketed. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize recommendation results based on the user's emotional data.

[0844] Hardware and Software Configuration

[0845] The server uses the following hardware and software to implement this system:

[0846] Data collection module: This module periodically obtains production and shipping data from local governments and companies via API. Specifically, it uses HTTP requests.

[0847] Scraping tools: scraping data from public databases and websites using scraping techniques, using libraries such as BeautifulSoup and Scrapy.

[0848] Crawling tools: Crawling demand data from news sites and blogs, for example, using tools such as Selenium or Puppeteer.

[0849] Generative AI model: Used to match supply and demand databases and discover potential hit products. This is a model that applies natural language processing (NLP) technology, such as OpenAI's GPT model.

[0850] Emotion engine: Collects and analyzes emotional data in real time from the user's voice, facial expressions, input data, etc. For example, using Microsoft Azure Cognitive Services.

[0851] Database management system: A database for storing supply data and demand data, for example, MySQL or PostgreSQL.

[0852] Specific examples

[0853] For example, here is a specific example from Shizuoka Prefecture:

[0854] Supply data collection:

[0855] The server uses an API to collect production data on local specialties such as green tea, mandarin oranges, and wasabi from local governments and companies in Shizuoka Prefecture, and stores that information in a supply database.

[0856] In addition, information on green tea production volume and quality will be collected from publicly available databases and websites through scraping and stored in a supply database in a unified format.

[0857] Demand data collection:

[0858] The server uses an API to obtain the number of searches for keywords such as "health benefits of green tea" from search engines and stores the information in a demand database.

[0859] In addition, articles about health-consciousness are collected by crawling from news sites and blogs, categorized into "healthy foods," and stored in a demand database.

[0860] Collecting and analyzing sentiment data:

[0861] The server uses an emotion engine installed on the user's device to analyze the user's voice and facial expressions in real time while they are reading an article about green tea, and recognizes "positive" emotions.

[0862] Generative AI suggestions:

[0863] The server's generation AI matches green tea data from the supply database with health food trend data from the demand database to generate an idea for a new product: a "green tea drink with detoxifying effects."

[0864] Furthermore, based on the user's emotional data, the system generates optimal product concepts, target markets, and sales plans as proposals.

[0865] Viewing Suggested Results:

[0866] The user's device displays the proposal results received from the server, and the user can check details such as the product concept and sales plan for the "Green Tea Detox Drink."

[0867] Prompt Sentence Examples

[0868] "Please propose a new product idea that uses green tea, a specialty of Shizuoka Prefecture, and is in line with the health food trend. Please take into account user sentiment data and optimize the proposal results."

[0869] This enables the system to combine regional characteristics with real-time user emotional data to make effective and accurate product recommendations.

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

[0871] Step 1:

[0872] Supply Data Collection

[0873] The server uses an API to obtain production and shipping data from local governments and companies. For example, it obtains green tea production data for Shizuoka Prefecture through an HTTP request and saves it as a CSV file. It also uses scraping technology to collect data from publicly available databases and websites. The input is raw data obtained from the API or webpage, and the output is a list of the various types of collected data.

[0874] Step 2:

[0875] Supply data organization

[0876] The server classifies the collected data by region and standardizes the format. For example, it classifies green tea data into the "Shizuoka Prefecture" category and standardizes the weight unit to kg. It deletes any duplicate data and stores the organized data in the supply database. The input is the collected raw data, and the output is an organized, consistent dataset.

[0877] Step 3:

[0878] Demand data collection

[0879] The server collects demand data via APIs of search engines and social media platforms. For example, it obtains the number of searches for a specific keyword (e.g., "green tea health benefits") and saves this as trend data. At the same time, it also collects data from news sites and blogs by crawling. The input is trend data on the Internet, and the output is a list of the collected demand data.

[0880] Step 4:

[0881] Organizing demand data

[0882] The server categorizes the collected demand data by category and standardizes the format. For example, it stores the data in categories such as "healthy foods" and "ecology" and attaches search and mention frequency information. The input is raw data, and the output is an organized demand dataset.

[0883] Step 5:

[0884] Collecting user emotion data

[0885] The server uses an emotion engine installed on the user's device to collect emotion data in real time from the user's voice and facial expressions. For example, a camera captures the user's facial expression while reading an article about green tea and recognizes the emotion as "positive." The input is the user's real-time emotion data, and the output is classified emotion data.

[0886] Step 6:

[0887] Analyzing and organizing emotion data

[0888] The server organizes the collected emotional data by timeline and situation, and creates a basis for optimizing future proposals by referring to past data. For example, it stores data such as "positive reaction after reading an article about green tea at 10:30 on October 15, 2023." The input is emotional data collected in real time, and the output is an analyzed and organized emotional dataset.

[0889] Step 7:

[0890] Data matching by generative AI

[0891] The server's generation AI compares the supply database with the demand database and extracts highly relevant data. For example, it matches "green tea" information from the supply database with "health food trends" information from the demand database. The input is supply data and demand data, and the output is a new product idea as a result of the matching.

[0892] Step 8:

[0893] Generating proposal results taking into account user emotion data

[0894] The server combines the matching results of the generation AI with the user's emotional data to extract optimal product ideas. For example, if the user expresses positive feelings toward green tea, it generates a suggestion for "green tea detox drink." The input is the matching results and emotional data, and the output is a detailed suggestion.

[0895] Step 9:

[0896] Sending the proposal results to the device

[0897] The server sends the generated proposal results to the user's device. For example, it sends the proposal document in JSON format to the device and makes it viewable. The input is the generated proposal results, and the output is the transmitted data.

[0898] Step 10:

[0899] Displaying the proposed results

[0900] The user's terminal displays the proposal results received from the server. For example, a specific product concept or sales plan is displayed on the screen. The input is the proposal results sent from the server, and the output is the displayed information.

[0901] (Application example 2)

[0902] 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."

[0903] Existing product development platforms are limited to simply matching supply and demand data and do not take user sentiment into account. This makes it difficult to propose products that accurately reflect consumers' latent needs. It is also difficult to maximize the appeal of local specialties and develop products that respond to trends in real time. This hinders improvements in sales efficiency and the rapid launch of new products.

[0904] 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.

[0905] In this invention, the server includes a supply data collection means for collecting and organizing data on goods produced and shipped in the region; a demand data collection means for collecting and organizing data on web search history, news articles, social media posts, search trends, and world affairs; a means for building a supply database and a demand database; a means for matching the supply database and the demand database using generative AI to discover and propose products to be introduced; an emotion data collection means for collecting and analyzing user emotion data in real time; a means for optimizing proposal results taking into account the collected emotion data; and a means for displaying the proposal results. This enables accurate product proposals that take into account user emotion in addition to matching supply data and demand data. Furthermore, it is possible to maximize the appeal of regional specialty products and quickly bring new products that are in line with trends to market, which is expected to improve sales efficiency.

[0906] "Supply data collection means" refers to a means for collecting and organizing data on goods produced and shipped in the region.

[0907] "Demand data collection methods" are methods for collecting and organizing data on web search history, news articles, social media posts, search trends, and world events.

[0908] A "supply database" is a database for storing and managing collected supply data.

[0909] A "demand database" is a database for storing and managing collected demand data.

[0910] "Generative AI" is artificial intelligence that collates supply and demand databases and analyzes relevant data.

[0911] The "emotion data collection means" is a means for collecting emotion data from the user's voice, facial expression, input data, etc., and analyzing it in real time.

[0912] The "means for displaying the proposed results" is a means for displaying to the user the product information proposed as a result of analysis by the generation AI.

[0913] A system for implementing the present invention collects supply data, such as goods produced and shipped in a region and services provided, and organizes and stores it in a supply database. It also collects demand data, such as web search history, news articles, social media posts, search trends, and world events, and organizes and stores it in a demand database. The system matches these two databases using generative AI to discover and recommend products that should be marketed. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it can optimize recommendation results based on the user's emotion data.

[0914] System Configuration

[0915] 1. Hardware to be used

[0916] Server (operation of database and generative AI)

[0917] Smartphones and tablets (for the user interface)

[0918] 2. Software to be used

[0919] Database management systems (e.g., MySQL, PostgreSQL)

[0920] Crawling tools for collecting data from news sites, etc. (e.g., Scrapy)

[0921] Emotion engine libraries (e.g., Microsoft Azure Emotion API, Google Cloud Vision API)

[0922] Machine learning libraries (e.g. TensorFlow, PyTorch)

[0923] Web development frameworks (e.g., Django, Flask)

[0924] Program processing flow

[0925] The server uses supply data collection tools to collect production and shipping data from local governments and companies. It also uses scraping technology to obtain information from publicly available databases and websites. The collected data is categorized by region, and detailed information is stored in the supply database.

[0926] Next, the server uses demand data collection means to collect trend information using APIs of search engines and social media platforms, and also obtains data from the latest news sites and blogs using crawling technology, categorizes each piece of information, and stores the detailed information in a demand database.

[0927] Users' emotional data is collected using an emotion engine in an application on a smartphone or tablet. The engine collects users' voices, facial expressions, input data, etc. in real time, analyzes and organizes the emotional data, and stores it in an emotion database.

[0928] The server uses generative AI to match supply and demand databases and automatically extract relevant data. It analyzes the data based on past successes and trend prediction algorithms to predict potential hit products. By taking into account emotional data, it extracts optimal product ideas based on user sentiment and generates proposals that include details such as product concept, target market, and sales plan.

[0929] The proposal results are displayed on the user's smartphone or tablet, and the user can use these results to develop new products and sales strategies.

[0930] Specific examples

[0931] For example, here is a specific example from Shizuoka Prefecture:

[0932] When collecting supply data, information on Shizuoka Prefecture's specialty products, green tea, mandarin oranges, and wasabi, is stored in the supply database. When collecting demand data, the fact that health foods and detoxes are trending is stored in the demand database. When the emotion engine recognizes the user's emotion as "positive," the server's generation AI matches the detox effects of green tea with trend information to generate new product ideas.

[0933] The server generates a proposal for a "detox drink using green tea" and sends it to the user's device. The user can then create a development plan for the green tea drink based on the proposal received.

[0934] Example prompt sentence:

[0935] Please propose new product ideas based on the following supply and demand data. The supply data includes green tea, mandarin oranges, and wasabi from Shizuoka Prefecture. The demand data includes "healthy food," "detox," and "low calorie." Users indicate positive sentiment. Extract the best product ideas and propose a product concept, target market, and sales plan.

[0936] In this way, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to advance product development quickly and effectively.

[0937] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0938] Step 1:

[0939] The server collects production and shipping data provided by local governments and companies using supply data collection methods. Specifically, it obtains data using APIs and collects information from public databases and web pages using scraping technology. The collected data is categorized by region and stored in a supply database.

[0940] Input: Production and shipping data from local governments and companies, information from public databases

[0941] Data processing: Classification by region, removal of duplicate data, unification of format

[0942] Output: Supply database

[0943] Step 2:

[0944] The server collects data on web search history, news articles, social media posts, search trends, and world affairs using demand data collection methods. Specifically, it obtains trend information using search engine and social media APIs, and collects data from news sites and blogs using crawling technology. The collected data is categorized and stored in a demand database.

[0945] Input: Web search history, news articles, social media posts, search trends, world events

[0946] Data processing: Classification by category, addition of detailed information (number of searches, frequency of mentions)

[0947] Output: Demand database

[0948] Step 3:

[0949] An emotion engine is used in an application installed on the user's device to collect the user's emotional data. Specifically, voice, facial expressions, and input data are collected and analyzed in real time and stored in an emotion database. The emotional data is organized by time axis and situation.

[0950] Input: User's voice, facial expressions, input data

[0951] Data calculation: Real-time analysis of emotional data, organizing it by time axis and situation

[0952] Output: Emotion database

[0953] Step 4:

[0954] The server uses generative AI to match supply and demand databases and automatically extract relevant data. Specifically, it compares supply and demand data and analyzes the data based on trend prediction algorithms, thereby predicting potential hit products.

[0955] Input: Supply database, Demand database

[0956] Data calculation: Matching supply and demand, data analysis using trend prediction algorithms

[0957] Output: A list of potential hits

[0958] Step 5:

[0959] The server uses the collected emotional data to extract optimal product ideas based on the matching results of the generative AI. Specifically, it adds the emotional data to the analysis results of the generative AI to generate proposals that include details such as the product concept, target market, and sales plan.

[0960] Input: sentiment database, list of potential hit products

[0961] Data calculation: Generate product ideas that reflect emotional data and create detailed proposals

[0962] Output: Optimal product ideas and proposals

[0963] Step 6:

[0964] The proposal results are displayed on the user's device. Specifically, the product ideas and proposal content generated by the server are sent to a smartphone or tablet application and visually displayed to the user. The user can then formulate new product development and sales strategies based on these proposal results.

[0965] Input: Optimal product ideas and proposals

[0966] Action: Sends suggestions and displays them on smartphones and tablets

[0967] Output: Displayed suggestion results

[0968] This series of processes not only optimally matches regional characteristics with consumer trends, but also combines user emotional data to provide more accurate proposal results, enabling local governments and companies to develop products quickly and effectively.

[0969] 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.

[0970] 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.

[0971] 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.

[0972] [Third embodiment]

[0973] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0974] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0975] 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).

[0976] 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.

[0977] 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.

[0978] 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).

[0979] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0980] 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.

[0981] 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.

[0982] 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.

[0983] 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.

[0984] 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."

[0985] This system collects supply data such as goods produced and shipped in the region and services provided, organizes it, and stores it in a supply database. It also collects demand data such as web search history, news articles, social media posts, search trends, and world events, organizes it, and stores it in a demand database. It matches these two databases using generative AI to discover and suggest products that should be marketed.

[0986] Program processing flow

[0987] 1. Collecting and organizing supply data

[0988] Server: Collects data for distribution

[0989] The server collects production and shipping data via data provision APIs from local governments and companies.

[0990] The server uses scraping technology to obtain information from publicly available databases and websites.

[0991] Server: Organizing the data provided

[0992] The server categorizes the collected data by region, attaches detailed information (e.g., production volume, quality, price) and stores it in a supply database.

[0993] 2. Collecting and organizing demand data

[0994] Server: Collects demand data

[0995] The server uses APIs from search engines and social media platforms to collect trending information.

[0996] The server uses crawling technology to obtain the latest information from news sites and blogs.

[0997] Server: Organizing demand data

[0998] The server classifies the collected data by category (e.g., health foods, ecology, technology) and stores it in a demand database.

[0999] 3. Data matching and proposals

[1000] Server: Data matching process by generative AI

[1001] The generative AI on the server compares the supply database with the demand database and extracts highly relevant data.

[1002] Generative AI uses past success stories and trend-prediction algorithms to predict potential hit products.

[1003] Server: Generates proposal results

[1004] The server concretizes product ideas based on the AI ​​matching results and generates proposals that include details such as product concept, target market, and sales plan.

[1005] 4. Displaying the proposed results

[1006] Device: Display of suggested results

[1007] The user's (local government or company's) terminal receives the proposal results from the server and displays detailed information (product concept, target market, sales plan).

[1008] Users can create development plans for new specialty products based on these proposals.

[1009] Specific examples

[1010] For example, here is a specific example from Shizuoka Prefecture:

[1011] Supply Data Collection

[1012] Region: Shizuoka Prefecture

[1013] Items: Green tea, mandarin oranges, wasabi

[1014] Tourist attractions: hot springs, historical buildings

[1015] Demand data collection

[1016] Recent search trends: Healthy food, detox, low calorie

[1017] News article: As health consciousness grows, attention is focused on the benefits of green tea

[1018] Proposal example

[1019] 1. The server stores information about Shizuoka Prefecture's specialty products, green tea and mandarin oranges, in a supply database.

[1020] 2. The server stores in the demand database that "health foods" and "detox" are trending.

[1021] 3. The server's generation AI matches the detoxifying effects of green tea with trend information to generate new product ideas.

[1022] 4. The server generates a recommendation for a "detox drink using green tea" and sends it to the device.

[1023] 5. The user creates a development plan for a green tea drink based on the received proposal results.

[1024] In this way, the present invention efficiently proposes new specialty products that optimally match regional characteristics with consumer trends, enabling local governments and businesses to rapidly and effectively develop products.

[1025] The processing flow will be explained below.

[1026] Step 1: Gather supply data

[1027] Server: Collects production and shipping data from local governments and companies using APIs.

[1028] Server: Information is obtained from public databases and websites using scraping technology.

[1029] Server: Removes duplicates from the collected data and standardizes the data format.

[1030] Step 2: Organize and store supply data

[1031] Server: Classifies collected supply data by region and organizes goods, services, tourist resources, specialty products, and historical industry data.

[1032] Server: Attaches detailed information (e.g. production volume, quality, price) to each data item and stores it in a supply database.

[1033] Server: Creates indexes for stored data and optimizes search speed.

[1034] Step 3: Collect demand data

[1035] Server: Uses APIs of search engines and social media platforms to collect trend information.

[1036] Server: Obtains the latest information from news sites and blogs using crawling technology.

[1037] Server: Removes duplicates from the collected data and standardizes the data format.

[1038] Step 4: Organize and store demand data

[1039] Server: Classifies the collected demand data by category (e.g., health foods, ecology, technology).

[1040] Server: Attach detailed information (e.g., number of searches, frequency of mentions) to each piece of data and store it in the demand database.

[1041] Server: Creates indexes for stored data and optimizes search speed.

[1042] Step 5: Matching the data

[1043] Server: Uses generative AI to match supply and demand databases, automatically extracting relevant data.

[1044] Server: Generative AI analyzes data based on past successes and trend prediction algorithms to predict potential hit products.

[1045] Server: Organizes the matching results from AI and extracts product ideas that should be marketed.

[1046] Step 6: Generate proposal results

[1047] Server: Materializes the product ideas obtained from the matching results and generates detailed proposals (product concept, target market, sales plan).

[1048] Server: Compiles the generated proposal results into a report format for local governments and businesses.

[1049] Step 7: Viewing the Suggestion Results

[1050] Terminal: Receives the proposal results provided by the server.

[1051] Terminal: The proposal results are displayed so that users can view them. Detailed information (product concept, target market, sales plan) can be confirmed.

[1052] User: Based on the received proposals, a development plan for a new specialty product can be created.

[1053] Example 1

[1054] 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."

[1055] Currently, many regions and companies are struggling to effectively market their specialty products and services. One reason for this is that matching supply and demand takes time and effort, preventing appropriate product proposals from being made quickly. Furthermore, with global conditions and consumer trends constantly changing, it is difficult to determine which areas to focus on. In these circumstances, a system is needed that effectively integrates local characteristics with global trends and allows for fast and efficient product proposals.

[1056] 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.

[1057] In this invention, the server includes: a supply data collection means for collecting and organizing data on goods produced and shipped in the region; a demand data collection means for collecting and organizing data on web search history, news articles, information sharing platform posts, search trends, and international affairs; a means for constructing a supply database and a demand database; a means for matching the supply database and the demand database using generation AI and making new product proposals; a means for displaying the proposal results; a means for classifying supply data by region and storing it in the supply database with detailed information attached; a means for collecting trend information using the API of a search engine or information sharing platform; and a means for concretizing product ideas based on the matching process and generating proposal content such as a product concept, target market, and sales plan, thereby enabling fast and efficient product proposals for local specialty products and services through supply and demand matching.

[1058] "Supply data collection means" refers to a means for collecting and organizing data on goods produced and shipped in the region.

[1059] "Demand data collection means" refers to means for collecting and organizing data on web search history, news articles, posts on information sharing platforms, search trends, and international affairs.

[1060] The "supply database" is a database for storing and managing data on goods produced and shipped in the region.

[1061] A "demand database" is a database for storing and managing data related to demand.

[1062] "Generative AI" is a system that uses artificial intelligence technology to analyze data and perform matching and new product suggestions.

[1063] The "matching means" is a means for comparing the supply database and the demand database using generation AI to make new product proposals.

[1064] The "means for displaying proposal results" is a means for displaying the proposal results made by the generation AI to the user.

[1065] The "supply data classification means" is a means for classifying collected supply data by region, attaching detailed information, and storing the data in the supply database.

[1066] "Trend data collection means" refers to a means for collecting trend information using the APIs of search engines and information sharing platforms.

[1067] The "product idea realization means" is a means for realizing a product idea based on a matching process and generating proposal contents such as a product concept, target market, and sales plan.

[1068] This invention is a system that uses AI to match supply data, such as goods produced and shipped in a region and services provided, with demand data, such as web search history, news articles, posts on information sharing platforms, search trends, and international affairs, to discover and suggest products that should be marketed. This system is implemented using the following hardware and software.

[1069] 1. Collecting and organizing supply data

[1070] Server: Use of data provision API

[1071] The server uses a data provision API to collect supply data from local governments and companies. Specifically, it periodically obtains production and shipping data. The data is provided in JSON format and can be collected using an API client (e.g., an HTTP library).

[1072] Example: A server collects data on green tea production volume and quality from the Shizuoka Prefecture Agricultural Cooperative API.

[1073] Server: Use of scraping technology

[1074] The server obtains supply data from the public websites of local businesses using scraping techniques, for example, using an HTML parsing library to extract product pricing information and availability from specialty product pages.

[1075] Example: A server parses HTML from a company's specialties page to obtain pricing information for green tea.

[1076] Server: Classification of collected data

[1077] The server categorizes the collected data by region, attaches detailed information and stores it in a supply database, using a database management system (e.g., MySQL or PostgreSQL) for this process.

[1078] 2. Collecting and organizing demand data

[1079] Server: API collection of trend data

[1080] The server uses the Google Trends API and Twitter API to collect search trend information, which is then analyzed and stored in a demand database.

[1081] Example: The server uses the Google Trends API to collect search volume data for keywords related to "health foods" and "detox."

[1082] Server: Use of crawling techniques

[1083] The server crawls news sites and blogs to obtain the latest demand information, analyzes the information, categorizes it, and stores it in a demand database.

[1084] Example: A server crawls health-related articles from news sites and stores them in a demand database.

[1085] 3. Data matching and proposals

[1086] Server: Matching process by generation AI

[1087] A server-based generation AI (e.g., GPT-4) is used to match the supply database with the demand database, extracting highly relevant data based on keyword matches and correlations.

[1088] Example: Generative AI matches green tea supply data with "health food" trend information.

[1089] Server: Proposal generation

[1090] The server then creates a new product proposal based on the relevant data extracted by the generative AI, including details such as the product concept, target market, and sales plan.

[1091] Example: Generative AI generates product ideas for a "green tea detox drink" and creates a detailed sales plan.

[1092] 4. Displaying the proposed results

[1093] Terminal: Receiving and displaying the proposed results

[1094] The user's device receives the recommendation results from the server and displays detailed information. A dashboard-style UI is used, allowing the user to easily check the details of the recommended products.

[1095] Example: The user's terminal receives the proposal results from the server and displays the new product concept, target market, and sales plan.

[1096] Prompt Sentence Examples

[1097] An example of a prompt sentence input to a generative AI model:

[1098] "The supply data includes green tea and mandarin oranges produced in Shizuoka Prefecture. The current demand data includes health foods and detoxes, which are trending. Please use this data to propose new product ideas."

[1099] By efficiently matching supply and demand data, the system enables local specialties and services to enter the market quickly and effectively.

[1100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1101] Step 1: Gather supply data

[1102] Server: Use of data provision API

[1103] The server uses a data provision API to collect supply data from local governments and companies. The server periodically sends requests to the API endpoint and obtains production volume and quality information in JSON format.

[1104] Input: API request

[1105] Output: JSON formatted supply data

[1106] Specifically, the server sends an HTTP request and analyzes the data obtained as a response.

[1107] Step 2: Scrape supply data

[1108] Server: Use of scraping technology

[1109] The server obtains supply data from publicly available websites of local businesses using scraping techniques, for example, using HTML parsing libraries to extract product pricing information and availability from specialty product pages.

[1110] Input: Webpage URL

[1111] Output: Extracted feed data

[1112] Specifically, the server accesses the web page, analyzes the HTML, and extracts the necessary data.

[1113] Step 3: Classify and store supply data

[1114] Server: Classification of collected data

[1115] The server categorizes the collected data by region and stores it in a supply database along with detailed information (production volume, quality, price).

[1116] Input: Supply data before classification

[1117] Output: Data to be inserted into the supply database

[1118] Specifically, the server classifies the data based on the region name and inserts a new record into the database.

[1119] Step 4: Collect demand data

[1120] Server: API collection of trend data

[1121] The server uses the Google Trends API and Twitter API to collect search trend information, which is then analyzed and stored in a demand database.

[1122] Input: API request

[1123] Output: Demand data in JSON format

[1124] Specifically, the server sends an API request and obtains trend information in JSON format.

[1125] Step 5: Crawl for demand data

[1126] Server: Use of crawling techniques

[1127] The server crawls news sites and blogs to obtain the latest demand information. The analyzed information is categorized and stored in a demand database.

[1128] Input: Website URL

[1129] Output: Retrieved demand data

[1130] Specifically, the server accesses the news site, analyzes the HTML, and extracts demand data.

[1131] Step 6: Classify and store demand data

[1132] Server: Classification of collected data

[1133] The server classifies the collected demand data into categories (healthy foods, ecology, technology, etc.) and stores them in a demand database.

[1134] Input: Demand data before classification

[1135] Output: Data to be inserted into the demand database

[1136] Specifically, the server categorizes the data based on the category name and inserts a new record into the database.

[1137] Step 7: Matching the data

[1138] Server: Matching by generative AI

[1139] The server-based AI compares the supply and demand databases to extract relevant data, then analyzes the data based on keyword matches and correlations.

[1140] Input: Supply data, Demand data

[1141] Output: Matching results

[1142] Specifically, the server uses generative AI to analyze supply and demand data and extract highly relevant pairs.

[1143] Step 8: Generate proposals

[1144] Server: Creating a concrete proposal

[1145] The server then uses the relevant data extracted by the generative AI to create new product ideas, including details such as the product concept, target market, and sales plan.

[1146] Input: Matching results

[1147] Output: Specific product suggestions

[1148] Specifically, the server analyzes the output of the generative AI and converts the product ideas into detailed proposal documents.

[1149] Step 9: Viewing the Suggestion Results

[1150] Terminal: Receiving and displaying the proposed results

[1151] The user's terminal receives the proposal results sent from the server and displays the detailed information.

[1152] Input: Proposal result data

[1153] Output: Display of proposal results

[1154] Specifically, the device receives data from the server and displays it on a dashboard-style UI.

[1155] Step 10: Use the proposal

[1156] User: Product development based on received results

[1157] The user makes a product development plan based on the received proposal results.

[1158] Input: Suggestion results

[1159] Output: Product development plan

[1160] Specifically, the user analyzes the proposal and provides feedback to the product development department.

[1161] (Application example 1)

[1162] 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."

[1163] Conventional systems were unable to effectively match data on locally produced and shipped goods and services provided with demand data, making it particularly difficult to utilize proposal results in real time. This meant that product proposals and inventory management in physical stores could not be carried out quickly, leading to the issue of being unable to respond promptly to customer needs.

[1164] 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.

[1165] In this invention, the server includes a supply data collection means for collecting and organizing data on goods produced and shipped in the region, a demand data collection means for collecting and organizing data on web search history, news articles, social media posts, search trends, and world affairs, a means for building a supply database and a demand database, a means for matching the supply database and the demand database with a generation AI to discover and propose products to be introduced, a means for displaying the proposal results, and a means for providing access to the proposal results in real time using a smart device.This enables product proposals and inventory management in physical stores to be carried out quickly and effectively, making it possible to respond to customer needs immediately.

[1166] "Supply data collection means" refers to a device or system that collects and organizes data on goods produced and shipped in a region.

[1167] "Demand data collection means" refers to a device or system that collects and organizes data on web search history, news articles, social media posts, search trends, and world events.

[1168] "Supply Database" refers to a database that stores collected supply data and stores detailed information categorized by region.

[1169] A "demand database" is a database that classifies collected demand data by category and stores trend information.

[1170] "Generative AI" is an artificial intelligence system that matches supply databases with demand databases to discover and propose products that should be marketed.

[1171] "Means for displaying proposal results" refers to a device or system for displaying proposals obtained by the generation AI to the user.

[1172] A "smart device" is a device that can connect to the Internet, such as a smartphone, smart glasses, or a head-mounted display.

[1173] "Means for providing real-time access to recommendation results" refers to a device or system that enables real-time access to the recommendation results of the generative AI using a smart device.

[1174] This invention collects supply data on goods produced and shipped in the region and services provided, and demand data such as web search history, news articles, social media posts, search trends, and world affairs, and organizes and stores them in a supply database and a demand database. This allows the generation AI to match the two databases, making it possible to efficiently discover and propose new products and services that should be introduced.

[1175] Program Overview

[1176] The server collects supply and demand data and uses AI to collate it, while smart devices (such as smartphones or smart glasses) display real-time recommendations, helping in-store operations.

[1177] Hardware and Software Used

[1178] Hardware: Servers, smart devices (smartphones, smart glasses, head-mounted displays)

[1179] software:

[1180] Python: Used for data collection and processing

[1181] Requests: Used to retrieve data from the API

[1182] JSON: A Data Interchange Format

[1183] Generative AI models: used to match data and generate recommendations

[1184] Data processing flow

[1185] The server uses APIs and crawling technology to collect supply data on goods produced and shipped in the region, as well as various demand data for services provided. The collected data is stored in a supply database and a demand database. A generative AI model compares these databases to generate relevant product and service recommendations. The results are delivered to smart devices in real time, enabling store employees to quickly make product recommendations to customers.

[1186] Specific examples

[1187] For example, consider a case where a customer wants health-conscious products at a brick-and-mortar store in Shizuoka Prefecture. The server collects supply data for green tea and mandarin oranges produced in Shizuoka Prefecture and stores it in a supply database. At the same time, it collects demand data on the trending health foods and detox products and stores it in a demand database. The generative AI matches these data and suggests a detox drink made with green tea. This suggestion is displayed in real time to employees through smart glasses, allowing them to provide immediate advice to the customer.

[1188] Prompt Sentence Examples

[1189] Based on local products and current trends, please suggest products to promote in-store. Please use the following data:

[1190] Supply data:

[1191] Green Tea

[1192] mandarin orange

[1193] Demand Data:

[1194] health food

[1195] Detox

[1196] Example output format:

[1197] Item: Green tea

[1198] Trend: Detoxification

[1199] Recommended action: Recommend this item in store

[1200] In this way, the present invention can optimally match regional characteristics with consumer trends, thereby realizing efficient product proposals and inventory management in physical stores.

[1201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1202] Step 1:

[1203] The server collects data on goods produced and shipped in the region via data provision APIs from local governments and companies. It receives supply data from the API as input and obtains it as output. This obtained data includes production volume, quality, price, etc. Specifically, it calls the API to obtain data and then formats it.

[1204] Step 2:

[1205] The server collects data on web search history, news articles, social media posts, search trends, and world affairs. It receives demand data as input using each platform's API and web crawling technology, and obtains demand data as output. Specifically, it uses search engine APIs to collect trend information and crawls news sites for the latest information.

[1206] Step 3:

[1207] The server organizes the collected supply data and stores it in a supply database. It receives supply data as input and stores the formatted supply data as output in the supply database. Specifically, it classifies the data by region and attaches detailed information such as production volume and quality.

[1208] Step 4:

[1209] The server organizes the collected demand data and stores it in the demand database. It receives demand data as input and stores the formatted demand data as output in the demand database. Specifically, it classifies the data by category (e.g., health, ecology, technology) and stores it in the demand database.

[1210] Step 5:

[1211] The generative AI model on the server compares the supply and demand databases to extract highly relevant data. It receives the supply and demand databases as input and generates matching results as output. Specifically, it analyzes the supply and demand data based on prompt statements to identify highly relevant products and services.

[1212] Step 6:

[1213] The server concretizes product ideas based on the matching results of the generative AI model. It receives the matching results as input and generates a product concept, target market, and sales plan as output. Specifically, it creates detailed proposals by referring to past success stories and trends.

[1214] Step 7:

[1215] The smart device (e.g., smart glasses) receives the proposal results from the server and displays them to the user. It receives the proposal results from the server as input and displays them in the user's field of view as output. Specifically, it downloads data via the network and overlays the proposal results in the user's field of view.

[1216] Step 8:

[1217] The user (e.g., a store employee) proposes product details to the customer based on the proposal results displayed on the smart device. The user receives the proposal results on the smart device as input and makes product proposals to the customer as output. Specific operations include checking the displayed information and explaining the benefits and features of specific products to the customer.

[1218] 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.

[1219] This system collects supply data, such as goods produced and shipped locally and services provided, and organizes and stores it in a supply database. It also collects demand data, such as web search history, news articles, social media posts, search trends, and world events, and organizes and stores it in a demand database. It matches these two databases using generative AI to discover and recommend products that should be marketed. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it can optimize recommendation results based on the user's emotional data.

[1220] Program processing flow

[1221] 1. Collecting and organizing supply data

[1222] Server: Collects data for distribution

[1223] The server uses an API to collect production and shipping data from local governments and companies.

[1224] The server uses scraping technology to obtain information from publicly available databases and websites.

[1225] Server: Organizing the data provided

[1226] The server categorizes the collected data by region, attaches detailed information (e.g., production volume, quality, price) and stores it in a supply database.

[1227] The server standardizes the data format and deletes duplicate data.

[1228] 2. Collecting and organizing demand data

[1229] Server: Collects demand data

[1230] The server uses APIs from search engines and social media platforms to collect trending information.

[1231] The server uses crawling technology to obtain the latest information from news sites and blogs.

[1232] Server: Organizing demand data

[1233] The server classifies the collected data into categories (e.g., health foods, ecology, technology).

[1234] The server attaches detailed information (e.g., number of searches, frequency of mentions) to each piece of data and stores it in a demand database.

[1235] 3. Collecting and analyzing user emotion data

[1236] Server: Collects user emotion data

[1237] The server uses an emotion engine installed on the user's device to collect emotion data from the user's voice, facial expressions, input data, etc.

[1238] The server analyzes the collected emotion data in real time.

[1239] Server: Emotion data organization

[1240] The server organizes the emotion data by time axis and situation and stores it as an emotion database.

[1241] The server uses each user's past emotional data to create a foundation for optimizing future proposal results.

[1242] 4. Data matching and suggestions

[1243] Server: Data matching process by generative AI

[1244] The generative AI on the server compares the supply database with the demand database and automatically extracts highly relevant data.

[1245] Generative AI analyzes data based on past successes and trend-prediction algorithms to predict potential hit products.

[1246] Server: Generates proposal results taking into account user emotion data

[1247] The server combines the matching results of the generation AI with the user's emotional data to extract the optimal product ideas.

[1248] The server generates a proposal that includes details such as the product concept, target market, and sales plan.

[1249] 5. Displaying the proposed results

[1250] Device: Display of suggested results

[1251] The user's (local government or company's) terminal receives the proposal results from the server and displays detailed information (product concept, target market, sales plan).

[1252] Users can create development plans for new specialty products based on these proposals.

[1253] Specific examples

[1254] For example, here is a specific example from Shizuoka Prefecture:

[1255] Supply Data Collection

[1256] Region: Shizuoka Prefecture

[1257] Items: Green tea, mandarin oranges, wasabi

[1258] Tourist attractions: hot springs, historical buildings

[1259] Demand data collection

[1260] Recent search trends: Healthy food, detox, low calorie

[1261] News article: As health consciousness grows, attention is focused on the benefits of green tea

[1262] Collecting user emotion data

[1263] The emotion engine collects facial expressions and voice in real time while the user is reading a presented article related to green tea, and recognizes "positive" emotions.

[1264] Proposal example

[1265] 1. The server stores information about Shizuoka Prefecture's specialty products, green tea and mandarin oranges, in a supply database.

[1266] 2. The server stores in the demand database that "health foods" and "detox" are trending.

[1267] 3. Based on the emotion engine's recognition of the user's emotion as "positive," the server's generative AI matches the detoxifying effects of green tea with trend information to generate new product ideas.

[1268] 4. The server generates a recommendation for a "detox drink using green tea" and sends it to the device.

[1269] 5. The user creates a development plan for a green tea drink based on the received proposal results.

[1270] In this way, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to advance product development quickly and effectively.

[1271] The processing flow will be explained below.

[1272] Step 1: Gather supply data

[1273] Server: Uses API to collect production and shipping data from local governments and companies. Collected data includes product type, production volume, quality, price, etc.

[1274] Server: Uses scraping technology to obtain information from public databases and websites, including information on tourist attractions and local specialties.

[1275] Step 2: Organize and store supply data

[1276] Server: Categorizes the collected supply data by region and attaches detailed information, such as green tea, mandarin oranges, and wasabi in Shizuoka Prefecture.

[1277] Server: Standardize data formats and remove duplicate data.

[1278] Server: Stores the organized data in a serving database and indexes it to optimize search speed.

[1279] Step 3: Collect demand data

[1280] Server: Uses APIs of search engines and social media platforms to collect trending information, including search counts, mention frequency, and hot topics.

[1281] Server: Uses crawling technology to obtain the latest information from news sites and blogs, including information on health foods and ecology.

[1282] Step 4: Organize and store demand data

[1283] Server: Categorizes the collected demand data into categories, such as health foods, ecology, technology, etc.

[1284] Server: Standardize data formats and remove duplicate data.

[1285] Server: Stores organized data in a demand database and indexes it to optimize search speed.

[1286] Step 5: Collect and analyze user sentiment data

[1287] Server: Using the emotion engine installed on the user's device, it collects emotion data from the user's voice, facial expressions, input data, etc. For example, the user's facial expressions and voice are recognized through a camera or microphone.

[1288] Server: Analyzes collected emotion data in real time and identifies positive or negative emotions.

[1289] Server: Organizes emotion data by time axis and situation and stores it in an emotion database.

[1290] Step 6: Matching the data

[1291] Server: Uses generative AI to match supply and demand databases, automatically extracting relevant data.

[1292] Server: Generative AI analyzes data based on past successes and trend prediction algorithms to predict potential hit products, such as combining the detoxifying effects of green tea with current trends.

[1293] Step 7: Generate proposals taking into account user emotion data

[1294] Server: Combines the matching results of the generation AI with the user's emotional data to extract optimal product ideas. If the user shows "positive" emotions, this tendency is reflected.

[1295] Server: Generates proposals that include details such as product concept, target market, and sales plan.

[1296] Step 8: Viewing the Suggestion Results

[1297] Terminal: Receives the proposal results provided by the server.

[1298] User: View the proposal results and check detailed information (product concept, target market, sales plan).

[1299] User: Based on the received proposal, create a development plan for a new local specialty product. For example, start product development based on the received proposal for a "green tea detox drink."

[1300] Through the above steps, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to develop products quickly and effectively.

[1301] Example 2

[1302] 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."

[1303] Efficiently linking information on locally produced goods and services with demand information on the Internet and proposing new products and services that should be introduced is a difficult task for existing systems. Furthermore, making optimal proposals that take user emotions into account requires the collection and analysis of real-time, accurate emotional data. However, a system that can integrate this data and provide optimal proposals for each user has yet to be developed.

[1304] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting and organizing data on goods produced and shipped in a region, a means for collecting and organizing data on internet search history, news articles, social network posts, search trends, and world affairs, a means for matching a supply database and a demand database using artificial intelligence to discover and propose products that should be introduced, a means for collecting, analyzing, and organizing user emotion data, a means for optimizing proposal results based on the emotion data, and a means for displaying the proposal results. This enables effective and accurate product proposals by combining regional characteristics with real-time user emotion data.

[1305] "Supply data" refers to information including goods, services, tourism resources, and historical industry data produced and shipped in the region.

[1306] "Demand Data" is information including internet search history, news articles, social network posts, search trends, and world affairs data.

[1307] "Supply database" refers to a database that organizes and stores supply data.

[1308] A "demand database" is a database that organizes and stores demand data.

[1309] "Artificial intelligence" refers to algorithms and software that match supply and demand databases to discover and propose products that should be marketed.

[1310] "Emotion data" refers to emotional information collected from the user's voice, facial expression, input data, and the like.

[1311] The "emotion engine" is software for collecting, analyzing, and organizing user emotional data.

[1312] "Proposal results" are the specific products that AI has discovered and proposed for the market.

[1313] "Search trends" refers to data about the frequency and fluctuations of keywords and phrases that users search for on the Internet.

[1314] "Social network posts" are data that include user posts on social media platforms.

[1315] MODE FOR CARRYING OUT THE INVENTION

[1316] This invention is a system that collects supply data, such as goods produced and shipped in a region and services provided, and organizes and stores it in a supply database. It also collects demand data, such as internet search history, news articles, social network posts, search trends, and world events, and organizes and stores it in a demand database. These two databases are matched using artificial intelligence (AI) to discover and recommend products that should be marketed. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize recommendation results based on the user's emotional data.

[1317] Hardware and Software Configuration

[1318] The server uses the following hardware and software to implement this system:

[1319] Data collection module: This module periodically obtains production and shipping data from local governments and companies via API. Specifically, it uses HTTP requests.

[1320] Scraping tools: scraping data from public databases and websites using scraping techniques, using libraries such as BeautifulSoup and Scrapy.

[1321] Crawling tools: Crawling demand data from news sites and blogs, for example, using tools such as Selenium or Puppeteer.

[1322] Generative AI model: Used to match supply and demand databases and discover potential hit products. This is a model that applies natural language processing (NLP) technology, such as OpenAI's GPT model.

[1323] Emotion engine: Collects and analyzes emotional data in real time from the user's voice, facial expressions, input data, etc. For example, using Microsoft Azure Cognitive Services.

[1324] Database management system: A database for storing supply data and demand data, for example, MySQL or PostgreSQL.

[1325] Specific examples

[1326] For example, here is a specific example from Shizuoka Prefecture:

[1327] Supply data collection:

[1328] The server uses an API to collect production data on local specialties such as green tea, mandarin oranges, and wasabi from local governments and companies in Shizuoka Prefecture, and stores that information in a supply database.

[1329] In addition, information on green tea production volume and quality will be collected from publicly available databases and websites through scraping and stored in a supply database in a unified format.

[1330] Demand data collection:

[1331] The server uses an API to obtain the number of searches for keywords such as "health benefits of green tea" from search engines and stores the information in a demand database.

[1332] In addition, articles about health-consciousness are collected by crawling from news sites and blogs, categorized into "healthy foods," and stored in a demand database.

[1333] Collecting and analyzing sentiment data:

[1334] The server uses an emotion engine installed on the user's device to analyze the user's voice and facial expressions in real time while they are reading an article about green tea, and recognizes "positive" emotions.

[1335] Generative AI suggestions:

[1336] The server's generation AI matches green tea data from the supply database with health food trend data from the demand database to generate an idea for a new product: a "green tea drink with detoxifying effects."

[1337] Furthermore, based on the user's emotional data, the system generates optimal product concepts, target markets, and sales plans as proposals.

[1338] Viewing Suggested Results:

[1339] The user's device displays the proposal results received from the server, and the user can check details such as the product concept and sales plan for the "Green Tea Detox Drink."

[1340] Prompt Sentence Examples

[1341] "Please propose a new product idea that uses green tea, a specialty of Shizuoka Prefecture, and is in line with the health food trend. Please take into account user sentiment data and optimize the proposal results."

[1342] This enables the system to combine regional characteristics with real-time user emotional data to make effective and accurate product recommendations.

[1343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1344] Step 1:

[1345] Supply Data Collection

[1346] The server uses an API to obtain production and shipping data from local governments and companies. For example, it obtains green tea production data for Shizuoka Prefecture through an HTTP request and saves it as a CSV file. It also uses scraping technology to collect data from publicly available databases and websites. The input is raw data obtained from the API or webpage, and the output is a list of the various types of collected data.

[1347] Step 2:

[1348] Supply data organization

[1349] The server classifies the collected data by region and standardizes the format. For example, it classifies green tea data into the "Shizuoka Prefecture" category and standardizes the weight unit to kg. It deletes any duplicate data and stores the organized data in the supply database. The input is the collected raw data, and the output is an organized, consistent dataset.

[1350] Step 3:

[1351] Demand data collection

[1352] The server collects demand data via APIs of search engines and social media platforms. For example, it obtains the number of searches for a specific keyword (e.g., "green tea health benefits") and saves this as trend data. At the same time, it also collects data from news sites and blogs by crawling. The input is trend data on the Internet, and the output is a list of the collected demand data.

[1353] Step 4:

[1354] Organizing demand data

[1355] The server categorizes the collected demand data by category and standardizes the format. For example, it stores the data in categories such as "healthy foods" and "ecology" and attaches search and mention frequency information. The input is raw data, and the output is an organized demand dataset.

[1356] Step 5:

[1357] Collecting user emotion data

[1358] The server uses an emotion engine installed on the user's device to collect emotion data in real time from the user's voice and facial expressions. For example, a camera captures the user's facial expression while reading an article about green tea and recognizes the emotion as "positive." The input is the user's real-time emotion data, and the output is classified emotion data.

[1359] Step 6:

[1360] Analyzing and organizing emotion data

[1361] The server organizes the collected emotional data by timeline and situation, and creates a basis for optimizing future proposals by referring to past data. For example, it stores data such as "positive reaction after reading an article about green tea at 10:30 on October 15, 2023." The input is emotional data collected in real time, and the output is an analyzed and organized emotional dataset.

[1362] Step 7:

[1363] Data matching by generative AI

[1364] The server's generation AI compares the supply database with the demand database and extracts highly relevant data. For example, it matches "green tea" information from the supply database with "health food trends" information from the demand database. The input is supply data and demand data, and the output is a new product idea as a result of the matching.

[1365] Step 8:

[1366] Generating proposal results taking into account user emotion data

[1367] The server combines the matching results of the generation AI with the user's emotional data to extract optimal product ideas. For example, if the user expresses positive feelings toward green tea, it generates a suggestion for "green tea detox drink." The input is the matching results and emotional data, and the output is a detailed suggestion.

[1368] Step 9:

[1369] Sending the proposal results to the device

[1370] The server sends the generated proposal results to the user's device. For example, it sends the proposal document in JSON format to the device and makes it viewable. The input is the generated proposal results, and the output is the transmitted data.

[1371] Step 10:

[1372] Displaying the proposed results

[1373] The user's terminal displays the proposal results received from the server. For example, a specific product concept or sales plan is displayed on the screen. The input is the proposal results sent from the server, and the output is the displayed information.

[1374] (Application example 2)

[1375] 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."

[1376] Existing product development platforms are limited to simply matching supply and demand data and do not take user sentiment into account. This makes it difficult to propose products that accurately reflect consumers' latent needs. It is also difficult to maximize the appeal of local specialties and develop products that respond to trends in real time. This hinders improvements in sales efficiency and the rapid launch of new products.

[1377] 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.

[1378] In this invention, the server includes a supply data collection means for collecting and organizing data on goods produced and shipped in the region; a demand data collection means for collecting and organizing data on web search history, news articles, social media posts, search trends, and world affairs; a means for building a supply database and a demand database; a means for matching the supply database and the demand database using generative AI to discover and propose products to be introduced; an emotion data collection means for collecting and analyzing user emotion data in real time; a means for optimizing proposal results taking into account the collected emotion data; and a means for displaying the proposal results. This enables accurate product proposals that take into account user emotion in addition to matching supply data and demand data. Furthermore, it is possible to maximize the appeal of regional specialty products and quickly bring new products that are in line with trends to market, which is expected to improve sales efficiency.

[1379] "Supply data collection means" refers to a means for collecting and organizing data on goods produced and shipped in the region.

[1380] "Demand data collection methods" are methods for collecting and organizing data on web search history, news articles, social media posts, search trends, and world events.

[1381] A "supply database" is a database for storing and managing collected supply data.

[1382] A "demand database" is a database for storing and managing collected demand data.

[1383] "Generative AI" is artificial intelligence that collates supply and demand databases and analyzes relevant data.

[1384] The "emotion data collection means" is a means for collecting emotion data from the user's voice, facial expression, input data, etc., and analyzing it in real time.

[1385] The "means for displaying the proposed results" is a means for displaying to the user the product information proposed as a result of analysis by the generation AI.

[1386] A system for implementing the present invention collects supply data, such as goods produced and shipped in a region and services provided, and organizes and stores it in a supply database. It also collects demand data, such as web search history, news articles, social media posts, search trends, and world events, and organizes and stores it in a demand database. The system matches these two databases using generative AI to discover and recommend products that should be marketed. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it can optimize recommendation results based on the user's emotion data.

[1387] System Configuration

[1388] 1. Hardware to be used

[1389] Server (operation of database and generative AI)

[1390] Smartphones and tablets (for the user interface)

[1391] 2. Software to be used

[1392] Database management systems (e.g., MySQL, PostgreSQL)

[1393] Crawling tools for collecting data from news sites, etc. (e.g., Scrapy)

[1394] Emotion engine libraries (e.g., Microsoft Azure Emotion API, Google Cloud Vision API)

[1395] Machine learning libraries (e.g. TensorFlow, PyTorch)

[1396] Web development frameworks (e.g., Django, Flask)

[1397] Program processing flow

[1398] The server uses supply data collection tools to collect production and shipping data from local governments and companies. It also uses scraping technology to obtain information from publicly available databases and websites. The collected data is categorized by region, and detailed information is stored in the supply database.

[1399] Next, the server uses demand data collection means to collect trend information using APIs of search engines and social media platforms, and also obtains data from the latest news sites and blogs using crawling technology, categorizes each piece of information, and stores the detailed information in a demand database.

[1400] Users' emotional data is collected using an emotion engine in an application on a smartphone or tablet. The engine collects users' voices, facial expressions, input data, etc. in real time, analyzes and organizes the emotional data, and stores it in an emotion database.

[1401] The server uses generative AI to match supply and demand databases and automatically extract relevant data. It analyzes the data based on past successes and trend prediction algorithms to predict potential hit products. By taking into account emotional data, it extracts optimal product ideas based on user sentiment and generates proposals that include details such as product concept, target market, and sales plan.

[1402] The proposal results are displayed on the user's smartphone or tablet, and the user can use these results to develop new products and sales strategies.

[1403] Specific examples

[1404] For example, here is a specific example from Shizuoka Prefecture:

[1405] When collecting supply data, information on Shizuoka Prefecture's specialty products, green tea, mandarin oranges, and wasabi, is stored in the supply database. When collecting demand data, the fact that health foods and detoxes are trending is stored in the demand database. When the emotion engine recognizes the user's emotion as "positive," the server's generation AI matches the detox effects of green tea with trend information to generate new product ideas.

[1406] The server generates a proposal for a "detox drink using green tea" and sends it to the user's device. The user can then create a development plan for the green tea drink based on the proposal received.

[1407] Example prompt sentence:

[1408] Please propose new product ideas based on the following supply and demand data. The supply data includes green tea, mandarin oranges, and wasabi from Shizuoka Prefecture. The demand data includes "healthy food," "detox," and "low calorie." Users indicate positive sentiment. Extract the best product ideas and propose a product concept, target market, and sales plan.

[1409] In this way, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to advance product development quickly and effectively.

[1410] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1411] Step 1:

[1412] The server collects production and shipping data provided by local governments and companies using supply data collection methods. Specifically, it obtains data using APIs and collects information from public databases and web pages using scraping technology. The collected data is categorized by region and stored in a supply database.

[1413] Input: Production and shipping data from local governments and companies, information from public databases

[1414] Data processing: Classification by region, removal of duplicate data, unification of format

[1415] Output: Supply database

[1416] Step 2:

[1417] The server collects data on web search history, news articles, social media posts, search trends, and world affairs using demand data collection methods. Specifically, it obtains trend information using search engine and social media APIs, and collects data from news sites and blogs using crawling technology. The collected data is categorized and stored in a demand database.

[1418] Input: Web search history, news articles, social media posts, search trends, world events

[1419] Data processing: Classification by category, addition of detailed information (number of searches, frequency of mentions)

[1420] Output: Demand database

[1421] Step 3:

[1422] An emotion engine is used in an application installed on the user's device to collect the user's emotional data. Specifically, voice, facial expressions, and input data are collected and analyzed in real time and stored in an emotion database. The emotional data is organized by time axis and situation.

[1423] Input: User's voice, facial expressions, input data

[1424] Data calculation: Real-time analysis of emotional data, organizing it by time axis and situation

[1425] Output: Emotion database

[1426] Step 4:

[1427] The server uses generative AI to match supply and demand databases and automatically extract relevant data. Specifically, it compares supply and demand data and analyzes the data based on trend prediction algorithms, thereby predicting potential hit products.

[1428] Input: Supply database, Demand database

[1429] Data calculation: Matching supply and demand, data analysis using trend prediction algorithms

[1430] Output: A list of potential hits

[1431] Step 5:

[1432] The server uses the collected emotional data to extract optimal product ideas based on the matching results of the generative AI. Specifically, it adds the emotional data to the analysis results of the generative AI to generate proposals that include details such as the product concept, target market, and sales plan.

[1433] Input: sentiment database, list of potential hit products

[1434] Data calculation: Generate product ideas that reflect emotional data and create detailed proposals

[1435] Output: Optimal product ideas and proposals

[1436] Step 6:

[1437] The proposal results are displayed on the user's device. Specifically, the product ideas and proposal content generated by the server are sent to a smartphone or tablet application and visually displayed to the user. The user can then formulate new product development and sales strategies based on these proposal results.

[1438] Input: Optimal product ideas and proposals

[1439] Action: Sends suggestions and displays them on smartphones and tablets

[1440] Output: Displayed suggestion results

[1441] This series of processes not only optimally matches regional characteristics with consumer trends, but also combines user emotional data to provide more accurate proposal results, enabling local governments and companies to develop products quickly and effectively.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] [Fourth embodiment]

[1446] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1447] 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.

[1448] 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).

[1449] 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.

[1450] 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.

[1451] 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).

[1452] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] 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."

[1459] This system collects supply data such as goods produced and shipped in the region and services provided, organizes it, and stores it in a supply database. It also collects demand data such as web search history, news articles, social media posts, search trends, and world events, organizes it, and stores it in a demand database. It matches these two databases using generative AI to discover and suggest products that should be marketed.

[1460] Program processing flow

[1461] 1. Collecting and organizing supply data

[1462] Server: Collects data for distribution

[1463] The server collects production and shipping data via data provision APIs from local governments and companies.

[1464] The server uses scraping technology to obtain information from publicly available databases and websites.

[1465] Server: Organizing the data provided

[1466] The server categorizes the collected data by region, attaches detailed information (e.g., production volume, quality, price) and stores it in a supply database.

[1467] 2. Collecting and organizing demand data

[1468] Server: Collects demand data

[1469] The server uses APIs from search engines and social media platforms to collect trending information.

[1470] The server uses crawling technology to obtain the latest information from news sites and blogs.

[1471] Server: Organizing demand data

[1472] The server classifies the collected data by category (e.g., health foods, ecology, technology) and stores it in a demand database.

[1473] 3. Data matching and proposals

[1474] Server: Data matching process by generative AI

[1475] The generative AI on the server compares the supply database with the demand database and extracts highly relevant data.

[1476] Generative AI uses past success stories and trend-prediction algorithms to predict potential hit products.

[1477] Server: Generates proposal results

[1478] The server concretizes product ideas based on the AI ​​matching results and generates proposals that include details such as product concept, target market, and sales plan.

[1479] 4. Displaying the proposed results

[1480] Device: Display of suggested results

[1481] The user's (local government or company's) terminal receives the proposal results from the server and displays detailed information (product concept, target market, sales plan).

[1482] Users can create development plans for new specialty products based on these proposals.

[1483] Specific examples

[1484] For example, here is a specific example from Shizuoka Prefecture:

[1485] Supply Data Collection

[1486] Region: Shizuoka Prefecture

[1487] Items: Green tea, mandarin oranges, wasabi

[1488] Tourist attractions: hot springs, historical buildings

[1489] Demand data collection

[1490] Recent search trends: Healthy food, detox, low calorie

[1491] News article: As health consciousness grows, attention is focused on the benefits of green tea

[1492] Proposal example

[1493] 1. The server stores information about Shizuoka Prefecture's specialty products, green tea and mandarin oranges, in a supply database.

[1494] 2. The server stores in the demand database that "health foods" and "detox" are trending.

[1495] 3. The server's generation AI matches the detoxifying effects of green tea with trend information to generate new product ideas.

[1496] 4. The server generates a recommendation for a "detox drink using green tea" and sends it to the device.

[1497] 5. The user creates a development plan for a green tea drink based on the received proposal results.

[1498] In this way, the present invention efficiently proposes new specialty products that optimally match regional characteristics with consumer trends, enabling local governments and businesses to rapidly and effectively develop products.

[1499] The processing flow will be explained below.

[1500] Step 1: Gather supply data

[1501] Server: Collects production and shipping data from local governments and companies using APIs.

[1502] Server: Information is obtained from public databases and websites using scraping technology.

[1503] Server: Removes duplicates from the collected data and standardizes the data format.

[1504] Step 2: Organize and store supply data

[1505] Server: Classifies collected supply data by region and organizes goods, services, tourist resources, specialty products, and historical industry data.

[1506] Server: Attaches detailed information (e.g. production volume, quality, price) to each data item and stores it in a supply database.

[1507] Server: Creates indexes for stored data and optimizes search speed.

[1508] Step 3: Collect demand data

[1509] Server: Uses APIs of search engines and social media platforms to collect trend information.

[1510] Server: Obtains the latest information from news sites and blogs using crawling technology.

[1511] Server: Removes duplicates from the collected data and standardizes the data format.

[1512] Step 4: Organize and store demand data

[1513] Server: Classifies the collected demand data by category (e.g., health foods, ecology, technology).

[1514] Server: Attach detailed information (e.g., number of searches, frequency of mentions) to each piece of data and store it in the demand database.

[1515] Server: Creates indexes for stored data and optimizes search speed.

[1516] Step 5: Matching the data

[1517] Server: Uses generative AI to match supply and demand databases, automatically extracting relevant data.

[1518] Server: Generative AI analyzes data based on past successes and trend prediction algorithms to predict potential hit products.

[1519] Server: Organizes the matching results from AI and extracts product ideas that should be marketed.

[1520] Step 6: Generate proposal results

[1521] Server: Materializes the product ideas obtained from the matching results and generates detailed proposals (product concept, target market, sales plan).

[1522] Server: Compiles the generated proposal results into a report format for local governments and businesses.

[1523] Step 7: Viewing the Suggestion Results

[1524] Terminal: Receives the proposal results provided by the server.

[1525] Terminal: The proposal results are displayed so that users can view them. Detailed information (product concept, target market, sales plan) can be confirmed.

[1526] User: Based on the received proposals, a development plan for a new specialty product can be created.

[1527] Example 1

[1528] 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."

[1529] Currently, many regions and companies are struggling to effectively market their specialty products and services. One reason for this is that matching supply and demand takes time and effort, preventing appropriate product proposals from being made quickly. Furthermore, with global conditions and consumer trends constantly changing, it is difficult to determine which areas to focus on. In these circumstances, a system is needed that effectively integrates local characteristics with global trends and allows for fast and efficient product proposals.

[1530] 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.

[1531] In this invention, the server includes: a supply data collection means for collecting and organizing data on goods produced and shipped in the region; a demand data collection means for collecting and organizing data on web search history, news articles, information sharing platform posts, search trends, and international affairs; a means for constructing a supply database and a demand database; a means for matching the supply database and the demand database using generation AI and making new product proposals; a means for displaying the proposal results; a means for classifying supply data by region and storing it in the supply database with detailed information attached; a means for collecting trend information using the API of a search engine or information sharing platform; and a means for concretizing product ideas based on the matching process and generating proposal content such as a product concept, target market, and sales plan, thereby enabling fast and efficient product proposals for local specialty products and services through supply and demand matching.

[1532] "Supply data collection means" refers to a means for collecting and organizing data on goods produced and shipped in the region.

[1533] "Demand data collection means" refers to means for collecting and organizing data on web search history, news articles, posts on information sharing platforms, search trends, and international affairs.

[1534] The "supply database" is a database for storing and managing data on goods produced and shipped in the region.

[1535] A "demand database" is a database for storing and managing data related to demand.

[1536] "Generative AI" is a system that uses artificial intelligence technology to analyze data and perform matching and new product suggestions.

[1537] The "matching means" is a means for comparing the supply database and the demand database using generation AI to make new product proposals.

[1538] The "means for displaying proposal results" is a means for displaying the proposal results made by the generation AI to the user.

[1539] The "supply data classification means" is a means for classifying collected supply data by region, attaching detailed information, and storing the data in the supply database.

[1540] "Trend data collection means" refers to a means for collecting trend information using the APIs of search engines and information sharing platforms.

[1541] The "product idea realization means" is a means for realizing a product idea based on a matching process and generating proposal contents such as a product concept, target market, and sales plan.

[1542] This invention is a system that uses AI to match supply data, such as goods produced and shipped in a region and services provided, with demand data, such as web search history, news articles, posts on information sharing platforms, search trends, and international affairs, to discover and suggest products that should be marketed. This system is implemented using the following hardware and software.

[1543] 1. Collecting and organizing supply data

[1544] Server: Use of data provision API

[1545] The server uses a data provision API to collect supply data from local governments and companies. Specifically, it periodically obtains production and shipping data. The data is provided in JSON format and can be collected using an API client (e.g., an HTTP library).

[1546] Example: A server collects data on green tea production volume and quality from the Shizuoka Prefecture Agricultural Cooperative API.

[1547] Server: Use of scraping technology

[1548] The server obtains supply data from the public websites of local businesses using scraping techniques, for example, using an HTML parsing library to extract product pricing information and availability from specialty product pages.

[1549] Example: A server parses HTML from a company's specialties page to obtain pricing information for green tea.

[1550] Server: Classification of collected data

[1551] The server categorizes the collected data by region, attaches detailed information and stores it in a supply database, using a database management system (e.g., MySQL or PostgreSQL) for this process.

[1552] 2. Collecting and organizing demand data

[1553] Server: API collection of trend data

[1554] The server uses the Google Trends API and Twitter API to collect search trend information, which is then analyzed and stored in a demand database.

[1555] Example: The server uses the Google Trends API to collect search volume data for keywords related to "health foods" and "detox."

[1556] Server: Use of crawling techniques

[1557] The server crawls news sites and blogs to obtain the latest demand information, analyzes the information, categorizes it, and stores it in a demand database.

[1558] Example: A server crawls health-related articles from news sites and stores them in a demand database.

[1559] 3. Data matching and proposals

[1560] Server: Matching process by generation AI

[1561] A server-based generation AI (e.g., GPT-4) is used to match the supply database with the demand database, extracting highly relevant data based on keyword matches and correlations.

[1562] Example: Generative AI matches green tea supply data with "health food" trend information.

[1563] Server: Proposal generation

[1564] The server then creates a new product proposal based on the relevant data extracted by the generative AI, including details such as the product concept, target market, and sales plan.

[1565] Example: Generative AI generates product ideas for a "green tea detox drink" and creates a detailed sales plan.

[1566] 4. Displaying the proposed results

[1567] Terminal: Receiving and displaying the proposed results

[1568] The user's device receives the recommendation results from the server and displays detailed information. A dashboard-style UI is used, allowing the user to easily check the details of the recommended products.

[1569] Example: The user's terminal receives the proposal results from the server and displays the new product concept, target market, and sales plan.

[1570] Prompt Sentence Examples

[1571] An example of a prompt sentence input to a generative AI model:

[1572] "The supply data includes green tea and mandarin oranges produced in Shizuoka Prefecture. The current demand data includes health foods and detoxes, which are trending. Please use this data to propose new product ideas."

[1573] By efficiently matching supply and demand data, the system enables local specialties and services to enter the market quickly and effectively.

[1574] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1575] Step 1: Gather supply data

[1576] Server: Use of data provision API

[1577] The server uses a data provision API to collect supply data from local governments and companies. The server periodically sends requests to the API endpoint and obtains production volume and quality information in JSON format.

[1578] Input: API request

[1579] Output: JSON formatted supply data

[1580] Specifically, the server sends an HTTP request and analyzes the data obtained as a response.

[1581] Step 2: Scrape supply data

[1582] Server: Use of scraping technology

[1583] The server obtains supply data from publicly available websites of local businesses using scraping techniques, for example, using HTML parsing libraries to extract product pricing information and availability from specialty product pages.

[1584] Input: Webpage URL

[1585] Output: Extracted feed data

[1586] Specifically, the server accesses the web page, analyzes the HTML, and extracts the necessary data.

[1587] Step 3: Classify and store supply data

[1588] Server: Classification of collected data

[1589] The server categorizes the collected data by region and stores it in a supply database along with detailed information (production volume, quality, price).

[1590] Input: Supply data before classification

[1591] Output: Data to be inserted into the supply database

[1592] Specifically, the server classifies the data based on the region name and inserts a new record into the database.

[1593] Step 4: Collect demand data

[1594] Server: API collection of trend data

[1595] The server uses the Google Trends API and Twitter API to collect search trend information, which is then analyzed and stored in a demand database.

[1596] Input: API request

[1597] Output: Demand data in JSON format

[1598] Specifically, the server sends an API request and obtains trend information in JSON format.

[1599] Step 5: Crawl for demand data

[1600] Server: Use of crawling techniques

[1601] The server crawls news sites and blogs to obtain the latest demand information. The analyzed information is categorized and stored in a demand database.

[1602] Input: Website URL

[1603] Output: Retrieved demand data

[1604] Specifically, the server accesses the news site, analyzes the HTML, and extracts demand data.

[1605] Step 6: Classify and store demand data

[1606] Server: Classification of collected data

[1607] The server classifies the collected demand data into categories (healthy foods, ecology, technology, etc.) and stores them in a demand database.

[1608] Input: Demand data before classification

[1609] Output: Data to be inserted into the demand database

[1610] Specifically, the server categorizes the data based on the category name and inserts a new record into the database.

[1611] Step 7: Matching the data

[1612] Server: Matching by generative AI

[1613] The server-based AI compares the supply and demand databases to extract relevant data, then analyzes the data based on keyword matches and correlations.

[1614] Input: Supply data, Demand data

[1615] Output: Matching results

[1616] Specifically, the server uses generative AI to analyze supply and demand data and extract highly relevant pairs.

[1617] Step 8: Generate proposals

[1618] Server: Creating a concrete proposal

[1619] The server then uses the relevant data extracted by the generative AI to create new product ideas, including details such as the product concept, target market, and sales plan.

[1620] Input: Matching results

[1621] Output: Specific product suggestions

[1622] Specifically, the server analyzes the output of the generative AI and converts the product ideas into detailed proposal documents.

[1623] Step 9: Viewing the Suggestion Results

[1624] Terminal: Receiving and displaying the proposed results

[1625] The user's terminal receives the proposal results sent from the server and displays the detailed information.

[1626] Input: Proposal result data

[1627] Output: Display of proposal results

[1628] Specifically, the device receives data from the server and displays it on a dashboard-style UI.

[1629] Step 10: Use the proposal

[1630] User: Product development based on received results

[1631] The user makes a product development plan based on the received proposal results.

[1632] Input: Suggestion results

[1633] Output: Product development plan

[1634] Specifically, the user analyzes the proposal and provides feedback to the product development department.

[1635] (Application example 1)

[1636] 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."

[1637] Conventional systems were unable to effectively match data on locally produced and shipped goods and services provided with demand data, making it particularly difficult to utilize proposal results in real time. This meant that product proposals and inventory management in physical stores could not be carried out quickly, leading to the issue of being unable to respond promptly to customer needs.

[1638] 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.

[1639] In this invention, the server includes a supply data collection means for collecting and organizing data on goods produced and shipped in the region, a demand data collection means for collecting and organizing data on web search history, news articles, social media posts, search trends, and world affairs, a means for building a supply database and a demand database, a means for matching the supply database and the demand database with a generation AI to discover and propose products to be introduced, a means for displaying the proposal results, and a means for providing access to the proposal results in real time using a smart device.This enables product proposals and inventory management in physical stores to be carried out quickly and effectively, making it possible to respond to customer needs immediately.

[1640] "Supply data collection means" refers to a device or system that collects and organizes data on goods produced and shipped in a region.

[1641] "Demand data collection means" refers to a device or system that collects and organizes data on web search history, news articles, social media posts, search trends, and world events.

[1642] "Supply Database" refers to a database that stores collected supply data and stores detailed information categorized by region.

[1643] A "demand database" is a database that classifies collected demand data by category and stores trend information.

[1644] "Generative AI" is an artificial intelligence system that matches supply databases with demand databases to discover and propose products that should be marketed.

[1645] "Means for displaying proposal results" refers to a device or system for displaying proposals obtained by the generation AI to the user.

[1646] A "smart device" is a device that can connect to the Internet, such as a smartphone, smart glasses, or a head-mounted display.

[1647] "Means for providing real-time access to recommendation results" refers to a device or system that enables real-time access to the recommendation results of the generative AI using a smart device.

[1648] This invention collects supply data on goods produced and shipped in the region and services provided, and demand data such as web search history, news articles, social media posts, search trends, and world affairs, and organizes and stores them in a supply database and a demand database. This allows the generation AI to match the two databases, making it possible to efficiently discover and propose new products and services that should be introduced.

[1649] Program Overview

[1650] The server collects supply and demand data and uses AI to collate it, while smart devices (such as smartphones or smart glasses) display real-time recommendations, helping in-store operations.

[1651] Hardware and Software Used

[1652] Hardware: Servers, smart devices (smartphones, smart glasses, head-mounted displays)

[1653] software:

[1654] Python: Used for data collection and processing

[1655] Requests: Used to retrieve data from the API

[1656] JSON: A Data Interchange Format

[1657] Generative AI models: used to match data and generate recommendations

[1658] Data processing flow

[1659] The server uses APIs and crawling technology to collect supply data on goods produced and shipped in the region, as well as various demand data for services provided. The collected data is stored in a supply database and a demand database. A generative AI model compares these databases to generate relevant product and service recommendations. The results are delivered to smart devices in real time, enabling store employees to quickly make product recommendations to customers.

[1660] Specific examples

[1661] For example, consider a case where a customer wants health-conscious products at a brick-and-mortar store in Shizuoka Prefecture. The server collects supply data for green tea and mandarin oranges produced in Shizuoka Prefecture and stores it in a supply database. At the same time, it collects demand data on the trending health foods and detox products and stores it in a demand database. The generative AI matches these data and suggests a detox drink made with green tea. This suggestion is displayed in real time to employees through smart glasses, allowing them to provide immediate advice to the customer.

[1662] Prompt Sentence Examples

[1663] Based on local products and current trends, please suggest products to promote in-store. Please use the following data:

[1664] Supply data:

[1665] Green Tea

[1666] mandarin orange

[1667] Demand Data:

[1668] health food

[1669] Detox

[1670] Example output format:

[1671] Item: Green tea

[1672] Trend: Detoxification

[1673] Recommended action: Recommend this item in store

[1674] In this way, the present invention can optimally match regional characteristics with consumer trends, thereby realizing efficient product proposals and inventory management in physical stores.

[1675] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1676] Step 1:

[1677] The server collects data on goods produced and shipped in the region via data provision APIs from local governments and companies. It receives supply data from the API as input and obtains it as output. This obtained data includes production volume, quality, price, etc. Specifically, it calls the API to obtain data and then formats it.

[1678] Step 2:

[1679] The server collects data on web search history, news articles, social media posts, search trends, and world affairs. It receives demand data as input using each platform's API and web crawling technology, and obtains demand data as output. Specifically, it uses search engine APIs to collect trend information and crawls news sites for the latest information.

[1680] Step 3:

[1681] The server organizes the collected supply data and stores it in a supply database. It receives supply data as input and stores the formatted supply data as output in the supply database. Specifically, it classifies the data by region and attaches detailed information such as production volume and quality.

[1682] Step 4:

[1683] The server organizes the collected demand data and stores it in the demand database. It receives demand data as input and stores the formatted demand data as output in the demand database. Specifically, it classifies the data by category (e.g., health, ecology, technology) and stores it in the demand database.

[1684] Step 5:

[1685] The generative AI model on the server compares the supply and demand databases to extract highly relevant data. It receives the supply and demand databases as input and generates matching results as output. Specifically, it analyzes the supply and demand data based on prompt statements to identify highly relevant products and services.

[1686] Step 6:

[1687] The server concretizes product ideas based on the matching results of the generative AI model. It receives the matching results as input and generates a product concept, target market, and sales plan as output. Specifically, it creates detailed proposals by referring to past success stories and trends.

[1688] Step 7:

[1689] The smart device (e.g., smart glasses) receives the proposal results from the server and displays them to the user. It receives the proposal results from the server as input and displays them in the user's field of view as output. Specifically, it downloads data via the network and overlays the proposal results in the user's field of view.

[1690] Step 8:

[1691] The user (e.g., a store employee) proposes product details to the customer based on the proposal results displayed on the smart device. The user receives the proposal results on the smart device as input and makes product proposals to the customer as output. Specific operations include checking the displayed information and explaining the benefits and features of specific products to the customer.

[1692] 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.

[1693] This system collects supply data, such as goods produced and shipped locally and services provided, and organizes and stores it in a supply database. It also collects demand data, such as web search history, news articles, social media posts, search trends, and world events, and organizes and stores it in a demand database. It matches these two databases using generative AI to discover and recommend products that should be marketed. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it can optimize recommendation results based on the user's emotional data.

[1694] Program processing flow

[1695] 1. Collecting and organizing supply data

[1696] Server: Collects data for distribution

[1697] The server uses an API to collect production and shipping data from local governments and companies.

[1698] The server uses scraping technology to obtain information from publicly available databases and websites.

[1699] Server: Organizing the data provided

[1700] The server categorizes the collected data by region, attaches detailed information (e.g., production volume, quality, price) and stores it in a supply database.

[1701] The server standardizes the data format and deletes duplicate data.

[1702] 2. Collecting and organizing demand data

[1703] Server: Collects demand data

[1704] The server uses APIs from search engines and social media platforms to collect trending information.

[1705] The server uses crawling technology to obtain the latest information from news sites and blogs.

[1706] Server: Organizing demand data

[1707] The server classifies the collected data into categories (e.g., health foods, ecology, technology).

[1708] The server attaches detailed information (e.g., number of searches, frequency of mentions) to each piece of data and stores it in a demand database.

[1709] 3. Collecting and analyzing user emotion data

[1710] Server: Collects user emotion data

[1711] The server uses an emotion engine installed on the user's device to collect emotion data from the user's voice, facial expressions, input data, etc.

[1712] The server analyzes the collected emotion data in real time.

[1713] Server: Emotion data organization

[1714] The server organizes the emotion data by time axis and situation and stores it as an emotion database.

[1715] The server uses each user's past emotional data to create a foundation for optimizing future proposal results.

[1716] 4. Data matching and suggestions

[1717] Server: Data matching process by generative AI

[1718] The generative AI on the server compares the supply database with the demand database and automatically extracts highly relevant data.

[1719] Generative AI analyzes data based on past successes and trend-prediction algorithms to predict potential hit products.

[1720] Server: Generates proposal results taking into account user emotion data

[1721] The server combines the matching results of the generation AI with the user's emotional data to extract the optimal product ideas.

[1722] The server generates a proposal that includes details such as the product concept, target market, and sales plan.

[1723] 5. Displaying the proposed results

[1724] Device: Display of suggested results

[1725] The user's (local government or company's) terminal receives the proposal results from the server and displays detailed information (product concept, target market, sales plan).

[1726] Users can create development plans for new specialty products based on these proposals.

[1727] Specific examples

[1728] For example, here is a specific example from Shizuoka Prefecture:

[1729] Supply Data Collection

[1730] Region: Shizuoka Prefecture

[1731] Items: Green tea, mandarin oranges, wasabi

[1732] Tourist attractions: hot springs, historical buildings

[1733] Demand data collection

[1734] Recent search trends: Healthy food, detox, low calorie

[1735] News article: As health consciousness grows, attention is focused on the benefits of green tea

[1736] Collecting user emotion data

[1737] The emotion engine collects facial expressions and voice in real time while the user is reading a presented article related to green tea, and recognizes "positive" emotions.

[1738] Proposal example

[1739] 1. The server stores information about Shizuoka Prefecture's specialty products, green tea and mandarin oranges, in a supply database.

[1740] 2. The server stores in the demand database that "health foods" and "detox" are trending.

[1741] 3. Based on the emotion engine's recognition of the user's emotion as "positive," the server's generative AI matches the detoxifying effects of green tea with trend information to generate new product ideas.

[1742] 4. The server generates a recommendation for a "detox drink using green tea" and sends it to the device.

[1743] 5. The user creates a development plan for a green tea drink based on the received proposal results.

[1744] In this way, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to advance product development quickly and effectively.

[1745] The processing flow will be explained below.

[1746] Step 1: Gather supply data

[1747] Server: Uses API to collect production and shipping data from local governments and companies. Collected data includes product type, production volume, quality, price, etc.

[1748] Server: Uses scraping technology to obtain information from public databases and websites, including information on tourist attractions and local specialties.

[1749] Step 2: Organize and store supply data

[1750] Server: Categorizes the collected supply data by region and attaches detailed information, such as green tea, mandarin oranges, and wasabi in Shizuoka Prefecture.

[1751] Server: Standardize data formats and remove duplicate data.

[1752] Server: Stores the organized data in a serving database and indexes it to optimize search speed.

[1753] Step 3: Collect demand data

[1754] Server: Uses APIs of search engines and social media platforms to collect trending information, including search counts, mention frequency, and hot topics.

[1755] Server: Uses crawling technology to obtain the latest information from news sites and blogs, including information on health foods and ecology.

[1756] Step 4: Organize and store demand data

[1757] Server: Categorizes the collected demand data into categories, such as health foods, ecology, technology, etc.

[1758] Server: Standardize data formats and remove duplicate data.

[1759] Server: Stores organized data in a demand database and indexes it to optimize search speed.

[1760] Step 5: Collect and analyze user sentiment data

[1761] Server: Using the emotion engine installed on the user's device, it collects emotion data from the user's voice, facial expressions, input data, etc. For example, the user's facial expressions and voice are recognized through a camera or microphone.

[1762] Server: Analyzes collected emotion data in real time and identifies positive or negative emotions.

[1763] Server: Organizes emotion data by time axis and situation and stores it in an emotion database.

[1764] Step 6: Matching the data

[1765] Server: Uses generative AI to match supply and demand databases, automatically extracting relevant data.

[1766] Server: Generative AI analyzes data based on past successes and trend prediction algorithms to predict potential hit products, such as combining the detoxifying effects of green tea with current trends.

[1767] Step 7: Generate proposals taking into account user emotion data

[1768] Server: Combines the matching results of the generation AI with the user's emotional data to extract optimal product ideas. If the user shows "positive" emotions, this tendency is reflected.

[1769] Server: Generates proposals that include details such as product concept, target market, and sales plan.

[1770] Step 8: Viewing the Suggestion Results

[1771] Terminal: Receives the proposal results provided by the server.

[1772] User: View the proposal results and check detailed information (product concept, target market, sales plan).

[1773] User: Based on the received proposal, create a development plan for a new local specialty product. For example, start product development based on the received proposal for a "green tea detox drink."

[1774] Through the above steps, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to develop products quickly and effectively.

[1775] Example 2

[1776] 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."

[1777] Efficiently linking information on locally produced goods and services with demand information on the Internet and proposing new products and services that should be introduced is a difficult task for existing systems. Furthermore, making optimal proposals that take user emotions into account requires the collection and analysis of real-time, accurate emotional data. However, a system that can integrate this data and provide optimal proposals for each user has yet to be developed.

[1778] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting and organizing data on goods produced and shipped in a region, a means for collecting and organizing data on internet search history, news articles, social network posts, search trends, and world affairs, a means for matching a supply database and a demand database using artificial intelligence to discover and propose products that should be introduced, a means for collecting, analyzing, and organizing user emotion data, a means for optimizing proposal results based on the emotion data, and a means for displaying the proposal results. This enables effective and accurate product proposals by combining regional characteristics with real-time user emotion data.

[1779] "Supply data" refers to information including goods, services, tourism resources, and historical industry data produced and shipped in the region.

[1780] "Demand Data" is information including internet search history, news articles, social network posts, search trends, and world affairs data.

[1781] "Supply database" refers to a database that organizes and stores supply data.

[1782] A "demand database" is a database that organizes and stores demand data.

[1783] "Artificial intelligence" refers to algorithms and software that match supply and demand databases to discover and propose products that should be marketed.

[1784] "Emotion data" refers to emotional information collected from the user's voice, facial expression, input data, and the like.

[1785] The "emotion engine" is software for collecting, analyzing, and organizing user emotional data.

[1786] "Proposal results" are the specific products that AI has discovered and proposed for the market.

[1787] "Search trends" refers to data about the frequency and fluctuations of keywords and phrases that users search for on the Internet.

[1788] "Social network posts" are data that include user posts on social media platforms.

[1789] MODE FOR CARRYING OUT THE INVENTION

[1790] This invention is a system that collects supply data, such as goods produced and shipped in a region and services provided, and organizes and stores it in a supply database. It also collects demand data, such as internet search history, news articles, social network posts, search trends, and world events, and organizes and stores it in a demand database. These two databases are matched using artificial intelligence (AI) to discover and recommend products that should be marketed. Furthermore, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize recommendation results based on the user's emotional data.

[1791] Hardware and Software Configuration

[1792] The server uses the following hardware and software to implement this system:

[1793] Data collection module: This module periodically obtains production and shipping data from local governments and companies via API. Specifically, it uses HTTP requests.

[1794] Scraping tools: scraping data from public databases and websites using scraping techniques, using libraries such as BeautifulSoup and Scrapy.

[1795] Crawling tools: Crawling demand data from news sites and blogs, for example, using tools such as Selenium or Puppeteer.

[1796] Generative AI model: Used to match supply and demand databases and discover potential hit products. This is a model that applies natural language processing (NLP) technology, such as OpenAI's GPT model.

[1797] Emotion engine: Collects and analyzes emotional data in real time from the user's voice, facial expressions, input data, etc. For example, using Microsoft Azure Cognitive Services.

[1798] Database management system: A database for storing supply data and demand data, for example, MySQL or PostgreSQL.

[1799] Specific examples

[1800] For example, here is a specific example from Shizuoka Prefecture:

[1801] Supply data collection:

[1802] The server uses an API to collect production data on local specialties such as green tea, mandarin oranges, and wasabi from local governments and companies in Shizuoka Prefecture, and stores that information in a supply database.

[1803] In addition, information on green tea production volume and quality will be collected from publicly available databases and websites through scraping and stored in a supply database in a unified format.

[1804] Demand data collection:

[1805] The server uses an API to obtain the number of searches for keywords such as "health benefits of green tea" from search engines and stores the information in a demand database.

[1806] In addition, articles about health-consciousness are collected by crawling from news sites and blogs, categorized into "healthy foods," and stored in a demand database.

[1807] Collecting and analyzing sentiment data:

[1808] The server uses an emotion engine installed on the user's device to analyze the user's voice and facial expressions in real time while they are reading an article about green tea, and recognizes "positive" emotions.

[1809] Generative AI suggestions:

[1810] The server's generation AI matches green tea data from the supply database with health food trend data from the demand database to generate an idea for a new product: a "green tea drink with detoxifying effects."

[1811] Furthermore, based on the user's emotional data, the system generates optimal product concepts, target markets, and sales plans as proposals.

[1812] Viewing Suggested Results:

[1813] The user's device displays the proposal results received from the server, and the user can check details such as the product concept and sales plan for the "Green Tea Detox Drink."

[1814] Prompt Sentence Examples

[1815] "Please propose a new product idea that uses green tea, a specialty of Shizuoka Prefecture, and is in line with the health food trend. Please take into account user sentiment data and optimize the proposal results."

[1816] This enables the system to combine regional characteristics with real-time user emotional data to make effective and accurate product recommendations.

[1817] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1818] Step 1:

[1819] Supply Data Collection

[1820] The server uses an API to obtain production and shipping data from local governments and companies. For example, it obtains green tea production data for Shizuoka Prefecture through an HTTP request and saves it as a CSV file. It also uses scraping technology to collect data from publicly available databases and websites. The input is raw data obtained from the API or webpage, and the output is a list of the various types of collected data.

[1821] Step 2:

[1822] Supply data organization

[1823] The server classifies the collected data by region and standardizes the format. For example, it classifies green tea data into the "Shizuoka Prefecture" category and standardizes the weight unit to kg. It deletes any duplicate data and stores the organized data in the supply database. The input is the collected raw data, and the output is an organized, consistent dataset.

[1824] Step 3:

[1825] Demand data collection

[1826] The server collects demand data via APIs of search engines and social media platforms. For example, it obtains the number of searches for a specific keyword (e.g., "green tea health benefits") and saves this as trend data. At the same time, it also collects data from news sites and blogs by crawling. The input is trend data on the Internet, and the output is a list of the collected demand data.

[1827] Step 4:

[1828] Organizing demand data

[1829] The server categorizes the collected demand data by category and standardizes the format. For example, it stores the data in categories such as "healthy foods" and "ecology" and attaches search and mention frequency information. The input is raw data, and the output is an organized demand dataset.

[1830] Step 5:

[1831] Collecting user emotion data

[1832] The server uses an emotion engine installed on the user's device to collect emotion data in real time from the user's voice and facial expressions. For example, a camera captures the user's facial expression while reading an article about green tea and recognizes the emotion as "positive." The input is the user's real-time emotion data, and the output is classified emotion data.

[1833] Step 6:

[1834] Analyzing and organizing emotion data

[1835] The server organizes the collected emotional data by timeline and situation, and creates a basis for optimizing future proposals by referring to past data. For example, it stores data such as "positive reaction after reading an article about green tea at 10:30 on October 15, 2023." The input is emotional data collected in real time, and the output is an analyzed and organized emotional dataset.

[1836] Step 7:

[1837] Data matching by generative AI

[1838] The server's generation AI compares the supply database with the demand database and extracts highly relevant data. For example, it matches "green tea" information from the supply database with "health food trends" information from the demand database. The input is supply data and demand data, and the output is a new product idea as a result of the matching.

[1839] Step 8:

[1840] Generating proposal results taking into account user emotion data

[1841] The server combines the matching results of the generation AI with the user's emotional data to extract optimal product ideas. For example, if the user expresses positive feelings toward green tea, it generates a suggestion for "green tea detox drink." The input is the matching results and emotional data, and the output is a detailed suggestion.

[1842] Step 9:

[1843] Sending the proposal results to the device

[1844] The server sends the generated proposal results to the user's device. For example, it sends the proposal document in JSON format to the device and makes it viewable. The input is the generated proposal results, and the output is the transmitted data.

[1845] Step 10:

[1846] Displaying the proposed results

[1847] The user's terminal displays the proposal results received from the server. For example, a specific product concept or sales plan is displayed on the screen. The input is the proposal results sent from the server, and the output is the displayed information.

[1848] (Application example 2)

[1849] 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."

[1850] Existing product development platforms are limited to simply matching supply and demand data and do not take user sentiment into account. This makes it difficult to propose products that accurately reflect consumers' latent needs. It is also difficult to maximize the appeal of local specialties and develop products that respond to trends in real time. This hinders improvements in sales efficiency and the rapid launch of new products.

[1851] 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.

[1852] In this invention, the server includes a supply data collection means for collecting and organizing data on goods produced and shipped in the region; a demand data collection means for collecting and organizing data on web search history, news articles, social media posts, search trends, and world affairs; a means for building a supply database and a demand database; a means for matching the supply database and the demand database using generative AI to discover and propose products to be introduced; an emotion data collection means for collecting and analyzing user emotion data in real time; a means for optimizing proposal results taking into account the collected emotion data; and a means for displaying the proposal results. This enables accurate product proposals that take into account user emotion in addition to matching supply data and demand data. Furthermore, it is possible to maximize the appeal of regional specialty products and quickly bring new products that are in line with trends to market, which is expected to improve sales efficiency.

[1853] "Supply data collection means" refers to a means for collecting and organizing data on goods produced and shipped in the region.

[1854] "Demand data collection methods" are methods for collecting and organizing data on web search history, news articles, social media posts, search trends, and world events.

[1855] A "supply database" is a database for storing and managing collected supply data.

[1856] A "demand database" is a database for storing and managing collected demand data.

[1857] "Generative AI" is artificial intelligence that collates supply and demand databases and analyzes relevant data.

[1858] The "emotion data collection means" is a means for collecting emotion data from the user's voice, facial expression, input data, etc., and analyzing it in real time.

[1859] The "means for displaying the proposed results" is a means for displaying to the user the product information proposed as a result of analysis by the generation AI.

[1860] A system for implementing the present invention collects supply data, such as goods produced and shipped in a region and services provided, and organizes and stores it in a supply database. It also collects demand data, such as web search history, news articles, social media posts, search trends, and world events, and organizes and stores it in a demand database. The system matches these two databases using generative AI to discover and recommend products that should be marketed. Furthermore, by combining this system with an emotion engine that recognizes user emotions, it can optimize recommendation results based on the user's emotion data.

[1861] System Configuration

[1862] 1. Hardware to be used

[1863] Server (operation of database and generative AI)

[1864] Smartphones and tablets (for the user interface)

[1865] 2. Software to be used

[1866] Database management systems (e.g., MySQL, PostgreSQL)

[1867] Crawling tools for collecting data from news sites, etc. (e.g., Scrapy)

[1868] Emotion engine libraries (e.g., Microsoft Azure Emotion API, Google Cloud Vision API)

[1869] Machine learning libraries (e.g. TensorFlow, PyTorch)

[1870] Web development frameworks (e.g., Django, Flask)

[1871] Program processing flow

[1872] The server uses supply data collection tools to collect production and shipping data from local governments and companies. It also uses scraping technology to obtain information from publicly available databases and websites. The collected data is categorized by region, and detailed information is stored in the supply database.

[1873] Next, the server uses demand data collection means to collect trend information using APIs of search engines and social media platforms, and also obtains data from the latest news sites and blogs using crawling technology, categorizes each piece of information, and stores the detailed information in a demand database.

[1874] Users' emotional data is collected using an emotion engine in an application on a smartphone or tablet. The engine collects users' voices, facial expressions, input data, etc. in real time, analyzes and organizes the emotional data, and stores it in an emotion database.

[1875] The server uses generative AI to match supply and demand databases and automatically extract relevant data. It analyzes the data based on past successes and trend prediction algorithms to predict potential hit products. By taking into account emotional data, it extracts optimal product ideas based on user sentiment and generates proposals that include details such as product concept, target market, and sales plan.

[1876] The proposal results are displayed on the user's smartphone or tablet, and the user can use these results to develop new products and sales strategies.

[1877] Specific examples

[1878] For example, here is a specific example from Shizuoka Prefecture:

[1879] When collecting supply data, information on Shizuoka Prefecture's specialty products, green tea, mandarin oranges, and wasabi, is stored in the supply database. When collecting demand data, the fact that health foods and detoxes are trending is stored in the demand database. When the emotion engine recognizes the user's emotion as "positive," the server's generation AI matches the detox effects of green tea with trend information to generate new product ideas.

[1880] The server generates a proposal for a "detox drink using green tea" and sends it to the user's device. The user can then create a development plan for the green tea drink based on the proposal received.

[1881] Example prompt sentence:

[1882] Please propose new product ideas based on the following supply and demand data. The supply data includes green tea, mandarin oranges, and wasabi from Shizuoka Prefecture. The demand data includes "healthy food," "detox," and "low calorie." Users indicate positive sentiment. Extract the best product ideas and propose a product concept, target market, and sales plan.

[1883] In this way, the present invention not only optimally matches regional characteristics with consumer trends, but also, by combining user emotional data, provides more accurate proposal results, enabling local governments and businesses to advance product development quickly and effectively.

[1884] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1885] Step 1:

[1886] The server collects production and shipping data provided by local governments and companies using supply data collection methods. Specifically, it obtains data using APIs and collects information from public databases and web pages using scraping technology. The collected data is categorized by region and stored in a supply database.

[1887] Input: Production and shipping data from local governments and companies, information from public databases

[1888] Data processing: Classification by region, removal of duplicate data, unification of format

[1889] Output: Supply database

[1890] Step 2:

[1891] The server collects data on web search history, news articles, social media posts, search trends, and world affairs using demand data collection methods. Specifically, it obtains trend information using search engine and social media APIs, and collects data from news sites and blogs using crawling technology. The collected data is categorized and stored in a demand database.

[1892] Input: Web search history, news articles, social media posts, search trends, world events

[1893] Data processing: Classification by category, addition of detailed information (number of searches, frequency of mentions)

[1894] Output: Demand database

[1895] Step 3:

[1896] An emotion engine is used in an application installed on the user's device to collect the user's emotional data. Specifically, voice, facial expressions, and input data are collected and analyzed in real time and stored in an emotion database. The emotional data is organized by time axis and situation.

[1897] Input: User's voice, facial expressions, input data

[1898] Data calculation: Real-time analysis of emotional data, organizing it by time axis and situation

[1899] Output: Emotion database

[1900] Step 4:

[1901] The server uses generative AI to match supply and demand databases and automatically extract relevant data. Specifically, it compares supply and demand data and analyzes the data based on trend prediction algorithms, thereby predicting potential hit products.

[1902] Input: Supply database, Demand database

[1903] Data calculation: Matching supply and demand, data analysis using trend prediction algorithms

[1904] Output: A list of potential hits

[1905] Step 5:

[1906] The server uses the collected emotional data to extract optimal product ideas based on the matching results of the generative AI. Specifically, it adds the emotional data to the analysis results of the generative AI to generate proposals that include details such as the product concept, target market, and sales plan.

[1907] Input: sentiment database, list of potential hit products

[1908] Data calculation: Generate product ideas that reflect emotional data and create detailed proposals

[1909] Output: Optimal product ideas and proposals

[1910] Step 6:

[1911] The proposal results are displayed on the user's device. Specifically, the product ideas and proposal content generated by the server are sent to a smartphone or tablet application and visually displayed to the user. The user can then formulate new product development and sales strategies based on these proposal results.

[1912] Input: Optimal product ideas and proposals

[1913] Action: Sends suggestions and displays them on smartphones and tablets

[1914] Output: Displayed suggestion results

[1915] This series of processes not only optimally matches regional characteristics with consumer trends, but also combines user emotional data to provide more accurate proposal results, enabling local governments and companies to develop products quickly and effectively.

[1916] 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.

[1917] 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.

[1918] 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.

[1919] 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.

[1920] 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.

[1921] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1922] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1923] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1924] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1925] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1926] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1927] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1928] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1929] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1930] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1931] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1932] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1933] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1934] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1935] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1936] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1937] The following is further disclosed regarding the above embodiment.

[1938] (Claim 1)

[1939] A supply data collection means for collecting and organizing data on goods produced and shipped in the region;

[1940] A demand data collection method that collects and organizes data on web search history, news articles, social media posts, search trends, and world events;

[1941] a means for establishing a supply database and a demand database;

[1942] A means of matching supply and demand databases with generation AI to discover and propose products that should be entered into the market,

[1943] a means for displaying the proposal results;

[1944] A system including:

[1945] (Claim 2)

[1946] 10. The system of claim 1, wherein the supply database is configured to include services, tourist attractions, specialty products, and historical industry data provided in the area.

[1947] (Claim 3)

[1948] The system of claim 1 , wherein the demand database is configured to include information in a plurality of categories, such as health-conscious, ecology, technology, gourmet, and travel.

[1949] "Example 1"

[1950] (Claim 1)

[1951] A supply data collection means for collecting and organizing data on goods produced and shipped in the region;

[1952] A demand data collection method for collecting and organizing data on web search history, news articles, information sharing platform posts, search trends, and international affairs;

[1953] a means for establishing a supply database and a demand database;

[1954] A means of matching supply and demand databases with generation AI to propose new products;

[1955] a means for displaying the proposal results;

[1956] means for categorizing supply data by region and storing the data in a supply database with detailed information attached;

[1957] A means of collecting trend information using APIs of search engines and information sharing platforms,

[1958] A means for realizing product ideas based on the matching process and generating proposal contents such as product concepts, target markets, and sales plans;

[1959] A system including:

[1960] (Claim 2)

[1961] 10. The system of claim 1, wherein the supply database is configured to include services, tourist attractions, specialty products, and historical industry data provided in the area.

[1962] (Claim 3)

[1963] The system of claim 1, wherein the demand database is configured to include information in a plurality of categories, such as health consciousness, environmental protection, science and technology, food culture, and travel.

[1964] "Application Example 1"

[1965] (Claim 1)

[1966] A supply data collection means for collecting and organizing data on goods produced and shipped in the region;

[1967] A demand data collection method that collects and organizes data on web search history, news articles, social media posts, search trends, and world events;

[1968] a means for establishing a supply database and a demand database;

[1969] A means of matching supply and demand databases with generation AI to discover and propose products that should be entered into the market,

[1970] a means for displaying the proposal results;

[1971] A means for providing real-time use of the recommendation results using a smart device;

[1972] A system including:

[1973] (Claim 2)

[1974] 10. The system of claim 1, wherein the supply database is configured to include services, tourist attractions, specialty products, and historical industry data provided in the area.

[1975] (Claim 3)

[1976] The system of claim 1 , wherein the demand database is configured to include information in a plurality of categories, such as health-conscious, ecology, technology, gourmet, and travel.

[1977] "Example 2: Combining Emotion Engines"

[1978] (Claim 1)

[1979] A means of collecting and organizing data on goods produced and shipped in the region,

[1980] A means of collecting and organizing data on internet search history, news articles, social network posts, search trends, and world events;

[1981] a means for establishing a supply database and a demand database;

[1982] A means of matching supply and demand databases with artificial intelligence to discover and propose products that should be entered into the market.

[1983] A means for collecting, analyzing, and organizing user emotion data;

[1984] A means for optimizing the proposal results based on emotion data;

[1985] a means for displaying the proposal results;

[1986] A system including:

[1987] (Claim 2)

[1988] 10. The system of claim 1, wherein the supply database is configured to include services, tourist attractions, specialty products, and historical industry data provided in the area.

[1989] (Claim 3)

[1990] The system of claim 1 , wherein the demand database is configured to include information in a plurality of categories, such as health-conscious, ecology, technology, gourmet, and travel.

[1991] "Application example 2 when combining emotion engines"

[1992] (Claim 1)

[1993] A supply data collection means for collecting and organizing data on goods produced and shipped in the region;

[1994] A demand data collection method that collects and organizes data on web search history, news articles, social media posts, search trends, and world events;

[1995] a means for establishing a supply database and a demand database;

[1996] A means of matching supply and demand databases with generation AI to discover and propose products that should be entered into the market,

[1997] emotional data collection means for collecting and analyzing emotional data of users in real time;

[1998] a means for optimizing the recommendation results by taking into account the collected emotional data;

[1999] a means for displaying the proposal results;

[2000] A system including:

[2001] (Claim 2)

[2002] 10. The system of claim 1, wherein the supply database is configured to include services, tourist attractions, specialty products, and historical industry data provided in the area.

[2003] (Claim 3)

[2004] The system of claim 1 , wherein the demand database is configured to include information in a plurality of categories, such as health-conscious, ecology, technology, gourmet, and travel. [Explanation of symbols]

[2005] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A supply data collection means for collecting and organizing data on goods produced and shipped in the region; A demand data collection method that collects and organizes data on web search history, news articles, social media posts, search trends, and world events; a means for establishing a supply database and a demand database; A means of matching supply and demand databases with generation AI to discover and propose products that should be introduced, and a means for displaying the proposal results; A system including:

2. The system of claim 1 , wherein the supply database is configured to include local services, tourist attractions, local specialties, and historical industry data.

3. The system according to claim 1 , wherein the demand database is configured to include information in a plurality of categories, such as health-conscious, ecology, technology, gourmet, and travel.

Images