system

Abstract

We provide the system. [Solution] Means of collecting consumer-related information, A means for analyzing the aforementioned consumer-related information and generating content based on consumer preferences, A means of translating the generated content into multiple languages, A means for optimizing the delivery route of the content translated into the aforementioned multiple languages, A means of promoting the trading of local specialty products using the generated content and suggesting purchases to consumers, A means of suggesting recipes or uses for local specialty products based on consumers' purchase history, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a problem that the recognition of local specialties is low and consumers do not fully understand their charm. In addition, it is necessary to improve the state where it is difficult for specialties to be differentiated from other similar products in the market and attract consumers' attention. It is required to overcome such a situation and activate the regional economy by spreading the charm of local specialties widely.

Means for Solving the Problems

[0005] This invention provides a system that collects consumer-related information, analyzes it, and generates content based on consumer preferences. This system generates recipes and usage examples related to local specialty products based on the collected information, and further distributes the content translated into multiple languages, enabling it to reach a wide range of consumers. Furthermore, by updating the generation algorithm based on feedback from consumers, it can consistently provide content that meets consumer needs. This, in turn, makes it possible to increase awareness of local specialty products and differentiate them in the market.

[0006] "Consumer-related information" refers to data concerning consumer preferences, behavior, and opinions.

[0007] "Analysis" refers to the process of classifying information and identifying patterns based on collected data.

[0008] "Consumer preference-based content" refers to information generated to reflect consumers' interests, concerns, and preferences.

[0009] "Recipes or usage examples related to local specialties" refers to cooking methods or specific ways of using local specialty products.

[0010] "Translation" refers to the process of replacing content written in one language with content in another different language.

[0011] "Distribution" refers to delivering generated content to target consumers.

[0012] "Feedback" refers to information such as opinions, impressions, and evaluations provided by consumers.

[0013] A "generative algorithm" refers to a program or method used to automatically create content. [Brief explanation of the drawing]

[0014] [Figure 1]It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to providing a system that maximizes the appeal of local specialty products and enables effective marketing to consumers. This system is configured to collect and analyze consumer-related information and generate content tailored to consumer preferences based on the results.

[0036] First, the server automatically collects consumer-related information from various data sources on the internet. This includes social media, online reviews, and search queries. Next, the collected data is analyzed using machine learning algorithms installed on the server. This analysis process provides insights into trends and consumer preferences.

[0037] After analysis, the server automatically generates recipes and usage examples related to local specialties based on consumer preferences and trends. For example, it can create a recipe for "apple and cinnamon tart" by incorporating cooking methods preferred by consumers for apples, a specialty product of a particular region. The content generated in this way is designed to attract consumer interest.

[0038] The generated content is translated into multiple languages. The server uses translation algorithms to convert the content into major foreign languages ​​such as English and Chinese. This makes it possible to widely communicate the appeal of local products to consumers both domestically and internationally.

[0039] The translated content is distributed from the server to social media and online platforms. Distribution is optimized according to the attributes of the target consumer. For example, Instagram is used for younger demographics, while LinkedIn® is used for professionals. This ensures effective communication to the target market.

[0040] Furthermore, this system has the ability to collect consumer feedback on the content actually provided. Users can react to the delivered content, providing ratings and comments. This feedback is collected on the server via the device and used to improve the generation algorithm for future content.

[0041] As described above, the present invention provides a consistent marketing system for effectively promoting local specialty products.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server collects consumer-related information from various data sources on the internet. This includes social media posts, online reviews, and search engine query data, which are automatically collected using APIs and crawling technologies.

[0045] Step 2:

[0046] The server analyzes the collected data using machine learning algorithms. At this stage, natural language processing techniques are used to extract consumer sentiment and preference patterns contained in the data and identify trends.

[0047] Step 3:

[0048] The server generates content that reflects consumer preferences related to local specialties based on the analysis results. For example, if the collected data is about apples, it will automatically create content that consumers will find interesting, such as a "new baked apple recipe."

[0049] Step 4:

[0050] The server translates the generated content into multiple languages. It utilizes machine translation technology to create language variations suitable for major markets, catering to a global consumer base.

[0051] Step 5:

[0052] The server distributes the translated content to selected social media and online platforms. It chooses the most effective platform (e.g., Facebook or Instagram) based on the attributes of the target audience and publishes the content according to a pre-set schedule.

[0053] Step 6:

[0054] Users react to delivered content by viewing, empathizing with, sharing, and rating it. These interactions serve as important feedback for measuring content acceptance.

[0055] Step 7:

[0056] The device collects user feedback and reaction data and sends it to the server. This feedback is used as data to more accurately reflect consumer needs when creating future content.

[0057] Step 8:

[0058] The server updates its generation algorithm based on feedback data to improve the quality and relevance of the content. This updating process is iterative, and the system is constantly adjusted to adapt to changing consumer preferences.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] There is a need to accurately understand the diverse preferences of consumers, generate engaging content based on those preferences, and efficiently distribute information to international consumers. Furthermore, it is necessary to collect consumer feedback and adaptively improve the content generation system to enhance the accuracy and effectiveness of the content.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for automatically acquiring consumer-related information from multiple information sources, means for analyzing the consumer-related information using a machine learning algorithm to generate content based on consumer preferences, and means for translating the generated content into multiple languages ​​using natural language processing technology. This enables the generation of content that matches consumer preferences and improves the efficiency of international information transmission.

[0064] "Consumer-related information" refers to all data concerning consumers, including their preferences, interests, behavioral patterns, and purchase history.

[0065] A "machine learning algorithm" refers to an automated computational method used to analyze collected data and identify patterns and trends.

[0066] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate human language, and includes text translation, sentiment analysis, and topic modeling.

[0067] "Translating into multiple languages" refers to the process of converting content written in one language into several different languages.

[0068] "Feedback mechanisms" refer to the methods and processes for collecting consumer reactions, evaluations, and opinions on generated content, and for analyzing and incorporating them into system improvements.

[0069] A "generative algorithm" refers to a structured procedure and method for automatically creating new content based on data analysis results.

[0070] This system aims to effectively communicate the appeal of local specialty products to consumers. The system's implementation primarily involves server-side processing, with user interaction occurring via terminals. The details of its structure are described below.

[0071] First, the server automatically collects consumer-related information from various sources on the internet. This process utilizes web crawlers and APIs to obtain data from social media, online reviews, and web search queries. Specific software used includes Python's Beautiful Soup and Scrapy.

[0072] Next, the server processes the collected data. Using machine learning libraries such as Scikit-learn and TENSORFLOW®, it performs data cleansing and topic modeling, and analyzes consumer preferences and trend data. This analysis helps to understand the characteristics of target consumers and obtain base information for generating content that matches their needs.

[0073] Using a generative AI model, the server generates specific content. For example, based on analysis results, it can devise new recipes using local specialties that consumers prefer. An example of a prompt is, "Generate a new dessert recipe using apples." Based on this prompt, the generative AI creates a specific recipe that meets consumer needs.

[0074] Subsequently, the generated content is translated into multiple languages. The server uses Google Translate API and other tools to translate the content into English, Spanish, French, and other languages. This translation process makes it possible to convey the appeal of local products to a wide range of consumers both domestically and internationally.

[0075] Furthermore, translated content is distributed through social media and online platforms. The server appropriately sets the distribution destination according to the attributes of the target consumers, selecting the most suitable platform based on those attributes, such as using Instagram or LinkedIn. This distribution allows for effective reach to the target market.

[0076] Finally, users can provide feedback on the content delivered through their devices. Ratings and comments are collected on the server via the devices. The collected feedback data is used to improve the generation algorithm for future content, enabling the creation of more sophisticated content. In this way, the system effectively promotes local specialty products.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server collects consumer-related information from social media, online reviews, and web search queries on the internet. This step utilizes tools such as Beautiful Soup and Scrapy to retrieve data via crawlers and APIs. Inputs are web pages and databases, and output is a set of collected raw data.

[0080] Step 2:

[0081] The server processes and analyzes the collected raw data. Specifically, it uses Python's Scikit-learn and TensorFlow to perform data cleansing, topic modeling, and sentiment analysis. The input is the raw data obtained in step 1, and the output is consumer preference patterns and trend information. This analysis allows for the identification of products and topics of particular interest.

[0082] Step 3:

[0083] The server generates content using a generative AI model based on the analysis results. At this stage, prompts are input to the generative AI to create specific recipes and usage examples. For example, a prompt such as "Generate a new dessert recipe using apples" is sent. The input is the analysis results from step 2 and a specific prompt, and the output is customized content tailored to the consumer.

[0084] Step 4:

[0085] The server translates the generated content into multiple languages. It uses the Google Translate API to convert the content into major foreign languages. The input is the generated content from step 3, and the output is the multilingualized content. This process enables the service to be tailored to consumers with diverse language backgrounds.

[0086] Step 5:

[0087] The server distributes the translated content to social media and online platforms. In this step, the appropriate platform, such as Instagram or LinkedIn, is selected based on consumer attributes. The input is the multilingual content from step 4, and the output is distribution to the target consumer group. This process enables effective marketing.

[0088] Step 6:

[0089] Users provide feedback on content delivered through their devices. User ratings and comments are sent to the server via the device and used to improve the algorithm for future deliveries. The input is user feedback, and the output is an indicator of the improved algorithm. Using this information, the server can further optimize the next content generation process.

[0090] (Application Example 1)

[0091] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] Today's consumers have diverse preferences, making effective marketing of local specialty products complex. Furthermore, communicating the appeal of these products to consumers with different language and cultural backgrounds in international markets is challenging. Additionally, personalized product recommendations based on consumer purchase history are often inadequate. Therefore, innovative systems are needed to effectively promote the trade of local specialty products and attract consumer interest.

[0093] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0094] In this invention, the server includes means for collecting consumer-related information, means for analyzing the consumer-related information to generate content based on consumer preferences, and means for translating the generated content into multiple languages. This enables the effective communication of the characteristics and usage examples of local products in multiple languages, and allows for personalized product suggestions based on the consumer's purchase history.

[0095] "Consumer-related information" refers to various types of data related to consumer preferences and purchasing behavior.

[0096] "Analysis" is the process of extracting consumer trends and preferences based on collected data.

[0097] "Content" refers to information provided to consumers, such as information related to local specialty products, recipes, and usage examples.

[0098] "Multilingual" refers to a means of responding to diverse markets by translating specific information into one or more languages.

[0099] "Optimizing delivery routes" refers to the process of optimizing delivery routes and methods in order to efficiently deliver products to consumers.

[0100] "Promoting transactions" refers to the means of encouraging consumers to purchase local specialty products and thereby increasing sales.

[0101] "Recommendations based on purchase history" is a technology that recommends local specialty products based on past consumer purchase data.

[0102] "Feedback" refers to opinions and evaluations provided by consumers, and is used to improve the system.

[0103] This invention is a marketing system designed to effectively convey the appeal of local specialty products to consumers. The system collects consumer-related information from various data sources, analyzes that data, and generates content tailored to consumer preferences. Specifically, a server collects consumer-related information from social media, online reviews, and search queries on the internet, and analyzes trends using machine learning algorithms. Based on these results, the server generates recipes and usage instructions for local specialty products that match consumer preferences. The generated content is translated into multiple languages ​​and distributed on the most suitable platform according to the attributes of the target consumers.

[0104] In this invention, the server uses high-performance hardware and can utilize cloud services such as Google Cloud Platform and Amazon Web Services. Software tools such as TensorFlow and PyTorch are used for machine learning, and NLTK and spaCy are used for natural language processing. Furthermore, the Google Translate API and similar tools are utilized for multilingual translation.

[0105] For example, if a user is interested in the local specialty "matcha," the server can generate various matcha recipes, translate them, and distribute them to the mobile apps of social media and online shopping sites that the user frequently visits. User feedback is collected through the device and used to create future content.

[0106] An example of a prompt for a generative AI model is, "Based on user preferences, suggest new ways to use local products that they might be interested in."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server automatically collects consumer-related information from social media, online reviews, and search queries on the internet. The input consists of various online data sources, and the output is raw data related to consumer preferences and trends. This step utilizes web crawling technology for data collection.

[0110] Step 2:

[0111] The server analyzes the collected consumer-related information using machine learning algorithms. The input is the raw consumer-related data obtained in step 1, and the output is the analysis results showing preferences and trends. This process uses TensorFlow and PyTorch to perform trend prediction and preference analysis.

[0112] Step 3:

[0113] The server generates content related to local specialties based on the analysis results. The input is the analysis results obtained in step 2, and the output is content such as recipes and usage examples for the local specialties. In this step, natural language generation technology is used to generate the content.

[0114] Step 4:

[0115] The server translates the generated content into multiple languages. The input is the content generated in step 3, and the output is the content translated into multiple languages. Translation is performed using a translation tool such as the Google Translate API.

[0116] Step 5:

[0117] The server delivers the translated content to the most suitable online platform for the target consumer. The input is the multilingual content obtained in step 4, and the output is the content delivered to each platform. This step involves integration with applications such as social media and e-commerce sites.

[0118] Step 6:

[0119] Users view the delivered content and send feedback from their devices to the server. Input consists of user ratings and comments, while output is feedback data stored on the server. This feedback is later analyzed and used to improve future content creation.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] This invention combines a consumer-related content generation system with an emotion engine that recognizes user emotions to achieve more personalized information delivery. This system has a function to recognize the user's emotional state in real time during the process of generating content based on consumer preferences and to reflect this in the generated content.

[0122] First, the server automatically collects consumer-related information from the internet. Sources include social media posts, review sites, and search engine queries. Next, this collected data is analyzed within the server using machine learning algorithms to reveal user preferences and trends.

[0123] Subsequently, based on consumer preferences and analysis results, recipes and usage examples related to local specialties are generated. For example, regarding locally produced tomatoes, if a user prefers "soup recipes using particularly sweet varieties," content can be automatically generated.

[0124] Next, by combining this system with an emotion engine, the device analyzes the user's emotions in real time. The emotion engine, for example, analyzes facial expressions and voice through the camera or voice input while the user is viewing content, and recognizes emotional states such as "excited" or "calm."

[0125] The server further personalizes content based on recognized user emotion data. For example, if the user is excited, it can suggest additional recipes for refreshing local specialty juices.

[0126] The generated content is made multilingual and distributed to social media and online platforms to attract attention. Specifically, content related to local specialties is translated into English, Chinese, and Spanish, and the platform is selected to reach the target audience.

[0127] Users can rate and provide feedback on the delivered content, and this data is collected on the server via their devices. This feedback is used to create future content, allowing us to constantly provide content optimized to meet the latest consumer needs and sentiments.

[0128] This invention is designed to enable the provision of personalized content that accurately captures the emotional state of users, thereby attracting greater consumer interest.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The server collects consumer-related information through users' internet activities. Specifically, it gathers social media posts, comments, review site ratings, and search history using APIs and web scraping.

[0132] Step 2:

[0133] The server uses machine learning algorithms to analyze the collected data. This analysis extracts consumer preferences and trends, and evaluates consumer interest in specific products and keywords.

[0134] Step 3:

[0135] The server generates content related to local specialties based on the analysis results. At this stage, it automatically creates recipes and usage examples for the specialties according to consumer preferences. For example, it might devise a "refreshing dessert recipe" using fruits from the local area.

[0136] Step 4:

[0137] The device transmits emotional data to the emotion engine using the user's camera and microphone. The emotion engine identifies the user's emotional state in real time through facial expression analysis and voice tone analysis.

[0138] Step 5:

[0139] The server adjusts the generated content based on the user's emotional state, as determined by the emotion engine. For example, if it determines that the user is stressed, it prioritizes content that introduces products or methods for use that have a relaxing effect.

[0140] Step 6:

[0141] The server translates personalized content into multiple languages ​​and delivers it through the most suitable platform for the target market. Specifically, the translated content is shared on Facebook, Instagram, Twitter, and other platforms, reaching consumers in specific regions and language areas.

[0142] Step 7:

[0143] Users view the delivered content and provide feedback on it. This feedback is collected through form submissions, comments, and rating systems.

[0144] Step 8:

[0145] The device organizes user feedback and sends it to the server. The server analyzes the feedback data and uses it to improve future content generation and sentiment analysis algorithms.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] In today's information society, consumers are exposed to vast amounts of information, making it crucial to efficiently provide them with information that matches their individual needs. However, conventional systems have a challenge in adequately providing personalized information based on consumer preferences and emotions. Furthermore, multilingual support is limited, resulting in insufficient service provision to global users. In addition, there is a need to effectively utilize consumer feedback to improve content quality.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes means for collecting consumer-related information, means for analyzing the consumer information and generating content based on the consumer's preferences, and means for recognizing the user's emotions and further personalizing the generated content based on those emotions. This makes it possible to provide personalized information based on the individual consumer's preferences and emotions.

[0151] "Consumer-related information" refers to data and feedback related to consumer behavior, preferences, and opinions.

[0152] "Analysis" refers to the process of analyzing collected data to identify consumer trends and patterns.

[0153] "Generating content" refers to creating new information such as text, images, and videos based on consumer information.

[0154] "Recognizing user emotions" refers to technology that identifies the user's emotional state at a given time based on their facial expressions, voice, and other factors.

[0155] "Personalization" refers to optimizing the information provided to individual consumers according to their preferences and emotions.

[0156] "Multilingual conversion" refers to the process of translating generated content into multiple different languages.

[0157] "Sending" refers to delivering generated content to users via communication methods such as the internet.

[0158] "Product information or usage examples related to specific items" refers to products and their applications that are characteristic of a particular region or culture.

[0159] "Gathering feedback" refers to the act of collecting feedback and opinions from consumers.

[0160] "Updating generation instructions" refers to improving the instructions and processes for generating content based on newly acquired data.

[0161] The following describes embodiments for carrying out the present invention. This system is designed to provide individually optimized information, taking into account consumer preferences and real-time emotional states.

[0162] First, the server collects information from the internet. This involves methods such as web scraping and APIs to gather data from social media posts, review sites, and search engines. At this stage, a vast amount of data on consumer behavior is collected.

[0163] Next, the collected data is analyzed on the server. Machine learning algorithms are used for data analysis to extract consumer preferences and behavioral patterns. Text mining and natural language processing techniques are used in this analysis. Based on the analysis results, a generative AI model is used to generate consumer-related content. For example, recipes using local specialties from a specific region are automatically created.

[0164] Furthermore, this system incorporates an emotion engine. The device can recognize the user's emotions in real time by analyzing their facial expressions and voice. This enables personalization based on the user's emotional state. For example, if a user is excited, it can provide products or information with a suitable refreshing effect.

[0165] The generated content is translated into multiple languages ​​and distributed to target users through online platforms. For example, information about local products is translated into English, Chinese, Spanish, and other languages ​​and sent to consumers who speak those languages.

[0166] Finally, users can provide ratings and feedback on the content, and this data is again aggregated on the server and used to create future content. This ensures that users are always provided with the latest and most relevant information.

[0167] A concrete example of a prompt message could be: "Please provide a recipe using very sweet tomatoes. Please consider the user's emotions in the process." This is how the system provides personalized information tailored to the user's preferences and emotions.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] The server collects consumer information from the internet. This process uses social media APIs and web scraping techniques to collect posts containing specific keywords and hashtags. The input data consists of social media posts and word-of-mouth information, and the output is structured data. Specifically, the server periodically crawls the information sources and stores new data in the database.

[0171] Step 2:

[0172] The server analyzes the collected data. This process uses machine learning algorithms to extract consumer preferences and trends. The input is the data obtained in step 1, and the output is consumer preference patterns and trend information. Specifically, it performs text mining and clustering to identify products and categories that consumers prefer.

[0173] Step 3:

[0174] The server generates content using a generative AI model. At this stage, it uses the analysis results obtained in step 2 as input to create personalized content for specific consumers. The output is content such as recipes and product information. Specifically, it prompts the generative AI model with the message, "Generate a new cooking recipe using popular local products," and retrieves a new recipe.

[0175] Step 4:

[0176] The device recognizes the user's emotions in real time. An emotion engine uses data collected from the camera and microphone to determine the user's emotional state. Input is the user's facial expressions and voice data, and output is an emotion label such as "excited" or "calm." Specific operations include facial image analysis using facial recognition technology and tone analysis using voice analysis.

[0177] Step 5:

[0178] The server further personalizes the content based on the user's emotional data. It takes the emotional data into account and makes final adjustments to the content created in Step 3. The input is the emotional label and generated content, and the output is content adapted to the user's state. For example, a relaxed user might receive a suggestion for a refreshing local juice.

[0179] Step 6:

[0180] The server translates and transmits the completed content in multiple languages. At this stage, the generated content is converted into multiple languages ​​and delivered to users in the target country or region. The input is the content completed up to step 5, and the output is multilingual content. Specifically, a translation API is used to convert the content into English, Chinese, Spanish, etc., and distribute it to the online platform.

[0181] Step 7:

[0182] Users view the received content and provide ratings and feedback. This feedback is sent to the server via the device and used to improve future content creation. The input is the user's feedback, and the output is the rating data stored in the server's database. Specifically, users communicate their ease of use, satisfaction with the content, etc., to the server through a rating form.

[0183] (Application Example 2)

[0184] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0185] Conventional content delivery systems have the challenge of not adequately personalizing content based on individual user emotions and preferences, making it difficult to achieve comprehensive consumer satisfaction. Furthermore, when providing multilingual support, flexible content adjustments based on user emotions are not implemented. There is a need for a system that can solve these problems and enable more effective information delivery.

[0186] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0187] In this invention, the server includes a structure for collecting consumption data, a structure for analyzing the consumption data and generating content based on the user's preferences, a structure for translating the generated content into multiple languages, a structure for recognizing the user's emotional state in real time, and a structure for further individualizing the content according to the emotional state. This enables a high level of personalization that responds to the user's emotions and preferences.

[0188] "Consumer data" refers to information about users' purchase history, browsing history, and behavioral patterns.

[0189] "User preferences" refer to the products, services, or areas of interest that a particular user enjoys.

[0190] A "content generation structure" is a system that generates relevant information and suggested content based on users' consumption data and preferences.

[0191] A "multilingual translation structure" is a system that translates generated content into different languages ​​and delivers it to diverse users in an appropriate format.

[0192] "User's emotional state" refers to information that indicates the user's current feelings and emotional state, such as joy or dissatisfaction.

[0193] A "real-time recognition structure" is a system that analyzes data in accordance with the current situation and obtains results immediately.

[0194] A "personalized structure" is a mechanism for adjusting and optimizing content and services to suit specific users.

[0195] One embodiment of this invention is a system for realizing an e-commerce site application incorporating an emotion engine. The details are described below.

[0196] The server first collects user consumption data, including browsing and purchase history. Next, it analyzes the collected data to generate personalized content based on the user's preferences. This process utilizes machine learning algorithms to automatically create content that is more interesting and engaging to the user.

[0197] The device collects data through its camera and microphone to recognize the user's emotional state in real time, and analyzes it using machine learning models such as TensorFlow. This allows it to recognize the emotions the user is feeling while browsing products, such as "enjoying" or "confusing."

[0198] The server further customizes content for each user based on the recognized emotion data. For example, if it recognizes that a user is happy, it adjusts the content to proactively suggest related products and discount information. This process enables more effective product recommendations that are tailored to the user's emotions and preferences.

[0199] If a user's facial expression indicates confusion while searching for a new gadget, the server can provide relevant review articles or FAQ pages to alleviate the user's confusion. An example of a prompt to input into the generating AI model would be, "Generate the best product suggestions based on the following emotion data: Enjoying, Interested."

[0200] This system makes it possible to personalize the experience based on the user's latest emotions and preferences, thereby improving consumer satisfaction.

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The server collects user consumption data via the internet. Input data includes browsing history and purchase history. The server retrieves this data and stores it in a database.

[0204] Step 2:

[0205] The server analyzes stored consumption data using machine learning algorithms. The input is consumption data, and the output is features related to the user's preferences and interests. Through this analysis, the server identifies products and content that the user is most likely to be interested in.

[0206] Step 3:

[0207] The device collects the user's facial expressions and voice through its camera and microphone, and analyzes their emotional state in real time. Video and audio are provided as input data, which is processed by machine learning models such as TensorFlow, and the output generates emotion labels such as "enjoying" or "confused."

[0208] Step 4:

[0209] The server integrates user emotional states and preference data to generate personalized content. Inputs are emotional labels and preference features, while outputs are personalized product suggestions and information. The server combines this data to create optimal content that captures the user's interest.

[0210] Step 5:

[0211] The server translates the generated personalized content into the required target language through a multilingual translation engine. The input is the generated content, and the output is the translated content. This allows the server to deliver content appropriately to a global audience.

[0212] Step 6:

[0213] Users view personalized content provided on their devices, select products, and provide feedback. Input consists of user selections and feedback, while output is information for improving future content. The device sends this information to a server for use in improving future content.

[0214] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0215] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0230] This invention relates to providing a system that maximizes the appeal of local specialty products and enables effective marketing to consumers. This system is configured to collect and analyze consumer-related information and generate content tailored to consumer preferences based on the results.

[0231] First, the server automatically collects consumer-related information from various data sources on the internet. This includes social media, online reviews, and search queries. Next, the collected data is analyzed using machine learning algorithms installed on the server. This analysis process provides insights into trends and consumer preferences.

[0232] After analysis, the server automatically generates recipes and usage examples related to local specialties based on consumer preferences and trends. For example, it can create a recipe for "apple and cinnamon tart" by incorporating cooking methods preferred by consumers for apples, a specialty product of a particular region. The content generated in this way is designed to attract consumer interest.

[0233] The generated content is translated into multiple languages. The server uses translation algorithms to convert the content into major foreign languages ​​such as English and Chinese. This makes it possible to widely communicate the appeal of local products to consumers both domestically and internationally.

[0234] The translated content is distributed from the server to social media and online platforms. Distribution is optimized according to the attributes of the target consumer. For example, Instagram is used for younger demographics, while LinkedIn is used for professionals. This ensures effective communication to the target market.

[0235] Furthermore, this system has the ability to collect consumer feedback on the content actually provided. Users can react to the delivered content, providing ratings and comments. This feedback is collected on the server via the device and used to improve the generation algorithm for future content.

[0236] As described above, the present invention provides a consistent marketing system for effectively promoting local specialty products.

[0237] The following describes the processing flow.

[0238] Step 1:

[0239] The server collects consumer-related information from various data sources on the internet. This includes social media posts, online reviews, and search engine query data, which are automatically collected using APIs and crawling technologies.

[0240] Step 2:

[0241] The server analyzes the collected data using machine learning algorithms. At this stage, natural language processing techniques are used to extract consumer sentiment and preference patterns contained in the data and identify trends.

[0242] Step 3:

[0243] The server generates content that reflects consumer preferences related to local specialties based on the analysis results. For example, if the collected data is about apples, it will automatically create content that consumers will find interesting, such as a "new baked apple recipe."

[0244] Step 4:

[0245] The server translates the generated content into multiple languages. It utilizes machine translation technology to create language variations suitable for major markets, catering to a global consumer base.

[0246] Step 5:

[0247] The server distributes the translated content to selected social media and online platforms. It chooses the most effective platform (e.g., Facebook or Instagram) based on the attributes of the target audience and publishes the content according to a pre-set schedule.

[0248] Step 6:

[0249] Users react to delivered content by viewing, empathizing with, sharing, and rating it. These interactions serve as important feedback for measuring content acceptance.

[0250] Step 7:

[0251] The device collects user feedback and reaction data and sends it to the server. This feedback is used as data to more accurately reflect consumer needs when creating future content.

[0252] Step 8:

[0253] The server updates its generation algorithm based on feedback data to improve the quality and relevance of the content. This updating process is iterative, and the system is constantly adjusted to adapt to changing consumer preferences.

[0254] (Example 1)

[0255] Next, we will describe Example 1. 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."

[0256] There is a need to accurately understand the diverse preferences of consumers, generate engaging content based on those preferences, and efficiently distribute information to international consumers. Furthermore, it is necessary to collect consumer feedback and adaptively improve the content generation system to enhance the accuracy and effectiveness of the content.

[0257] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0258] In this invention, the server includes means for automatically acquiring consumer-related information from multiple information sources, means for analyzing the consumer-related information using a machine learning algorithm to generate content based on consumer preferences, and means for translating the generated content into multiple languages ​​using natural language processing technology. This enables the generation of content that matches consumer preferences and improves the efficiency of international information transmission.

[0259] "Consumer-related information" refers to all data concerning consumers, including their preferences, interests, behavioral patterns, and purchase history.

[0260] A "machine learning algorithm" refers to an automated computational method used to analyze collected data and identify patterns and trends.

[0261] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate human language, and includes text translation, sentiment analysis, and topic modeling.

[0262] "Translating into multiple languages" refers to the process of converting content written in one language into several different languages.

[0263] "Feedback mechanisms" refer to the methods and processes for collecting consumer reactions, evaluations, and opinions on generated content, and for analyzing and incorporating them into system improvements.

[0264] A "generative algorithm" refers to a structured procedure and method for automatically creating new content based on data analysis results.

[0265] This system aims to effectively communicate the appeal of local specialty products to consumers. The system's implementation primarily involves server-side processing, with user interaction occurring via terminals. The details of its structure are described below.

[0266] First, the server automatically collects consumer-related information from various sources on the internet. This process utilizes web crawlers and APIs to obtain data from social media, online reviews, and web search queries. Specific software used includes Python's Beautiful Soup and Scrapy.

[0267] Next, the server processes the collected data. Using machine learning libraries such as Scikit-learn and TensorFlow, it performs data cleansing and topic modeling, and analyzes consumer preferences and trend data. This analysis helps to understand the characteristics of target consumers and obtain base information for generating content that matches their needs.

[0268] Using a generative AI model, the server generates specific content. For example, based on analysis results, it can devise new recipes using local specialties that consumers prefer. An example of a prompt is, "Generate a new dessert recipe using apples." Based on this prompt, the generative AI creates a specific recipe that meets consumer needs.

[0269] Subsequently, the generated content is translated into multiple languages. The server uses the Google Translate API and other tools to translate the content into English, Spanish, French, and other languages. This translation process makes it possible to convey the appeal of local products to a wide range of consumers both domestically and internationally.

[0270] Furthermore, translated content is distributed through social media and online platforms. The server appropriately sets the distribution destination according to the attributes of the target consumers, selecting the most suitable platform based on those attributes, such as using Instagram or LinkedIn. This distribution allows for effective reach to the target market.

[0271] Finally, users can provide feedback on the content delivered through their devices. Ratings and comments are collected on the server via the devices. The collected feedback data is used to improve the generation algorithm for future content, enabling the creation of more sophisticated content. In this way, the system effectively promotes local specialty products.

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The server collects consumer-related information from social media, online reviews, and web search queries on the internet. This step utilizes tools such as Beautiful Soup and Scrapy to retrieve data via crawlers and APIs. Inputs are web pages and databases, and output is a set of collected raw data.

[0275] Step 2:

[0276] The server processes and analyzes the collected raw data. Specifically, it uses Python's Scikit-learn and TensorFlow to perform data cleansing, topic modeling, and sentiment analysis. The input is the raw data obtained in step 1, and the output is consumer preference patterns and trend information. This analysis allows for the identification of products and topics of particular interest.

[0277] Step 3:

[0278] The server generates content using a generative AI model based on the analysis results. At this stage, prompts are input to the generative AI to create specific recipes and usage examples. For example, a prompt such as "Generate a new dessert recipe using apples" is sent. The input is the analysis results from step 2 and a specific prompt, and the output is customized content tailored to the consumer.

[0279] Step 4:

[0280] The server translates the generated content into multiple languages. Using the Google Translate API, the content is converted into major foreign languages. The input is the generated content from Step 3, and the output is the content that supports multiple languages. This process enables catering to consumers with various language backgrounds.

[0281] Step 5:

[0282] The server distributes the translated content to SNS and online platforms. In this step, appropriate platforms such as Instagram and LinkedIn are selected according to the attributes of consumers. The input is the multilingual content from Step 4, and the output is the distribution to the target consumer group. This process realizes effective marketing.

[0283] Step 6:

[0284] Users provide feedback on the content distributed through the terminal. The evaluations and comments of users are sent to the server via the terminal and are utilized for improving the algorithm in subsequent times. The input is the feedback from users, and the output is the indicators for the improved algorithm. Using this information, the server can further optimize the next content generation process.

[0285] (Application Example 1)

[0286] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0287] Today's consumers have diverse preferences, making effective marketing of local specialty products complex. Furthermore, communicating the appeal of these products to consumers with different language and cultural backgrounds in international markets is challenging. Additionally, personalized product recommendations based on consumer purchase history are often inadequate. Therefore, innovative systems are needed to effectively promote the trade of local specialty products and attract consumer interest.

[0288] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0289] In this invention, the server includes means for collecting consumer-related information, means for analyzing the consumer-related information to generate content based on consumer preferences, and means for translating the generated content into multiple languages. This enables the effective communication of the characteristics and usage examples of local products in multiple languages, and allows for personalized product suggestions based on the consumer's purchase history.

[0290] "Consumer-related information" refers to various types of data related to consumer preferences and purchasing behavior.

[0291] "Analysis" is the process of extracting consumer trends and preferences based on collected data.

[0292] "Content" refers to information provided to consumers, such as information related to local specialty products, recipes, and usage examples.

[0293] "Multilingual" refers to a means of responding to diverse markets by translating specific information into one or more languages.

[0294] "Optimizing delivery routes" refers to the process of optimizing delivery routes and methods in order to efficiently deliver products to consumers.

[0295] "Promoting transactions" refers to the means of encouraging consumers to purchase local specialty products and thereby increasing sales.

[0296] "Recommendations based on purchase history" is a technology that recommends local specialty products based on past consumer purchase data.

[0297] "Feedback" refers to opinions and evaluations provided by consumers, and is used to improve the system.

[0298] This invention is a marketing system designed to effectively convey the appeal of local specialty products to consumers. The system collects consumer-related information from various data sources, analyzes that data, and generates content tailored to consumer preferences. Specifically, a server collects consumer-related information from social media, online reviews, and search queries on the internet, and analyzes trends using machine learning algorithms. Based on these results, the server generates recipes and usage instructions for local specialty products that match consumer preferences. The generated content is translated into multiple languages ​​and distributed on the most suitable platform according to the attributes of the target consumers.

[0299] In this invention, the server uses high-performance hardware and can utilize cloud services such as Google Cloud Platform and Amazon Web Services. Software tools such as TensorFlow and PyTorch are used for machine learning, and NLTK and spaCy are used for natural language processing. Furthermore, the Google Translate API and similar tools are utilized for multilingual translation.

[0300] For example, if a user is interested in the local specialty "matcha," the server can generate various matcha recipes, translate them, and distribute them to the mobile apps of social media and online shopping sites that the user frequently visits. User feedback is collected through the device and used to create future content.

[0301] An example of a prompt for a generative AI model is, "Based on user preferences, suggest new ways to use local products that they might be interested in."

[0302] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0303] Step 1:

[0304] The server automatically collects consumer-related information from SNSs, online reviews, and search queries on the Internet. The input is various online data sources, and the output is raw data related to consumer preferences and trends. In this step, data collection is performed using web crawling technology.

[0305] Step 2:

[0306] The server analyzes the collected consumer-related information using machine learning algorithms. The input is the raw data of consumer-related information obtained in Step 1, and the output is the analysis result indicating preferences and trends. In this process, TensorFlow or PyTorch is used to perform trend prediction and preference analysis.

[0307] Step 3:

[0308] The server generates content related to specialty products based on the analysis result. The input is the analysis result obtained in Step 2, and the output is content such as recipes and usage examples of specialty products. In this step, natural language generation technology is utilized to generate content.

[0309] Step 4:

[0310] The server translates the generated content into multiple languages. The input is the content generated in Step 3, and the output is the content translated into multiple languages. Translation is performed using a translation tool such as the Google Translate API.

[0311] Step 5:

[0312] The server delivers the translated content to the most suitable online platform for the target consumer. The input is the multilingual content obtained in step 4, and the output is the content delivered to each platform. This step involves integration with applications such as social media and e-commerce sites.

[0313] Step 6:

[0314] Users view the delivered content and send feedback from their devices to the server. Input consists of user ratings and comments, while output is feedback data stored on the server. This feedback is later analyzed and used to improve future content creation.

[0315] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0316] This invention combines a consumer-related content generation system with an emotion engine that recognizes user emotions to achieve more personalized information delivery. This system has a function to recognize the user's emotional state in real time during the process of generating content based on consumer preferences and to reflect this in the generated content.

[0317] First, the server automatically collects consumer-related information from the internet. Sources include social media posts, review sites, and search engine queries. Next, this collected data is analyzed within the server using machine learning algorithms to reveal user preferences and trends.

[0318] Subsequently, based on consumer preferences and analysis results, recipes and usage examples related to local specialties are generated. For example, regarding locally produced tomatoes, if a user prefers "soup recipes using particularly sweet varieties," content can be automatically generated.

[0319] Next, by combining this system with an emotion engine, the device analyzes the user's emotions in real time. The emotion engine, for example, analyzes facial expressions and voice through the camera or voice input while the user is viewing content, and recognizes emotional states such as "excited" or "calm."

[0320] The server further personalizes content based on recognized user emotion data. For example, if the user is excited, it can suggest additional recipes for refreshing local specialty juices.

[0321] The generated content is made multilingual and distributed to social media and online platforms to attract attention. Specifically, content related to local specialties is translated into English, Chinese, and Spanish, and the platform is selected to reach the target audience.

[0322] Users can rate and provide feedback on the delivered content, and this data is collected on the server via their devices. This feedback is used to create future content, allowing us to constantly provide content optimized to meet the latest consumer needs and sentiments.

[0323] This invention is designed to enable the provision of personalized content that accurately captures the emotional state of users, thereby attracting greater consumer interest.

[0324] The following describes the processing flow.

[0325] Step 1:

[0326] The server collects consumer-related information through users' internet activities. Specifically, it gathers social media posts, comments, review site ratings, and search history using APIs and web scraping.

[0327] Step 2:

[0328] The server uses machine learning algorithms to analyze the collected data. This analysis extracts consumer preferences and trends, and evaluates consumer interest in specific products and keywords.

[0329] Step 3:

[0330] The server generates content related to local specialties based on the analysis results. At this stage, it automatically creates recipes and usage examples for the specialties according to consumer preferences. For example, it might devise a "refreshing dessert recipe" using fruits from the local area.

[0331] Step 4:

[0332] The device transmits emotional data to the emotion engine using the user's camera and microphone. The emotion engine identifies the user's emotional state in real time through facial expression analysis and voice tone analysis.

[0333] Step 5:

[0334] The server adjusts the generated content based on the user's emotional state, as determined by the emotion engine. For example, if it determines that the user is stressed, it prioritizes content that introduces products or methods for use that have a relaxing effect.

[0335] Step 6:

[0336] The server translates personalized content into multiple languages ​​and delivers it through the most suitable platform for the target market. Specifically, the translated content is shared on Facebook, Instagram, Twitter, and other platforms, reaching consumers in specific regions and language areas.

[0337] Step 7:

[0338] Users view the delivered content and provide feedback on it. This feedback is collected through form submissions, comments, and rating systems.

[0339] Step 8:

[0340] The device organizes user feedback and sends it to the server. The server analyzes the feedback data and uses it to improve future content generation and sentiment analysis algorithms.

[0341] (Example 2)

[0342] Next, we will describe Example 2. 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".

[0343] In today's information society, consumers are exposed to vast amounts of information, making it crucial to efficiently provide them with information that matches their individual needs. However, conventional systems have a challenge in adequately providing personalized information based on consumer preferences and emotions. Furthermore, multilingual support is limited, resulting in insufficient service provision to global users. In addition, there is a need to effectively utilize consumer feedback to improve content quality.

[0344] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0345] In this invention, the server includes means for collecting consumer-related information, means for analyzing the consumer information and generating content based on the consumer's preferences, and means for recognizing the user's emotions and further personalizing the generated content based on those emotions. This makes it possible to provide personalized information based on the individual consumer's preferences and emotions.

[0346] "Consumer-related information" refers to data and feedback related to consumer behavior, preferences, and opinions.

[0347] "Analysis" refers to the process of analyzing collected data to identify consumer trends and patterns.

[0348] "Generating content" refers to creating new information such as text, images, and videos based on consumer information.

[0349] "Recognizing user emotions" refers to technology that identifies the user's emotional state at a given time based on their facial expressions, voice, and other factors.

[0350] "Personalization" refers to optimizing the information provided to individual consumers according to their preferences and emotions.

[0351] "Multilingual conversion" refers to the process of translating generated content into multiple different languages.

[0352] "Sending" refers to delivering generated content to users via communication methods such as the internet.

[0353] "Product information or usage examples related to specific items" refers to products and their applications that are characteristic of a particular region or culture.

[0354] "Gathering feedback" refers to the act of collecting feedback and opinions from consumers.

[0355] "Updating generation instructions" refers to improving the instructions and processes for generating content based on newly acquired data.

[0356] The following describes embodiments for carrying out the present invention. This system is designed to provide individually optimized information, taking into account consumer preferences and real-time emotional states.

[0357] First, the server collects information from the internet. This involves methods such as web scraping and APIs to gather data from social media posts, review sites, and search engines. At this stage, a vast amount of data on consumer behavior is collected.

[0358] Next, the collected data is analyzed on the server. Machine learning algorithms are used for data analysis to extract consumer preferences and behavioral patterns. Text mining and natural language processing techniques are used in this analysis. Based on the analysis results, a generative AI model is used to generate consumer-related content. For example, recipes using local specialties from a specific region are automatically created.

[0359] Furthermore, this system incorporates an emotion engine. The device can recognize the user's emotions in real time by analyzing their facial expressions and voice. This enables personalization based on the user's emotional state. For example, if a user is excited, it can provide products or information with a suitable refreshing effect.

[0360] The generated content is translated into multiple languages ​​and distributed to target users through online platforms. For example, information about local products is translated into English, Chinese, Spanish, and other languages ​​and sent to consumers who speak those languages.

[0361] Finally, users can provide ratings and feedback on the content, and this data is again aggregated on the server and used to create future content. This ensures that users are always provided with the latest and most relevant information.

[0362] A concrete example of a prompt message could be: "Please provide a recipe using very sweet tomatoes. Please consider the user's emotions in the process." This is how the system provides personalized information tailored to the user's preferences and emotions.

[0363] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0364] Step 1:

[0365] The server collects consumer information from the internet. This process uses social media APIs and web scraping techniques to collect posts containing specific keywords and hashtags. The input data consists of social media posts and word-of-mouth information, and the output is structured data. Specifically, the server periodically crawls the information sources and stores new data in the database.

[0366] Step 2:

[0367] The server analyzes the collected data. This process uses machine learning algorithms to extract consumer preferences and trends. The input is the data obtained in step 1, and the output is consumer preference patterns and trend information. Specifically, it performs text mining and clustering to identify products and categories that consumers prefer.

[0368] Step 3:

[0369] The server generates content using a generative AI model. At this stage, it uses the analysis results obtained in step 2 as input to create personalized content for specific consumers. The output is content such as recipes and product information. Specifically, it prompts the generative AI model with the message, "Generate a new cooking recipe using popular local products," and retrieves a new recipe.

[0370] Step 4:

[0371] The device recognizes the user's emotions in real time. An emotion engine uses data collected from the camera and microphone to determine the user's emotional state. Input is the user's facial expressions and voice data, and output is an emotion label such as "excited" or "calm." Specific operations include facial image analysis using facial recognition technology and tone analysis using voice analysis.

[0372] Step 5:

[0373] The server further personalizes the content based on the user's emotional data. It takes the emotional data into account and makes final adjustments to the content created in Step 3. The input is the emotional label and generated content, and the output is content adapted to the user's state. For example, a relaxed user might receive a suggestion for a refreshing local juice.

[0374] Step 6:

[0375] The server translates and transmits the completed content in multiple languages. At this stage, the generated content is converted into multiple languages ​​and delivered to users in the target country or region. The input is the content completed up to step 5, and the output is multilingual content. Specifically, a translation API is used to convert the content into English, Chinese, Spanish, etc., and distribute it to the online platform.

[0376] Step 7:

[0377] Users view the received content and provide ratings and feedback. This feedback is sent to the server via the device and used to improve future content creation. The input is the user's feedback, and the output is the rating data stored in the server's database. Specifically, users communicate their ease of use, satisfaction with the content, etc., to the server through a rating form.

[0378] (Application Example 2)

[0379] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0380] Conventional content delivery systems have the challenge of not adequately personalizing content based on individual user emotions and preferences, making it difficult to achieve comprehensive consumer satisfaction. Furthermore, when providing multilingual support, flexible content adjustments based on user emotions are not implemented. There is a need for a system that can solve these problems and enable more effective information delivery.

[0381] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0382] In this invention, the server includes a structure for collecting consumption data, a structure for analyzing the consumption data and generating content based on the user's preferences, a structure for translating the generated content into multiple languages, a structure for recognizing the user's emotional state in real time, and a structure for further individualizing the content according to the emotional state. This enables a high level of personalization that responds to the user's emotions and preferences.

[0383] "Consumer data" refers to information about users' purchase history, browsing history, and behavioral patterns.

[0384] "User preferences" refer to the products, services, or areas of interest that a particular user enjoys.

[0385] A "content generation structure" is a system that generates relevant information and suggested content based on users' consumption data and preferences.

[0386] A "multilingual translation structure" is a system that translates generated content into different languages ​​and delivers it to diverse users in an appropriate format.

[0387] "User's emotional state" refers to information that indicates the user's current feelings and emotional state, such as joy or dissatisfaction.

[0388] A "real-time recognition structure" is a system that analyzes data in accordance with the current situation and obtains results immediately.

[0389] A "personalized structure" is a mechanism for adjusting and optimizing content and services to suit specific users.

[0390] One embodiment of this invention is a system for realizing an e-commerce site application incorporating an emotion engine. The details are described below.

[0391] The server first collects user consumption data, including browsing and purchase history. Next, it analyzes the collected data to generate personalized content based on the user's preferences. This process utilizes machine learning algorithms to automatically create content that is more interesting and engaging to the user.

[0392] The device collects data through its camera and microphone to recognize the user's emotional state in real time, and analyzes it using machine learning models such as TensorFlow. This allows it to recognize the emotions the user is feeling while browsing products, such as "enjoying" or "confusing."

[0393] The server further customizes content for each user based on the recognized emotion data. For example, if it recognizes that a user is happy, it adjusts the content to proactively suggest related products and discount information. This process enables more effective product recommendations that are tailored to the user's emotions and preferences.

[0394] If a user's facial expression indicates confusion while searching for a new gadget, the server can provide relevant review articles or FAQ pages to alleviate the user's confusion. An example of a prompt to input into the generating AI model would be, "Generate the best product suggestions based on the following emotion data: Enjoying, Interested."

[0395] This system makes it possible to personalize the experience based on the user's latest emotions and preferences, thereby improving consumer satisfaction.

[0396] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0397] Step 1:

[0398] The server collects user consumption data via the internet. Input data includes browsing history and purchase history. The server retrieves this data and stores it in a database.

[0399] Step 2:

[0400] The server analyzes stored consumption data using machine learning algorithms. The input is consumption data, and the output is features related to the user's preferences and interests. Through this analysis, the server identifies products and content that the user is most likely to be interested in.

[0401] Step 3:

[0402] The device collects the user's facial expressions and voice through its camera and microphone, and analyzes their emotional state in real time. Video and audio are provided as input data, which is processed by machine learning models such as TensorFlow, and the output generates emotion labels such as "enjoying" or "confused."

[0403] Step 4:

[0404] The server integrates user emotional states and preference data to generate personalized content. Inputs are emotional labels and preference features, while outputs are personalized product suggestions and information. The server combines this data to create optimal content that captures the user's interest.

[0405] Step 5:

[0406] The server translates the generated personalized content into the required target language through a multilingual translation engine. The input is the generated content, and the output is the translated content. This allows the server to deliver content appropriately to a global audience.

[0407] Step 6:

[0408] Users view personalized content provided on their devices, select products, and provide feedback. Input consists of user selections and feedback, while output is information for improving future content. The device sends this information to a server for use in improving future content.

[0409] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0410] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0411] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0412] [Third Embodiment]

[0413] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0414] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0415] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0416] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0417] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0418] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0419] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0420] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0421] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0422] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0423] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0424] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0425] This invention relates to providing a system that maximizes the appeal of local specialty products and enables effective marketing to consumers. This system is configured to collect and analyze consumer-related information and generate content tailored to consumer preferences based on the results.

[0426] First, the server automatically collects consumer-related information from various data sources on the internet. This includes social media, online reviews, and search queries. Next, the collected data is analyzed using machine learning algorithms installed on the server. This analysis process provides insights into trends and consumer preferences.

[0427] After analysis, the server automatically generates recipes and usage examples related to local specialties based on consumer preferences and trends. For example, it can create a recipe for "apple and cinnamon tart" by incorporating cooking methods preferred by consumers for apples, a specialty product of a particular region. The content generated in this way is designed to attract consumer interest.

[0428] The generated content is translated into multiple languages. The server uses translation algorithms to convert the content into major foreign languages ​​such as English and Chinese. This makes it possible to widely communicate the appeal of local products to consumers both domestically and internationally.

[0429] The translated content is distributed from the server to social media and online platforms. Distribution is optimized according to the attributes of the target consumer. For example, Instagram is used for younger demographics, while LinkedIn is used for professionals. This ensures effective communication to the target market.

[0430] Furthermore, this system has the ability to collect consumer feedback on the content actually provided. Users can react to the delivered content, providing ratings and comments. This feedback is collected on the server via the device and used to improve the generation algorithm for future content.

[0431] As described above, the present invention provides a consistent marketing system for effectively promoting local specialty products.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The server collects consumer-related information from various data sources on the internet. This includes social media posts, online reviews, and search engine query data, which are automatically collected using APIs and crawling technologies.

[0435] Step 2:

[0436] The server analyzes the collected data using machine learning algorithms. At this stage, natural language processing techniques are used to extract consumer sentiment and preference patterns contained in the data and identify trends.

[0437] Step 3:

[0438] The server generates content that reflects consumer preferences related to local specialties based on the analysis results. For example, if the collected data is about apples, it will automatically create content that consumers will find interesting, such as a "new baked apple recipe."

[0439] Step 4:

[0440] The server translates the generated content into multiple languages. It utilizes machine translation technology to create language variations suitable for major markets, catering to a global consumer base.

[0441] Step 5:

[0442] The server distributes the translated content to selected social media and online platforms. It chooses the most effective platform (e.g., Facebook or Instagram) based on the attributes of the target audience and publishes the content according to a pre-set schedule.

[0443] Step 6:

[0444] Users react to delivered content by viewing, empathizing with, sharing, and rating it. These interactions serve as important feedback for measuring content acceptance.

[0445] Step 7:

[0446] The device collects user feedback and reaction data and sends it to the server. This feedback is used as data to more accurately reflect consumer needs when creating future content.

[0447] Step 8:

[0448] The server updates its generation algorithm based on feedback data to improve the quality and relevance of the content. This updating process is iterative, and the system is constantly adjusted to adapt to changing consumer preferences.

[0449] (Example 1)

[0450] Next, we will describe Example 1. 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."

[0451] There is a need to accurately understand the diverse preferences of consumers, generate engaging content based on those preferences, and efficiently distribute information to international consumers. Furthermore, it is necessary to collect consumer feedback and adaptively improve the content generation system to enhance the accuracy and effectiveness of the content.

[0452] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0453] In this invention, the server includes means for automatically acquiring consumer-related information from multiple information sources, means for analyzing the consumer-related information using a machine learning algorithm to generate content based on consumer preferences, and means for translating the generated content into multiple languages ​​using natural language processing technology. This enables the generation of content that matches consumer preferences and improves the efficiency of international information transmission.

[0454] "Consumer-related information" refers to all data concerning consumers, including their preferences, interests, behavioral patterns, and purchase history.

[0455] A "machine learning algorithm" refers to an automated computational method used to analyze collected data and identify patterns and trends.

[0456] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate human language, and includes text translation, sentiment analysis, and topic modeling.

[0457] "Translating into multiple languages" refers to the process of converting content written in one language into several different languages.

[0458] "Feedback mechanisms" refer to the methods and processes for collecting consumer reactions, evaluations, and opinions on generated content, and for analyzing and incorporating them into system improvements.

[0459] A "generative algorithm" refers to a structured procedure and method for automatically creating new content based on data analysis results.

[0460] This system aims to effectively communicate the appeal of local specialty products to consumers. The system's implementation primarily involves server-side processing, with user interaction occurring via terminals. The details of its structure are described below.

[0461] First, the server automatically collects consumer-related information from various sources on the internet. This process utilizes web crawlers and APIs to obtain data from social media, online reviews, and web search queries. Specific software used includes Python's Beautiful Soup and Scrapy.

[0462] Next, the server processes the collected data. Using machine learning libraries such as Scikit-learn and TensorFlow, it performs data cleansing and topic modeling, and analyzes consumer preferences and trend data. This analysis helps to understand the characteristics of target consumers and obtain base information for generating content that matches their needs.

[0463] Using a generative AI model, the server generates specific content. For example, based on analysis results, it can devise new recipes using local specialties that consumers prefer. An example of a prompt is, "Generate a new dessert recipe using apples." Based on this prompt, the generative AI creates a specific recipe that meets consumer needs.

[0464] Subsequently, the generated content is translated into multiple languages. The server uses the Google Translate API and other tools to translate the content into English, Spanish, French, and other languages. This translation process makes it possible to convey the appeal of local products to a wide range of consumers both domestically and internationally.

[0465] Furthermore, translated content is distributed through social media and online platforms. The server appropriately sets the distribution destination according to the attributes of the target consumers, selecting the most suitable platform based on those attributes, such as using Instagram or LinkedIn. This distribution allows for effective reach to the target market.

[0466] Finally, users can provide feedback on the content delivered through their devices. Ratings and comments are collected on the server via the devices. The collected feedback data is used to improve the generation algorithm for future content, enabling the creation of more sophisticated content. In this way, the system effectively promotes local specialty products.

[0467] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0468] Step 1:

[0469] The server collects consumer-related information from social media, online reviews, and web search queries on the internet. This step utilizes tools such as Beautiful Soup and Scrapy to retrieve data via crawlers and APIs. Inputs are web pages and databases, and output is a set of collected raw data.

[0470] Step 2:

[0471] The server processes and analyzes the collected raw data. Specifically, it uses Python's Scikit-learn and TensorFlow to perform data cleansing, topic modeling, and sentiment analysis. The input is the raw data obtained in step 1, and the output is consumer preference patterns and trend information. This analysis allows for the identification of products and topics of particular interest.

[0472] Step 3:

[0473] The server generates content using a generative AI model based on the analysis results. At this stage, prompts are input to the generative AI to create specific recipes and usage examples. For example, a prompt such as "Generate a new dessert recipe using apples" is sent. The input is the analysis results from step 2 and a specific prompt, and the output is customized content tailored to the consumer.

[0474] Step 4:

[0475] The server translates the generated content into multiple languages. It uses the Google Translate API to convert the content into major foreign languages. The input is the generated content from step 3, and the output is the multilingualized content. This process enables the service to be tailored to consumers with diverse language backgrounds.

[0476] Step 5:

[0477] The server distributes the translated content to social media and online platforms. In this step, the appropriate platform, such as Instagram or LinkedIn, is selected based on consumer attributes. The input is the multilingual content from step 4, and the output is distribution to the target consumer group. This process enables effective marketing.

[0478] Step 6:

[0479] Users provide feedback on content delivered through their devices. User ratings and comments are sent to the server via the device and used to improve the algorithm for future deliveries. The input is user feedback, and the output is an indicator of the improved algorithm. Using this information, the server can further optimize the next content generation process.

[0480] (Application Example 1)

[0481] Next, we will explain Application Example 1. In the following explanation, 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."

[0482] Today's consumers have diverse preferences, making effective marketing of local specialty products complex. Furthermore, communicating the appeal of these products to consumers with different language and cultural backgrounds in international markets is challenging. Additionally, personalized product recommendations based on consumer purchase history are often inadequate. Therefore, innovative systems are needed to effectively promote the trade of local specialty products and attract consumer interest.

[0483] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0484] In this invention, the server includes means for collecting consumer-related information, means for analyzing the consumer-related information to generate content based on consumer preferences, and means for translating the generated content into multiple languages. This enables the effective communication of the characteristics and usage examples of local products in multiple languages, and allows for personalized product suggestions based on the consumer's purchase history.

[0485] "Consumer-related information" refers to various types of data related to consumer preferences and purchasing behavior.

[0486] "Analysis" is the process of extracting consumer trends and preferences based on collected data.

[0487] "Content" refers to information provided to consumers, such as information related to local specialty products, recipes, and usage examples.

[0488] "Multilingual" refers to a means of responding to diverse markets by translating specific information into one or more languages.

[0489] "Optimizing delivery routes" refers to the process of optimizing delivery routes and methods in order to efficiently deliver products to consumers.

[0490] "Promoting transactions" refers to the means of encouraging consumers to purchase local specialty products and thereby increasing sales.

[0491] "Recommendations based on purchase history" is a technology that recommends local specialty products based on past consumer purchase data.

[0492] "Feedback" refers to opinions and evaluations provided by consumers, and is used to improve the system.

[0493] This invention is a marketing system designed to effectively convey the appeal of local specialty products to consumers. The system collects consumer-related information from various data sources, analyzes that data, and generates content tailored to consumer preferences. Specifically, a server collects consumer-related information from social media, online reviews, and search queries on the internet, and analyzes trends using machine learning algorithms. Based on these results, the server generates recipes and usage instructions for local specialty products that match consumer preferences. The generated content is translated into multiple languages ​​and distributed on the most suitable platform according to the attributes of the target consumers.

[0494] In this invention, the server uses high-performance hardware and can utilize cloud services such as Google Cloud Platform and Amazon Web Services. Software tools such as TensorFlow and PyTorch are used for machine learning, and NLTK and spaCy are used for natural language processing. Furthermore, the Google Translate API and similar tools are utilized for multilingual translation.

[0495] For example, if a user is interested in the local specialty "matcha," the server can generate various matcha recipes, translate them, and distribute them to the mobile apps of social media and online shopping sites that the user frequently visits. User feedback is collected through the device and used to create future content.

[0496] An example of a prompt for a generative AI model is, "Based on user preferences, suggest new ways to use local products that they might be interested in."

[0497] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0498] Step 1:

[0499] The server automatically collects consumer-related information from social media, online reviews, and search queries on the internet. The input consists of various online data sources, and the output is raw data related to consumer preferences and trends. This step utilizes web crawling technology for data collection.

[0500] Step 2:

[0501] The server analyzes the collected consumer-related information using machine learning algorithms. The input is the raw consumer-related data obtained in step 1, and the output is the analysis results showing preferences and trends. This process uses TensorFlow and PyTorch to perform trend prediction and preference analysis.

[0502] Step 3:

[0503] The server generates content related to local specialties based on the analysis results. The input is the analysis results obtained in step 2, and the output is content such as recipes and usage examples for the local specialties. In this step, natural language generation technology is used to generate the content.

[0504] Step 4:

[0505] The server translates the generated content into multiple languages. The input is the content generated in step 3, and the output is the content translated into multiple languages. Translation is performed using a translation tool such as the Google Translate API.

[0506] Step 5:

[0507] The server delivers the translated content to the most suitable online platform for the target consumer. The input is the multilingual content obtained in step 4, and the output is the content delivered to each platform. This step involves integration with applications such as social media and e-commerce sites.

[0508] Step 6:

[0509] Users view the delivered content and send feedback from their devices to the server. Input consists of user ratings and comments, while output is feedback data stored on the server. This feedback is later analyzed and used to improve future content creation.

[0510] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0511] This invention combines a consumer-related content generation system with an emotion engine that recognizes user emotions to achieve more personalized information delivery. This system has a function to recognize the user's emotional state in real time during the process of generating content based on consumer preferences and to reflect this in the generated content.

[0512] First, the server automatically collects consumer-related information from the internet. Sources include social media posts, review sites, and search engine queries. Next, this collected data is analyzed within the server using machine learning algorithms to reveal user preferences and trends.

[0513] Subsequently, based on consumer preferences and analysis results, recipes and usage examples related to local specialties are generated. For example, regarding locally produced tomatoes, if a user prefers "soup recipes using particularly sweet varieties," content can be automatically generated.

[0514] Next, by combining this system with an emotion engine, the device analyzes the user's emotions in real time. The emotion engine, for example, analyzes facial expressions and voice through the camera or voice input while the user is viewing content, and recognizes emotional states such as "excited" or "calm."

[0515] The server further personalizes content based on recognized user emotion data. For example, if the user is excited, it can suggest additional recipes for refreshing local specialty juices.

[0516] The generated content is made multilingual and distributed to social media and online platforms to attract attention. Specifically, content related to local specialties is translated into English, Chinese, and Spanish, and the platform is selected to reach the target audience.

[0517] Users can rate and provide feedback on the delivered content, and this data is collected on the server via their devices. This feedback is used to create future content, allowing us to constantly provide content optimized to meet the latest consumer needs and sentiments.

[0518] This invention is designed to enable the provision of personalized content that accurately captures the emotional state of users, thereby attracting greater consumer interest.

[0519] The following describes the processing flow.

[0520] Step 1:

[0521] The server collects consumer-related information through users' internet activities. Specifically, it gathers social media posts, comments, review site ratings, and search history using APIs and web scraping.

[0522] Step 2:

[0523] The server uses machine learning algorithms to analyze the collected data. This analysis extracts consumer preferences and trends, and evaluates consumer interest in specific products and keywords.

[0524] Step 3:

[0525] The server generates content related to local specialties based on the analysis results. At this stage, it automatically creates recipes and usage examples for the specialties according to consumer preferences. For example, it might devise a "refreshing dessert recipe" using fruits from the local area.

[0526] Step 4:

[0527] The device transmits emotional data to the emotion engine using the user's camera and microphone. The emotion engine identifies the user's emotional state in real time through facial expression analysis and voice tone analysis.

[0528] Step 5:

[0529] The server adjusts the generated content based on the user's emotional state, as determined by the emotion engine. For example, if it determines that the user is stressed, it prioritizes content that introduces products or methods for use that have a relaxing effect.

[0530] Step 6:

[0531] The server translates personalized content into multiple languages ​​and delivers it through the most suitable platform for the target market. Specifically, it publishes translated content on Facebook, Instagram, Twitter, etc., reaching consumers in specific regions and language areas.

[0532] Step 7:

[0533] Users view the delivered content and provide feedback on it. This feedback is collected through form submissions, comments, and rating systems.

[0534] Step 8:

[0535] The device organizes user feedback and sends it to the server. The server analyzes the feedback data and uses it to improve future content generation and sentiment analysis algorithms.

[0536] (Example 2)

[0537] Next, we will describe Example 2. 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."

[0538] In today's information society, consumers are exposed to vast amounts of information, making it crucial to efficiently provide them with information that matches their individual needs. However, conventional systems have a challenge in adequately providing personalized information based on consumer preferences and emotions. Furthermore, multilingual support is limited, resulting in insufficient service provision to global users. In addition, there is a need to effectively utilize consumer feedback to improve content quality.

[0539] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0540] In this invention, the server includes means for collecting consumer-related information, means for analyzing the consumer information and generating content based on the consumer's preferences, and means for recognizing the user's emotions and further personalizing the generated content based on those emotions. This makes it possible to provide personalized information based on the individual consumer's preferences and emotions.

[0541] "Consumer-related information" refers to data and feedback related to consumer behavior, preferences, and opinions.

[0542] "Analysis" refers to the process of analyzing collected data to identify consumer trends and patterns.

[0543] "Generating content" refers to creating new information such as text, images, and videos based on consumer information.

[0544] "Recognizing user emotions" refers to technology that identifies the user's emotional state at a given time based on their facial expressions, voice, and other factors.

[0545] "Personalization" refers to optimizing the information provided to individual consumers according to their preferences and emotions.

[0546] "Multilingual conversion" refers to the process of translating generated content into multiple different languages.

[0547] "Sending" refers to delivering generated content to users via communication methods such as the internet.

[0548] "Product information or usage examples related to specific items" refers to products and their applications that are characteristic of a particular region or culture.

[0549] "Gathering feedback" refers to the act of collecting feedback and opinions from consumers.

[0550] "Updating generation instructions" refers to improving the instructions and processes for generating content based on newly acquired data.

[0551] The following describes embodiments for carrying out the present invention. This system is designed to provide individually optimized information, taking into account consumer preferences and real-time emotional states.

[0552] First, the server collects information from the internet. This involves methods such as web scraping and APIs to gather data from social media posts, review sites, and search engines. At this stage, a vast amount of data on consumer behavior is collected.

[0553] Next, the collected data is analyzed on the server. Machine learning algorithms are used for data analysis to extract consumer preferences and behavioral patterns. Text mining and natural language processing techniques are used in this analysis. Based on the analysis results, a generative AI model is used to generate consumer-related content. For example, recipes using local specialties from a specific region are automatically created.

[0554] Furthermore, this system incorporates an emotion engine. The device can recognize the user's emotions in real time by analyzing their facial expressions and voice. This enables personalization based on the user's emotional state. For example, if a user is excited, it can provide products or information with a suitable refreshing effect.

[0555] The generated content is translated into multiple languages ​​and distributed to target users through online platforms. For example, information about local products is translated into English, Chinese, Spanish, and other languages ​​and sent to consumers who speak those languages.

[0556] Finally, users can provide ratings and feedback on the content, and this data is again aggregated on the server and used to create future content. This ensures that users are always provided with the latest and most relevant information.

[0557] A concrete example of a prompt message could be: "Please provide a recipe using very sweet tomatoes. Please consider the user's emotions in the process." This is how the system provides personalized information tailored to the user's preferences and emotions.

[0558] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0559] Step 1:

[0560] The server collects consumer information from the internet. This process uses social media APIs and web scraping techniques to collect posts containing specific keywords and hashtags. The input data consists of social media posts and word-of-mouth information, and the output is structured data. Specifically, the server periodically crawls the information sources and stores new data in the database.

[0561] Step 2:

[0562] The server analyzes the collected data. This process uses machine learning algorithms to extract consumer preferences and trends. The input is the data obtained in step 1, and the output is consumer preference patterns and trend information. Specifically, it performs text mining and clustering to identify products and categories that consumers prefer.

[0563] Step 3:

[0564] The server generates content using a generative AI model. At this stage, it uses the analysis results obtained in step 2 as input to create personalized content for specific consumers. The output is content such as recipes and product information. Specifically, it prompts the generative AI model with the message, "Generate a new cooking recipe using popular local products," and retrieves a new recipe.

[0565] Step 4:

[0566] The device recognizes the user's emotions in real time. An emotion engine uses data collected from the camera and microphone to determine the user's emotional state. Input is the user's facial expressions and voice data, and output is an emotion label such as "excited" or "calm." Specific operations include facial image analysis using facial recognition technology and tone analysis using voice analysis.

[0567] Step 5:

[0568] The server further personalizes the content based on the user's emotional data. It takes the emotional data into account and makes final adjustments to the content created in Step 3. The input is the emotional label and generated content, and the output is content adapted to the user's state. For example, a relaxed user might receive a suggestion for a refreshing local juice.

[0569] Step 6:

[0570] The server translates and transmits the completed content in multiple languages. At this stage, the generated content is converted into multiple languages ​​and delivered to users in the target country or region. The input is the content completed up to step 5, and the output is multilingual content. Specifically, a translation API is used to convert the content into English, Chinese, Spanish, etc., and distribute it to the online platform.

[0571] Step 7:

[0572] Users view the received content and provide ratings and feedback. This feedback is sent to the server via the device and used to improve future content creation. The input is the user's feedback, and the output is the rating data stored in the server's database. Specifically, users communicate their ease of use, satisfaction with the content, etc., to the server through a rating form.

[0573] (Application Example 2)

[0574] Next, we will explain application example 2. In the following explanation, 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."

[0575] Conventional content delivery systems have the challenge of not adequately personalizing content based on individual user emotions and preferences, making it difficult to achieve comprehensive consumer satisfaction. Furthermore, when providing multilingual support, flexible content adjustments based on user emotions are not implemented. There is a need for a system that can solve these problems and enable more effective information delivery.

[0576] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0577] In this invention, the server includes a structure for collecting consumption data, a structure for analyzing the consumption data and generating content based on the user's preferences, a structure for translating the generated content into multiple languages, a structure for recognizing the user's emotional state in real time, and a structure for further individualizing the content according to the emotional state. This enables a high level of personalization that responds to the user's emotions and preferences.

[0578] "Consumer data" refers to information about users' purchase history, browsing history, and behavioral patterns.

[0579] "User preferences" refer to the products, services, or areas of interest that a particular user enjoys.

[0580] A "content generation structure" is a system that generates relevant information and suggested content based on users' consumption data and preferences.

[0581] A "multilingual translation structure" is a system that translates generated content into different languages ​​and delivers it to diverse users in an appropriate format.

[0582] "User's emotional state" refers to information that indicates the user's current feelings and emotional state, such as joy or dissatisfaction.

[0583] A "real-time recognition structure" is a system that analyzes data in accordance with the current situation and obtains results immediately.

[0584] A "personalized structure" is a mechanism for adjusting and optimizing content and services to suit specific users.

[0585] One embodiment of this invention is a system for realizing an e-commerce site application incorporating an emotion engine. The details are described below.

[0586] The server first collects user consumption data, including browsing and purchase history. Next, it analyzes the collected data to generate personalized content based on the user's preferences. This process utilizes machine learning algorithms to automatically create content that is more interesting and engaging to the user.

[0587] The device collects data through its camera and microphone to recognize the user's emotional state in real time, and analyzes it using machine learning models such as TensorFlow. This allows it to recognize the emotions the user is feeling while browsing products, such as "enjoying" or "confusing."

[0588] The server further customizes content for each user based on the recognized emotion data. For example, if it recognizes that a user is happy, it adjusts the content to proactively suggest related products and discount information. This process enables more effective product recommendations that are tailored to the user's emotions and preferences.

[0589] If a user's facial expression indicates confusion while searching for a new gadget, the server can provide relevant review articles or FAQ pages to alleviate the user's confusion. An example of a prompt to input into the generating AI model would be, "Generate the best product suggestions based on the following emotion data: Enjoying, Interested."

[0590] This system makes it possible to personalize the experience based on the user's latest emotions and preferences, thereby improving consumer satisfaction.

[0591] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0592] Step 1:

[0593] The server collects user consumption data via the internet. Input data includes browsing history and purchase history. The server retrieves this data and stores it in a database.

[0594] Step 2:

[0595] The server analyzes stored consumption data using machine learning algorithms. The input is consumption data, and the output is features related to the user's preferences and interests. Through this analysis, the server identifies products and content that the user is most likely to be interested in.

[0596] Step 3:

[0597] The device collects the user's facial expressions and voice through its camera and microphone, and analyzes their emotional state in real time. Video and audio are provided as input data, which is processed by machine learning models such as TensorFlow, and the output generates emotional labels such as "enjoying" or "confused."

[0598] Step 4:

[0599] The server integrates user emotional states and preference data to generate personalized content. Inputs are emotional labels and preference features, while outputs are personalized product suggestions and information. The server combines this data to create optimal content that captures the user's interest.

[0600] Step 5:

[0601] The server translates the generated personalized content into the required target language through a multilingual translation engine. The input is the generated content, and the output is the translated content. This allows the server to deliver content appropriately to a global audience.

[0602] Step 6:

[0603] Users view personalized content provided on their devices, select products, and provide feedback. Input consists of user selections and feedback, while output is information for improving future content. The device sends this information to a server for use in improving future content.

[0604] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0605] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0606] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0607] [Fourth Embodiment]

[0608] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0609] As shown in Figure 7, the 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.

[0610] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0611] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0612] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0613] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0614] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0615] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0616] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0617] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0618] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0619] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0620] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0621] This invention relates to providing a system that maximizes the appeal of local specialty products and enables effective marketing to consumers. This system is configured to collect and analyze consumer-related information and generate content tailored to consumer preferences based on the results.

[0622] First, the server automatically collects consumer-related information from various data sources on the internet. This includes social media, online reviews, and search queries. Next, the collected data is analyzed using machine learning algorithms installed on the server. This analysis process provides insights into trends and consumer preferences.

[0623] After analysis, the server automatically generates recipes and usage examples related to local specialties based on consumer preferences and trends. For example, it can create a recipe for "apple and cinnamon tart" by incorporating cooking methods preferred by consumers for apples, a specialty product of a particular region. The content generated in this way is designed to attract consumer interest.

[0624] The generated content is translated into multiple languages. The server uses translation algorithms to convert the content into major foreign languages ​​such as English and Chinese. This makes it possible to widely communicate the appeal of local products to consumers both domestically and internationally.

[0625] The translated content is distributed from the server to social media and online platforms. Distribution is optimized according to the attributes of the target consumer. For example, Instagram is used for younger demographics, while LinkedIn is used for professionals. This ensures effective communication to the target market.

[0626] Furthermore, this system has the ability to collect consumer feedback on the content actually provided. Users can react to the delivered content, providing ratings and comments. This feedback is collected on the server via the device and used to improve the generation algorithm for future content.

[0627] As described above, the present invention provides a consistent marketing system for effectively promoting local specialty products.

[0628] The following describes the processing flow.

[0629] Step 1:

[0630] The server collects consumer-related information from various data sources on the internet. This includes social media posts, online reviews, and search engine query data, which are automatically collected using APIs and crawling technologies.

[0631] Step 2:

[0632] The server analyzes the collected data using machine learning algorithms. At this stage, natural language processing techniques are used to extract consumer sentiment and preference patterns contained in the data and identify trends.

[0633] Step 3:

[0634] The server generates content that reflects consumer preferences related to local specialties based on the analysis results. For example, if the collected data is about apples, it will automatically create content that consumers will find interesting, such as a "new baked apple recipe."

[0635] Step 4:

[0636] The server translates the generated content into multiple languages. It utilizes machine translation technology to create language variations suitable for major markets, catering to a global consumer base.

[0637] Step 5:

[0638] The server distributes the translated content to selected social media and online platforms. It chooses the most effective platform (e.g., Facebook or Instagram) based on the attributes of the target audience and publishes the content according to a pre-set schedule.

[0639] Step 6:

[0640] Users react to delivered content by viewing, empathizing with, sharing, and rating it. These interactions serve as important feedback for measuring content acceptance.

[0641] Step 7:

[0642] The device collects user feedback and reaction data and sends it to the server. This feedback is used as data to more accurately reflect consumer needs when creating future content.

[0643] Step 8:

[0644] The server updates its generation algorithm based on feedback data to improve the quality and relevance of the content. This updating process is iterative, and the system is constantly adjusted to adapt to changing consumer preferences.

[0645] (Example 1)

[0646] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0647] There is a need to accurately understand the diverse preferences of consumers, generate engaging content based on those preferences, and efficiently distribute information to international consumers. Furthermore, it is necessary to collect consumer feedback and adaptively improve the content generation system to enhance the accuracy and effectiveness of the content.

[0648] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0649] In this invention, the server includes means for automatically acquiring consumer-related information from multiple information sources, means for analyzing the consumer-related information using a machine learning algorithm to generate content based on consumer preferences, and means for translating the generated content into multiple languages ​​using natural language processing technology. This enables the generation of content that matches consumer preferences and improves the efficiency of international information transmission.

[0650] "Consumer-related information" refers to all data concerning consumers, including their preferences, interests, behavioral patterns, and purchase history.

[0651] A "machine learning algorithm" refers to an automated computational method used to analyze collected data and identify patterns and trends.

[0652] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate human language, and includes text translation, sentiment analysis, and topic modeling.

[0653] "Translating into multiple languages" refers to the process of converting content written in one language into several different languages.

[0654] "Feedback mechanisms" refer to the methods and processes for collecting consumer reactions, evaluations, and opinions on generated content, and for analyzing and incorporating them into system improvements.

[0655] A "generative algorithm" refers to a structured procedure and method for automatically creating new content based on data analysis results.

[0656] This system aims to effectively communicate the appeal of local specialty products to consumers. The system's implementation primarily involves server-side processing, with user interaction occurring via terminals. The details of its structure are described below.

[0657] First, the server automatically collects consumer-related information from various sources on the internet. This process utilizes web crawlers and APIs to obtain data from social media, online reviews, and web search queries. Specific software used includes Python's Beautiful Soup and Scrapy.

[0658] Next, the server processes the collected data. Using machine learning libraries such as Scikit-learn and TensorFlow, it performs data cleansing and topic modeling, and analyzes consumer preferences and trend data. This analysis helps to understand the characteristics of target consumers and obtain base information for generating content that matches their needs.

[0659] Using a generative AI model, the server generates specific content. For example, based on analysis results, it can devise new recipes using local specialties that consumers prefer. An example of a prompt is, "Generate a new dessert recipe using apples." Based on this prompt, the generative AI creates a specific recipe that meets consumer needs.

[0660] Subsequently, the generated content is translated into multiple languages. The server uses the Google Translate API and other tools to translate the content into English, Spanish, French, and other languages. This translation process makes it possible to convey the appeal of local products to a wide range of consumers both domestically and internationally.

[0661] Furthermore, translated content is distributed through social media and online platforms. The server appropriately sets the distribution destination according to the attributes of the target consumers, selecting the most suitable platform based on those attributes, such as using Instagram or LinkedIn. This distribution allows for effective reach to the target market.

[0662] Finally, users can provide feedback on the content delivered through their devices. Ratings and comments are collected on the server via the devices. The collected feedback data is used to improve the generation algorithm for future content, enabling the creation of more sophisticated content. In this way, the system effectively promotes local specialty products.

[0663] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0664] Step 1:

[0665] The server collects consumer-related information from social media, online reviews, and web search queries on the internet. This step utilizes tools such as Beautiful Soup and Scrapy to retrieve data via crawlers and APIs. Inputs are web pages and databases, and output is a set of collected raw data.

[0666] Step 2:

[0667] The server processes and analyzes the collected raw data. Specifically, it uses Python's Scikit-learn and TensorFlow to perform data cleansing, topic modeling, and sentiment analysis. The input is the raw data obtained in step 1, and the output is consumer preference patterns and trend information. This analysis allows for the identification of products and topics of particular interest.

[0668] Step 3:

[0669] The server generates content using a generative AI model based on the analysis results. At this stage, prompts are input to the generative AI to create specific recipes and usage examples. For example, a prompt such as "Generate a new dessert recipe using apples" is sent. The input is the analysis results from step 2 and a specific prompt, and the output is customized content tailored to the consumer.

[0670] Step 4:

[0671] The server translates the generated content into multiple languages. It uses the Google Translate API to convert the content into major foreign languages. The input is the generated content from step 3, and the output is the multilingualized content. This process enables the service to be tailored to consumers with diverse language backgrounds.

[0672] Step 5:

[0673] The server distributes the translated content to social media and online platforms. In this step, the appropriate platform, such as Instagram or LinkedIn, is selected based on consumer attributes. The input is the multilingual content from step 4, and the output is distribution to the target consumer group. This process enables effective marketing.

[0674] Step 6:

[0675] Users provide feedback on content delivered through their devices. User ratings and comments are sent to the server via the device and used to improve the algorithm for future deliveries. The input is user feedback, and the output is an indicator of the improved algorithm. Using this information, the server can further optimize the next content generation process.

[0676] (Application Example 1)

[0677] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0678] Today's consumers have diverse preferences, making effective marketing of local specialty products complex. Furthermore, communicating the appeal of these products to consumers with different language and cultural backgrounds in international markets is challenging. Additionally, personalized product recommendations based on consumer purchase history are often inadequate. Therefore, innovative systems are needed to effectively promote the trade of local specialty products and attract consumer interest.

[0679] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0680] In this invention, the server includes means for collecting consumer-related information, means for analyzing the consumer-related information to generate content based on consumer preferences, and means for translating the generated content into multiple languages. This enables the effective communication of the characteristics and usage examples of local products in multiple languages, and allows for personalized product suggestions based on the consumer's purchase history.

[0681] "Consumer-related information" refers to various types of data related to consumer preferences and purchasing behavior.

[0682] "Analysis" is the process of extracting consumer trends and preferences based on collected data.

[0683] "Content" refers to information provided to consumers, such as information related to local specialty products, recipes, and usage examples.

[0684] "Multilingual" refers to a means of responding to diverse markets by translating specific information into one or more languages.

[0685] "Optimizing delivery routes" refers to the process of optimizing delivery routes and methods in order to efficiently deliver products to consumers.

[0686] "Promoting transactions" refers to the means of encouraging consumers to purchase local specialty products and thereby increasing sales.

[0687] "Recommendations based on purchase history" is a technology that recommends local specialty products based on past consumer purchase data.

[0688] "Feedback" refers to opinions and evaluations provided by consumers, and is used to improve the system.

[0689] This invention is a marketing system designed to effectively convey the appeal of local specialty products to consumers. The system collects consumer-related information from various data sources, analyzes that data, and generates content tailored to consumer preferences. Specifically, a server collects consumer-related information from social media, online reviews, and search queries on the internet, and analyzes trends using machine learning algorithms. Based on these results, the server generates recipes and usage instructions for local specialty products that match consumer preferences. The generated content is translated into multiple languages ​​and distributed on the most suitable platform according to the attributes of the target consumers.

[0690] In this invention, the server uses high-performance hardware and can utilize cloud services such as Google Cloud Platform and Amazon Web Services. Software tools such as TensorFlow and PyTorch are used for machine learning, and NLTK and spaCy are used for natural language processing. Furthermore, the Google Translate API and similar tools are utilized for multilingual translation.

[0691] For example, if a user is interested in the local specialty "matcha," the server can generate various matcha recipes, translate them, and distribute them to the mobile apps of social media and online shopping sites that the user frequently visits. User feedback is collected through the device and used to create future content.

[0692] An example of a prompt for a generative AI model is, "Based on user preferences, suggest new ways to use local products that they might be interested in."

[0693] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0694] Step 1:

[0695] The server automatically collects consumer-related information from social media, online reviews, and search queries on the internet. The input consists of various online data sources, and the output is raw data related to consumer preferences and trends. This step utilizes web crawling technology for data collection.

[0696] Step 2:

[0697] The server analyzes the collected consumer-related information using machine learning algorithms. The input is the raw consumer-related data obtained in step 1, and the output is the analysis results showing preferences and trends. This process uses TensorFlow and PyTorch to perform trend prediction and preference analysis.

[0698] Step 3:

[0699] The server generates content related to local specialties based on the analysis results. The input is the analysis results obtained in step 2, and the output is content such as recipes and usage examples for the local specialties. In this step, natural language generation technology is used to generate the content.

[0700] Step 4:

[0701] The server translates the generated content into multiple languages. The input is the content generated in step 3, and the output is the content translated into multiple languages. Translation is performed using a translation tool such as the Google Translate API.

[0702] Step 5:

[0703] The server delivers the translated content to the most suitable online platform for the target consumer. The input is the multilingual content obtained in step 4, and the output is the content delivered to each platform. This step involves integration with applications such as social media and e-commerce sites.

[0704] Step 6:

[0705] Users view the delivered content and send feedback from their devices to the server. Input consists of user ratings and comments, while output is feedback data stored on the server. This feedback is later analyzed and used to improve future content creation.

[0706] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0707] This invention combines a consumer-related content generation system with an emotion engine that recognizes user emotions to achieve more personalized information delivery. This system has a function to recognize the user's emotional state in real time during the process of generating content based on consumer preferences and to reflect this in the generated content.

[0708] First, the server automatically collects consumer-related information from the internet. Sources include social media posts, review sites, and search engine queries. Next, this collected data is analyzed within the server using machine learning algorithms to reveal user preferences and trends.

[0709] Subsequently, based on consumer preferences and analysis results, recipes and usage examples related to local specialties are generated. For example, regarding locally produced tomatoes, if a user prefers "soup recipes using particularly sweet varieties," content can be automatically generated.

[0710] Next, by combining this system with an emotion engine, the device analyzes the user's emotions in real time. The emotion engine, for example, analyzes facial expressions and voice through the camera or voice input while the user is viewing content, and recognizes emotional states such as "excited" or "calm."

[0711] The server further personalizes content based on recognized user emotion data. For example, if the user is excited, it can suggest additional recipes for refreshing local specialty juices.

[0712] The generated content is made multilingual and distributed to social media and online platforms to attract attention. Specifically, content related to local specialties is translated into English, Chinese, and Spanish, and the platform is selected to reach the target audience.

[0713] Users can rate and provide feedback on the delivered content, and this data is collected on the server via their devices. This feedback is used to create future content, allowing us to constantly provide content optimized to meet the latest consumer needs and sentiments.

[0714] This invention is designed to enable the provision of personalized content that accurately captures the emotional state of users, thereby attracting greater consumer interest.

[0715] The following describes the processing flow.

[0716] Step 1:

[0717] The server collects consumer-related information through users' internet activities. Specifically, it gathers social media posts, comments, review site ratings, and search history using APIs and web scraping.

[0718] Step 2:

[0719] The server uses machine learning algorithms to analyze the collected data. This analysis extracts consumer preferences and trends, and evaluates consumer interest in specific products and keywords.

[0720] Step 3:

[0721] The server generates content related to local specialties based on the analysis results. At this stage, it automatically creates recipes and usage examples for the specialties according to consumer preferences. For example, it might devise a "refreshing dessert recipe" using fruits from the local area.

[0722] Step 4:

[0723] The device transmits emotional data to the emotion engine using the user's camera and microphone. The emotion engine identifies the user's emotional state in real time through facial expression analysis and voice tone analysis.

[0724] Step 5:

[0725] The server adjusts the generated content based on the user's emotional state, as determined by the emotion engine. For example, if it determines that the user is stressed, it prioritizes content that introduces products or methods for use that have a relaxing effect.

[0726] Step 6:

[0727] The server translates personalized content into multiple languages ​​and delivers it through the most suitable platform for the target market. Specifically, it publishes translated content on Facebook, Instagram, Twitter, etc., reaching consumers in specific regions and language areas.

[0728] Step 7:

[0729] Users view the delivered content and provide feedback on it. This feedback is collected through form submissions, comments, and rating systems.

[0730] Step 8:

[0731] The device organizes user feedback and sends it to the server. The server analyzes the feedback data and uses it to improve future content generation and sentiment analysis algorithms.

[0732] (Example 2)

[0733] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0734] In today's information society, consumers are exposed to vast amounts of information, making it crucial to efficiently provide them with information that matches their individual needs. However, conventional systems have a challenge in adequately providing personalized information based on consumer preferences and emotions. Furthermore, multilingual support is limited, resulting in insufficient service provision to global users. In addition, there is a need to effectively utilize consumer feedback to improve content quality.

[0735] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0736] In this invention, the server includes means for collecting consumer-related information, means for analyzing the consumer information and generating content based on the consumer's preferences, and means for recognizing the user's emotions and further personalizing the generated content based on those emotions. This makes it possible to provide personalized information based on the individual consumer's preferences and emotions.

[0737] "Consumer-related information" refers to data and feedback related to consumer behavior, preferences, and opinions.

[0738] "Analysis" refers to the process of analyzing collected data to identify consumer trends and patterns.

[0739] "Generating content" refers to creating new information such as text, images, and videos based on consumer information.

[0740] "Recognizing user emotions" refers to technology that identifies the user's emotional state at a given time based on their facial expressions, voice, and other factors.

[0741] "Personalization" refers to optimizing the information provided to individual consumers according to their preferences and emotions.

[0742] "Multilingual conversion" refers to the process of translating generated content into multiple different languages.

[0743] "Sending" refers to delivering generated content to users via communication methods such as the internet.

[0744] "Product information or usage examples related to specific items" refers to products and their applications that are characteristic of a particular region or culture.

[0745] "Gathering feedback" refers to the act of collecting feedback and opinions from consumers.

[0746] "Updating generation instructions" refers to improving the instructions and processes for generating content based on newly acquired data.

[0747] The following describes embodiments for carrying out the present invention. This system is designed to provide individually optimized information, taking into account consumer preferences and real-time emotional states.

[0748] First, the server collects information from the internet. This involves methods such as web scraping and APIs to gather data from social media posts, review sites, and search engines. At this stage, a vast amount of data on consumer behavior is collected.

[0749] Next, the collected data is analyzed on the server. Machine learning algorithms are used for data analysis to extract consumer preferences and behavioral patterns. Text mining and natural language processing techniques are used in this analysis. Based on the analysis results, a generative AI model is used to generate consumer-related content. For example, recipes using local specialties from a specific region are automatically created.

[0750] Furthermore, this system incorporates an emotion engine. The device can recognize the user's emotions in real time by analyzing their facial expressions and voice. This enables personalization based on the user's emotional state. For example, if a user is excited, it can provide products or information with a suitable refreshing effect.

[0751] The generated content is translated into multiple languages ​​and distributed to target users through online platforms. For example, information about local products is translated into English, Chinese, Spanish, and other languages ​​and sent to consumers who speak those languages.

[0752] Finally, users can provide ratings and feedback on the content, and this data is again aggregated on the server and used to create future content. This ensures that users are always provided with the latest and most relevant information.

[0753] A concrete example of a prompt message could be: "Please provide a recipe using very sweet tomatoes. Please consider the user's emotions in the process." This is how the system provides personalized information tailored to the user's preferences and emotions.

[0754] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0755] Step 1:

[0756] The server collects consumer information from the internet. This process uses social media APIs and web scraping techniques to collect posts containing specific keywords and hashtags. The input data consists of social media posts and word-of-mouth information, and the output is structured data. Specifically, the server periodically crawls the information sources and stores new data in the database.

[0757] Step 2:

[0758] The server analyzes the collected data. This process uses machine learning algorithms to extract consumer preferences and trends. The input is the data obtained in step 1, and the output is consumer preference patterns and trend information. Specifically, it performs text mining and clustering to identify products and categories that consumers prefer.

[0759] Step 3:

[0760] The server generates content using a generative AI model. At this stage, it uses the analysis results obtained in step 2 as input to create personalized content for specific consumers. The output is content such as recipes and product information. Specifically, it prompts the generative AI model with the message, "Generate a new cooking recipe using popular local products," and retrieves a new recipe.

[0761] Step 4:

[0762] The device recognizes the user's emotions in real time. An emotion engine uses data collected from the camera and microphone to determine the user's emotional state. Input is the user's facial expressions and voice data, and output is an emotion label such as "excited" or "calm." Specific operations include facial image analysis using facial recognition technology and tone analysis using voice analysis.

[0763] Step 5:

[0764] The server further personalizes the content based on the user's emotional data. It takes the emotional data into account and makes final adjustments to the content created in Step 3. The input is the emotional label and generated content, and the output is content adapted to the user's state. For example, a relaxed user might receive a suggestion for a refreshing local juice.

[0765] Step 6:

[0766] The server translates and transmits the completed content in multiple languages. At this stage, the generated content is converted into multiple languages ​​and delivered to users in the target country or region. The input is the content completed up to step 5, and the output is multilingual content. Specifically, a translation API is used to convert the content into English, Chinese, Spanish, etc., and distribute it to the online platform.

[0767] Step 7:

[0768] Users view the received content and provide ratings and feedback. This feedback is sent to the server via the device and used to improve future content creation. The input is the user's feedback, and the output is the rating data stored in the server's database. Specifically, users communicate their ease of use, satisfaction with the content, etc., to the server through a rating form.

[0769] (Application Example 2)

[0770] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0771] Conventional content delivery systems have the challenge of not adequately personalizing content based on individual user emotions and preferences, making it difficult to achieve comprehensive consumer satisfaction. Furthermore, when providing multilingual support, flexible content adjustments based on user emotions are not implemented. There is a need for a system that can solve these problems and enable more effective information delivery.

[0772] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0773] In this invention, the server includes a structure for collecting consumption data, a structure for analyzing the consumption data and generating content based on the user's preferences, a structure for translating the generated content into multiple languages, a structure for recognizing the user's emotional state in real time, and a structure for further individualizing the content according to the emotional state. This enables a high level of personalization that responds to the user's emotions and preferences.

[0774] "Consumer data" refers to information about users' purchase history, browsing history, and behavioral patterns.

[0775] "User preferences" refer to the products, services, or areas of interest that a particular user enjoys.

[0776] A "content generation structure" is a system that generates relevant information and suggested content based on users' consumption data and preferences.

[0777] A "multilingual translation structure" is a system that translates generated content into different languages ​​and delivers it to diverse users in an appropriate format.

[0778] "User's emotional state" refers to information that indicates the user's current feelings and emotional state, such as joy or dissatisfaction.

[0779] A "real-time recognition structure" is a system that analyzes data in accordance with the current situation and obtains results immediately.

[0780] A "personalized structure" is a mechanism for adjusting and optimizing content and services to suit specific users.

[0781] One embodiment of this invention is a system for realizing an e-commerce site application incorporating an emotion engine. The details are described below.

[0782] The server first collects user consumption data, including browsing and purchase history. Next, it analyzes the collected data to generate personalized content based on the user's preferences. This process utilizes machine learning algorithms to automatically create content that is more interesting and engaging to the user.

[0783] The device collects data through its camera and microphone to recognize the user's emotional state in real time, and analyzes it using machine learning models such as TensorFlow. This allows it to recognize the emotions the user is feeling while browsing products, such as "enjoying" or "confusing."

[0784] The server further customizes content for each user based on the recognized emotion data. For example, if it recognizes that a user is happy, it adjusts the content to proactively suggest related products and discount information. This process enables more effective product recommendations that are tailored to the user's emotions and preferences.

[0785] If a user's facial expression indicates confusion while searching for a new gadget, the server can provide relevant review articles or FAQ pages to alleviate the user's confusion. An example of a prompt to input into the generating AI model would be, "Generate the best product suggestions based on the following emotion data: Enjoying, Interested."

[0786] This system makes it possible to personalize the experience based on the user's latest emotions and preferences, thereby improving consumer satisfaction.

[0787] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0788] Step 1:

[0789] The server collects user consumption data via the internet. Input data includes browsing history and purchase history. The server retrieves this data and stores it in a database.

[0790] Step 2:

[0791] The server analyzes stored consumption data using machine learning algorithms. The input is consumption data, and the output is features related to the user's preferences and interests. Through this analysis, the server identifies products and content that the user is most likely to be interested in.

[0792] Step 3:

[0793] The device collects the user's facial expressions and voice through its camera and microphone, and analyzes their emotional state in real time. Video and audio are provided as input data, which is processed by machine learning models such as TensorFlow, and the output generates emotional labels such as "enjoying" or "confused."

[0794] Step 4:

[0795] The server integrates user emotional states and preference data to generate personalized content. Inputs are emotional labels and preference features, while outputs are personalized product suggestions and information. The server combines this data to create optimal content that captures the user's interest.

[0796] Step 5:

[0797] The server translates the generated personalized content into the required target language through a multilingual translation engine. The input is the generated content, and the output is the translated content. This allows the server to deliver content appropriately to a global audience.

[0798] Step 6:

[0799] Users view personalized content provided on their devices, select products, and provide feedback. Input consists of user selections and feedback, while output is information for improving future content. The device sends this information to a server for use in improving future content.

[0800] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0801] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0802] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0803] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0804] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0805] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0806] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0807] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0808] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0809] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0810] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0811] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0812] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0813] 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.

[0814] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0815] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0816] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0817] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0818] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0819] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0820] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0821] The following is further disclosed regarding the embodiments described above.

[0822] (Claim 1)

[0823] Means of collecting consumer-related information,

[0824] A means for analyzing the aforementioned consumer-related information and generating content based on consumer preferences,

[0825] A means of translating the generated content into multiple languages,

[0826] A means for distributing the content translated into the aforementioned multiple languages,

[0827] A system that includes this.

[0828] (Claim 2)

[0829] The system according to claim 1, comprising means for generating recipes or usage examples related to local specialty products based on the consumer-related information collected.

[0830] (Claim 3)

[0831] The system according to claim 1, further comprising means for collecting consumer feedback on the generated content, and means for updating the generation algorithm based on the feedback.

[0832] "Example 1"

[0833] (Claim 1)

[0834] A means of automatically obtaining consumer-related information from multiple sources,

[0835] A means for analyzing the aforementioned consumer-related information using a machine learning algorithm and generating content based on consumer preferences,

[0836] A method for translating the generated content into multiple languages ​​using natural language processing technology,

[0837] A means of delivering the multilingual translated content via an appropriate delivery method tailored to the attributes of the target consumers,

[0838] A feedback mechanism that collects consumer evaluation information on generated content and improves the generation algorithm based on the analysis results,

[0839] A system that includes this.

[0840] (Claim 2)

[0841] The system according to claim 1, comprising means for automatically creating suggestions or usage examples related to a specific product based on consumer preference information obtained through the aforementioned analysis.

[0842] (Claim 3)

[0843] The system according to claim 1, further comprising means for collecting consumer feedback data on the generated content and adaptively updating the generation algorithm based on this data.

[0844] "Application Example 1"

[0845] (Claim 1)

[0846] Means of collecting consumer-related information,

[0847] A means for analyzing the aforementioned consumer-related information and generating content based on consumer preferences,

[0848] A means of translating the generated content into multiple languages,

[0849] A means for optimizing the delivery route of the content translated into the aforementioned multiple languages,

[0850] A means of promoting the trading of local specialty products using the generated content and suggesting purchases to consumers,

[0851] A means of suggesting recipes or uses for local specialty products based on consumers' purchase history,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, comprising means for analyzing past consumer transaction data based on the collected consumer-related information and generating individual use cases utilizing local specialty products.

[0855] (Claim 3)

[0856] The system according to claim 1, further comprising means for collecting consumer feedback on the generated content and for improving the content in the next transaction based on the feedback.

[0857] "Example 2 of combining an emotion engine"

[0858] (Claim 1)

[0859] Means of gathering consumer-related information,

[0860] A means for analyzing the aforementioned consumer information and generating content based on consumer preferences,

[0861] A means of recognizing user emotions and further personalizing content generated based on those emotions,

[0862] Means for converting the generated content into multiple languages,

[0863] means for transmitting the converted content,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, comprising means for generating product information or usage examples related to a specific item based on the consumer information collected.

[0867] (Claim 3)

[0868] The system according to claim 1, further comprising means for collecting consumer evaluations of the generated content, and means for updating the generation instructions based on the evaluations.

[0869] "Application example 2 when combining with an emotional engine"

[0870] (Claim 1)

[0871] Structure for collecting consumption data,

[0872] A structure that analyzes the aforementioned consumption data to generate content based on user preferences,

[0873] A structure for translating the generated content into multiple languages,

[0874] The structure for distributing the content translated into the aforementioned multiple languages,

[0875] A structure that recognizes the user's emotional state in real time,

[0876] A structure that further individualizes the content according to the aforementioned emotional state,

[0877] Information systems including

[0878] (Claim 2)

[0879] The information system according to claim 1, comprising a structure that generates formulations or usage forms related to local specialty products based on the collected consumption data.

[0880] (Claim 3)

[0881] The information system according to claim 1, further comprising a structure for collecting user responses to the generated content, and a structure for updating the generation algorithm based on the responses. [Explanation of Symbols]

[0882] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting consumer-related information, A means for analyzing the aforementioned consumer-related information and generating content based on consumer preferences, A means of translating the generated content into multiple languages, A means for optimizing the delivery route of the content translated into the aforementioned multiple languages, A means of promoting the trading of local specialty products using the generated content and suggesting purchases to consumers, A means of suggesting recipes or uses for local specialty products based on consumers' purchase history, A system that includes this.

2. The system according to claim 1, comprising means for analyzing past consumer transaction data based on the collected consumer-related information and generating individual use cases utilizing local specialty products.

3. The system according to claim 1, further comprising means for collecting consumer feedback on the generated content and for improving the content in the next transaction based on the feedback.

Images