system

Abstract

We provide the system. [Solution] A means for acquiring user preference information and generating personalized beverage menus based on said preference information, A means for receiving customer inquiries and generating responses based on those inquiries, A means of analyzing acquired inventory data and generating reports to optimize inventory management, A means of obtaining market trend data from external sources and proposing marketing activities based on that data, A means for collecting quality data from supply routes and generating a quality control report by analyzing said data, A means to automatically recognize customer data using location information and efficiently provide personalized information, 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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] In the coffee industry, there is a demand for personalizing beverage menus according to diverse customer preferences, providing effective customer service, improving inventory management efficiency, optimizing marketing strategies, and monitoring and improving quality in the supply chain. However, there is no system that can efficiently and integrally manage these, which has become a factor hindering the improvement of business efficiency and customer satisfaction.

Means for Solving the Problems

[0005] This invention provides a system that generates personalized beverage menus based on user preference information and has the function of receiving customer inquiries and providing appropriate responses. Furthermore, it optimizes inventory management by analyzing acquired inventory data and proposes marketing campaigns based on externally acquired market trend data. In addition, it includes a system that achieves efficient business operations and improved customer satisfaction by analyzing quality data collected from the supply chain and generating quality control reports.

[0006] "User preference information" refers to data about a customer's personal preferences and requests, including information about their preferences regarding the taste, type, and temperature of beverages.

[0007] A "personalized beverage menu" is a list of beverages created to suit a specific customer based on their preferences, representing a personalized selection from a standard menu.

[0008] "Inventory data" refers to data that shows information about the quantity and condition of products and materials currently being handled by a store or chain.

[0009] "Market trend data" refers to statistical information that shows trends regarding consumer purchasing behavior and fluctuations in popularity within a specific industry or market.

[0010] A "marketing campaign" refers to advertising and sales strategies aimed at promoting a specific product or service, designed to attract consumer interest and encourage purchases.

[0011] The "supply chain" refers to the entire distribution route from the production of a product to its final consumption, including the process from raw material suppliers to manufacturers, delivery companies, and retailers.

[0012] "Quality data" refers to data that records information about the quality of a product or service, including evaluations of durability, safety, and performance, for example.

[0013] A "quality control report" is a report that evaluates the degree to which a product or service meets quality standards, documents the results, and provides guidance for improvement. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments 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, a labeled 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, a labeled 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, a labeled 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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[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 provides a system aimed at improving efficient operations and customer satisfaction in the coffee industry. The following describes the specific processing of the program of this system.

[0036] Menu Generation

[0037] The server retrieves user preference information from a database. Based on this, it generates a personalized beverage menu optimized for the user. For example, if the user has a preference for sweets, the server will suggest "caramel macchiato" as a special menu item. The generated menu is then displayed on the user's terminal.

[0038] Handling customer interactions

[0039] The server receives inquiries from users and generates responses appropriate to those inquiries. For example, if the server receives an inquiry such as "What do you recommend?", it creates a menu that reflects the user's preferences and returns it as a response. The response is sent to the user's terminal for the user to review.

[0040] Optimizing inventory management

[0041] The server retrieves and analyzes the latest inventory data from the inventory management system. Based on the analysis, it determines whether the inventory situation is "sufficient" or "insufficient" and generates a report. This report is sent to the store manager's terminal, enabling efficient inventory management.

[0042] Optimizing marketing strategy

[0043] The server collects market trend data from external data sources and analyzes the data to propose marketing campaigns. For example, during the summer months, it might suggest an "iced coffee campaign." This information is then sent to marketing personnel's terminals and used for promotional activities.

[0044] Improving quality control

[0045] The server collects and analyzes quality data from the supply chain. If there are quality issues, the server generates a quality control report indicating that "improvement is needed" and sends it to the administrator's terminal. This helps maintain overall quality and contributes to improved customer satisfaction.

[0046] Through the program processing described above, the present invention aims to unify various operations in the coffee industry, thereby improving customer experience and operational efficiency. This system enables flexible responses to user needs, thereby enhancing a competitive advantage within the industry.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server retrieves preference information from the database based on the user's profile. This process references past purchase history and entered preferences.

[0050] Step 2:

[0051] The server selects special menu options from the basic beverage menu based on the user's preference information. For example, based on the information that the user "likes sweets," it might select "Caramel Macchiato."

[0052] Step 3:

[0053] The server selects menu items and sends them to the user's device as a personalized beverage menu. The user can then view this menu on their device.

[0054] Step 4:

[0055] The user enters their inquiry through their device. For example, they might enter a question like, "What do you recommend?"

[0056] Step 5:

[0057] The server receives inquiries from users and generates corresponding responses. It prepares accurate responses based on the corresponding menus and information.

[0058] Step 6:

[0059] The server sends the generated response to the user's terminal. The user can then view the returned response on their terminal.

[0060] Step 7:

[0061] The server collects current inventory data from the inventory management system. Quantity and demand forecast data for each product are also checked here.

[0062] Step 8:

[0063] The system analyzes inventory data collected by the server to determine whether there is sufficient or insufficient inventory. Based on the inventory status, it sets appropriate management policies.

[0064] Step 9:

[0065] The server generates an inventory report based on the analysis results and sends it to the store manager's terminal. This allows the manager to understand the inventory situation and take necessary measures.

[0066] Step 10:

[0067] The server retrieves market trend data from external data sources. This data includes current consumer behavior and sales trends.

[0068] Step 11:

[0069] The server analyzes market trend data and proposes effective marketing campaigns. For example, it might plan a campaign tailored to the increased demand for iced coffee during the summer months.

[0070] Step 12:

[0071] The server sends the proposed marketing campaign to the marketing team's terminal, and the team then prepares to implement the campaign.

[0072] Step 13:

[0073] The server collects and analyzes quality data from the supply chain. This data includes product ratings and return information.

[0074] Step 14:

[0075] The server generates a quality control report based on quality data. If there are quality issues, the report will specify what needs to be improved.

[0076] Step 15:

[0077] The server generates a quality control report which is then sent to the administrator's terminal, and the administrator uses that report to implement quality improvement measures.

[0078] (Example 1)

[0079] 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."

[0080] The coffee industry demands services tailored to individual customer preferences, efficient inventory management, effective marketing based on trends, and rapid responses to quality improvements. However, traditional systems have struggled to integrate and manage these elements, resulting in insufficient improvements in customer satisfaction and operational efficiency.

[0081] 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.

[0082] In this invention, the server includes means for collecting user preference information and generating personalized beverage provision information using generation technology that uses said preference information as input; means for receiving customer inquiries and generating automated responses based on said inquiries; and means for analyzing acquired inventory information and generating notifications to optimize inventory management. This enables the provision of services tailored to user preferences, effective inventory management, and responses based on customer needs.

[0083] "Preference information" refers to data that indicates the specific preferences and interests of individual customers.

[0084] "Generative technology" refers to techniques for automatically constructing specialized information based on collected data.

[0085] "Beverage provision information" refers to information about beverages selected or recommended according to customer preferences.

[0086] An "inquiry" refers to a communication that includes questions or requests from customers.

[0087] "Inventory information" refers to data regarding the quantity and condition of products currently held.

[0088] A "notification" is a digital message sent to inform someone of a specific situation or piece of information.

[0089] "Trends" refer to information that indicates trends that change over time, such as market conditions and consumer preferences.

[0090] A "sales strategy" is a plan of marketing activities formulated to achieve a specific goal.

[0091] "Quality information" refers to data related to the quality of a product or service.

[0092] A "supply chain" is a system that includes a series of processes from the time a product or service reaches the end consumer.

[0093] This invention is a system designed to improve operational efficiency and customer satisfaction in the coffee industry. The specific implementation details are described below.

[0094] The server, which is the heart of the system, integrates and executes multiple functions. First, the server retrieves user preference information from a database. This database uses a common relational database management system (e.g., MySQL®). The server inputs the retrieved preference information as prompts into a generative AI model (e.g., a natural language generation model) to generate personalized beverage recommendation information. This generated information is sent to the user terminal (e.g., a smartphone app) and displayed visually on the UI.

[0095] For example, if the user's preference data includes "likes sweets," the input prompt to the generating AI model would be "User preference: likes sweets." As a result, the server generates a list including beverages such as "caramel macchiato" and presents it to the user's terminal.

[0096] Next, the server uses natural language processing techniques (e.g., NLP libraries) through a chatbot interface to generate responses to user inquiries. For example, if a user asks "What do you recommend?", the server refers to preference information and returns a response using appropriate beverage recommendations.

[0097] The server also retrieves inventory information from the ERP system and analyzes real-time inventory status using a Python data analysis library (e.g., Pandas). Based on the analysis results, notifications are sent to store managers' terminals to optimize inventory management.

[0098] Furthermore, the server collects external market trend information and analyzes it using machine learning libraries (e.g., scikit-learn) to propose sales strategies tailored to the season and trends. These proposals are then sent as notifications to marketing personnel's terminals.

[0099] Finally, the server collects quality information from the supply chain and analyzes it using quality control software (e.g., Six Sigma tool). If the analysis reveals areas that do not meet quality standards, it sends a notification to the administrator stating that "improvement is needed" to promote quality improvement.

[0100] Thus, this system integrates multiple functions and provides adaptive and efficient services based on user needs.

[0101] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0102] Step 1:

[0103] The server retrieves user preference information from the database. Given a user ID as input, it uses an SQL query to extract preference information (e.g., "likes sweets") from the database. This preference information will be used in subsequent processing steps.

[0104] Step 2:

[0105] The server inputs the extracted preference information as a prompt into the generative AI model. It generates a prompt sentence (e.g., "User preference: Likes sweets") and inputs it into the generative AI model. Based on the prompt, this model outputs personalized beverage suggestions (e.g., caramel macchiato).

[0106] Step 3:

[0107] The server sends the suggestions generated by the AI ​​model to the user's terminal. The outputted beverage suggestions are displayed on the user's smartphone or tablet application, allowing the user to visually confirm them.

[0108] Step 4:

[0109] Users review beverage suggestions via their device and, if possible, use the chat function to make additional inquiries (e.g., "What do you recommend?"). The inquiry is then sent to the server.

[0110] Step 5:

[0111] The server receives inquiries from users and analyzes their content using natural language processing technology. Based on the analysis, it generates an appropriate response (e.g., recommended menu items) using previously obtained preference information and beverage suggestions, and sends it to the user's terminal.

[0112] Step 6:

[0113] The server retrieves inventory information from the inventory management system and analyzes the data using Pandas. Based on the analysis, it determines whether the inventory is "sufficient" or "insufficient," and generates an inventory management report based on that. This report is then sent to the store manager's terminal.

[0114] Step 7:

[0115] The server retrieves market trend information from an external database and analyzes it using machine learning algorithms. Based on the analysis results, it generates proposals for marketing campaigns (e.g., a summer iced coffee campaign) and notifies marketing personnel.

[0116] Step 8:

[0117] The server collects quality information from the supply chain and analyzes it using quality analysis tools. If a product's quality does not meet the standards, it creates a quality control report indicating that "improvement is needed" and sends it to the administrator. Based on this report, quality improvements are made.

[0118] (Application Example 1)

[0119] 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."

[0120] In modern smart cities, people's needs are becoming increasingly diverse, requiring personalized services. Meanwhile, store operators need efficient and accurate inventory and quality control, as well as improved customer satisfaction. This invention aims to efficiently solve these challenges and bring benefits to both users and stores within smart cities.

[0121] 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.

[0122] In this invention, the server includes means for acquiring user preference information and generating personalized beverage menus based on said preference information; means for receiving customer inquiries and generating responses based on said inquiries; means for analyzing acquired inventory data and generating reports for optimizing inventory management; means for acquiring market trend data from external sources and proposing marketing activities based on said data; means for collecting quality data from supply routes and generating quality control reports by analyzing said data; and means for automatically recognizing customer data using location information and efficiently providing personalized information. This makes it possible for customers to receive personalized services in cafes and stores within smart cities.

[0123] "User preference information" refers to information about the characteristics and taste preferences of individual users regarding beverages they like.

[0124] A "personalized beverage menu" refers to a selection of beverages optimized for each individual, generated based on the user's preference information.

[0125] "Means of receiving inquiries" refers to the method by which a server receives and processes questions and requests from customers.

[0126] A "report for optimizing inventory management" is a detailed report provided to analyze the inventory status of goods and materials and enable their efficient operation.

[0127] "Market trend data" refers to external data that shows current market trends and consumer preferences, and serves as indicator information for marketing activities.

[0128] "Collecting quality data from supply chains" means gathering quality information about the suppliers and distribution channels of goods and materials, and using that data to improve quality.

[0129] A "quality control report" is a document that provides information on maintaining and improving quality, based on the results obtained from analyzing quality data.

[0130] "Automatically recognizing customer data using location information" refers to a method that detects a customer's current location and dynamically provides relevant services and information to the user based on that information.

[0131] "Means for providing personalized information" refers to a mechanism for providing customized information tailored to the preferences and circumstances of each individual user.

[0132] The system for implementing this invention acquires user preference information and generates personalized beverage menus based on that information. The server stores the preference data acquired from the user terminal in a database and analyzes it. This makes it possible to present the most suitable menu for each user. When a user visits a store, the terminal uses location information services to link with the store's system and provides services tailored to the user's preference information and current location.

[0133] The server also assists with inventory management by collecting inventory data in real time and generating reports necessary for efficient management. Furthermore, it generates quality control reports by collecting and analyzing quality data from the supply chain. These reports can be used to improve quality and detect anomalies early. Marketing personnel are provided with campaign suggestions based on market trend data to support promotional activities.

[0134] This system was developed using the Python programming language, with PostgreSQL for database management, Pandas for data analysis, and React Native for the frontend. This results in a simple and scalable system architecture.

[0135] As a concrete example, if a user provides preference information such as "I like strong coffee" and visits a store, the system will recommend menu items such as espresso and ristretto. This process is achieved through prompts to a generative AI model, as shown below.

[0136] An example of a prompt message would be, "Generate a top menu that recommends strong coffee." This allows the user to enjoy an optimized coffee experience.

[0137] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0138] Step 1:

[0139] The server stores preference information received from the user's terminal in a database. The input is the user's preference data, and the output is the preference information stored in the database. This process involves receiving preference information entered by the user through the terminal application and recording it in the database.

[0140] Step 2:

[0141] When a user approaches a store, the terminal automatically connects with the store's system using location services. The input is the user's GPS location data, and the output is the connection status with the store's system. Based on the user's current location, it initiates communication with the nearest store's system and sends and receives the necessary data.

[0142] Step 3:

[0143] The server generates a personalized beverage menu based on acquired preference information. The input is the user's preference information stored in the database, and the output is the personalized beverage menu. The server analyzes the preference information and performs a process to list the most suitable beverage items.

[0144] Step 4:

[0145] The user terminal displays the personalized beverage menu received from the server on its screen. The input is the beverage menu provided by the server, and the output is the menu displayed on the user's screen. The terminal receives the data and provides it to the user visually.

[0146] Step 5:

[0147] The server acquires inventory management data in real time and analyzes it. The input is the latest inventory data, and the output is a report on the inventory status. The server checks inventory levels, detects shortages or surpluses, and generates reports.

[0148] Step 6:

[0149] The server collects quality data from the supply chain and generates quality control reports. The input is quality data from the supply chain, and the output is the quality control report. The server analyzes the data based on quality standards and generates a report indicating areas where quality maintenance or improvement is needed.

[0150] Step 7:

[0151] The server retrieves market trend data and proposes marketing campaigns based on it. The input is the latest market trend data, and the output is campaign proposal information. The server performs trend analysis and provides information to streamline relevant promotional activities.

[0152] Step 8:

[0153] The user terminal utilizes suggestions and information provided by the server as prompts for the generating AI model. The input is data generated by the server, and the output is text as a prompt for the AI ​​model. The user terminal uses this data to generate effective input for the AI ​​model.

[0154] 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.

[0155] This invention is a system that incorporates an emotion engine to recognize user emotions and adjust personalized beverage menus, improve customer service capabilities, and optimize marketing strategies. This system integrates and processes user preference information, emotion information, inventory data, market trend data, and supply chain quality data.

[0156] Menu adjustments based on emotion engine

[0157] The server uses an emotion engine to recognize the user's emotions based on voice and text data from the user's device. If the user is feeling relaxed, it adds relaxing beverages such as chamomile tea to the menu. A unique and personalized beverage menu is generated based on both emotions and preferences.

[0158] Emotion-based customer service

[0159] The server uses an emotion engine to generate emotionally appropriate responses to user inquiries. For example, if it determines that a user is stressed, it will generate a response suggesting a relaxing beverage or a special offer. This response is sent to the user's device, enabling an emotionally empathetic approach.

[0160] Emotionally conscious marketing strategies

[0161] The server analyzes user emotion data obtained by the emotion engine in combination with market trend data. This allows it to predict what kinds of promotions users are interested in and generate emotionally appealing marketing campaigns. For example, if a user is feeling happy, the server will plan campaign messages that emphasize that emotion.

[0162] Thus, the system of the present invention utilizes emotional technology to improve the customer experience and optimize operations. Through appropriate menu provision, customer service, and marketing measures that incorporate user emotions, it becomes possible to build deeper relationships with customers.

[0163] The following describes the processing flow.

[0164] Step 1:

[0165] Users access the system through their devices and input information via voice or text. This input includes information about orders and inquiries.

[0166] Step 2:

[0167] The server receives voice or text data from the user and uses an emotion engine to analyze the user's emotions. This analysis identifies the user's emotional state (e.g., stress, happiness, satisfaction, etc.).

[0168] Step 3:

[0169] The server combines analyzed emotional states with user preference information to create a personalized beverage menu. For example, if it determines that the user is seeking relaxation, it will suggest beverages such as chamomile tea.

[0170] Step 4:

[0171] The server sends a personalized beverage menu to the user's device. The user can then review the suggested menu on their device and proceed with their order.

[0172] Step 5:

[0173] If a user reviews the menu and has further questions, they will re-enter their questions through the terminal. For example, they might enter a question like, "What are some recommended ways to relax?"

[0174] Step 6:

[0175] The server receives a new inquiry from the user and generates an appropriate response using the emotion engine. It takes the user's emotions into consideration and recommends relaxing beverages or offers.

[0176] Step 7:

[0177] The server sends the generated response to the user's terminal. The user can then review the response on their terminal and take further action as needed.

[0178] Step 8:

[0179] The server integrates and analyzes user sentiment data and market trend data to formulate marketing campaigns. It plans promotional content tailored to the emotional state and notifies marketing personnel.

[0180] Step 9:

[0181] The server sends the marketing campaign information it has formulated to the marketing team's terminal, allowing them to prepare to launch an emotionally appealing campaign.

[0182] Through this series of processes, the system makes full use of emotion recognition technology and enables flexible responses tailored to user needs.

[0183] (Example 2)

[0184] 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".

[0185] Traditional beverage delivery systems have struggled to provide services that take into account the emotional state of users, making it difficult to improve customer satisfaction. Furthermore, there has been a lack of emotion-based marketing strategies linked to market trends, resulting in ineffective promotions. Solving these challenges and enabling the provision of more personalized customer experiences is essential.

[0186] 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.

[0187] In this invention, the server includes means for acquiring emotion data from a user information terminal and recognizing emotions using an emotion engine based on said emotion data; means for adjusting a personalized beverage menu based on the recognized emotions and preference information; and means for generating emotion-appropriate responses to user inquiries. This enables the provision of services that take into account the user's emotional state and the optimization of marketing strategies.

[0188] "Emotional data" refers to information that indicates a user's emotional state, and is acquired through means such as voice and text.

[0189] An "emotion engine" is a system that uses generative AI models to analyze user emotions from data and recognize specific states.

[0190] "Preference information" refers to data about users' preferences and habits, and forms the basis for providing personalized services.

[0191] A "personalized beverage menu" is a list of beverages tailored to the user's mood and preferences, and offered individually.

[0192] A "marketing campaign" is a promotional activity planned based on a specific market strategy to attract customer attention.

[0193] "User interaction" is a general term for the communication and operations that take place between the user and the system, and is an important element for improving the user experience.

[0194] This invention utilizes an emotion engine to provide personalized services based on the user's emotional state. In the system's implementation, the user's terminal acquires voice and text data and transmits it to a server. On the server side, a generative AI model is used to analyze the data and recognize emotions. The generative AI model used here is, for example, based on natural language processing technology.

[0195] Specifically, data acquired from the user's device is transferred to a server via the internet. The server inputs the received data into an emotion engine and uses a generative AI model to estimate emotions. Once an emotion is recognized, it is combined with the user's preference information to generate a personalized beverage menu. In addition, appropriate responses are created to user inquiries based on their emotions and sent to the user's device.

[0196] As an example of how the system works, when a user feels the need to relax amidst their busy daily life, they can speak "I want to relax" into their device, and that voice data is sent to the server. The server analyzes the voice data and uses an emotion engine to recognize the emotion of relaxation. Based on the results, a menu is generated that suggests, for example, "chamomile tea," and sent to the user.

[0197] Examples of prompts include instructions such as, "Analyze the user's current emotional state and determine if they want to relax," or "Suggest a special offer that the user might be interested in."

[0198] In this way, it becomes possible to provide services that are tailored to the user's emotional state, thereby increasing user satisfaction.

[0199] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0200] Step 1:

[0201] The user's device collects voice or text data. Data is obtained when the user speaks into the device or types text. The input data includes information about the user's emotional state and preferences. This data forms the basis for subsequent analysis.

[0202] Step 2:

[0203] The user's device sends the collected voice or text data to the server. Specifically, the data is securely transferred to the server via the internet. This prepares the data for further analysis on the server side.

[0204] Step 3:

[0205] The server processes the received data and performs analysis using a generative AI model and an emotion engine. The AI ​​is instructed to "analyze the user's emotions" as a prompt. The input data is analyzed using the emotion recognition function of the generative AI model, and the user's emotional state is output. This emotion data is then used for subsequent personalization processes.

[0206] Step 4:

[0207] The server uses the results of emotion recognition and compares them with the user's preference information to generate a personalized beverage menu. This involves extracting the user's past preferences from a database and combining them with emotion data. As a result, the most suitable beverage menu for the user is output.

[0208] Step 5:

[0209] The server sends the generated beverage menu to the user's device. This communication process allows the user to review their personalized recommendations. Specifically, a notification of the recommendations is displayed on the device.

[0210] Step 6:

[0211] The server combines and analyzes emotional data and market information to generate marketing campaigns. This analysis determines promotional content that matches the user's emotional state. As a result, an effective marketing message is output.

[0212] Step 7:

[0213] Users review the menu and marketing information received on their devices and decide on their actual actions. Their reactions and feedback are collected again for future analysis. Specifically, users view suggestions and take actions such as placing orders.

[0214] (Application Example 2)

[0215] 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".

[0216] In today's brick-and-mortar stores, personalized product recommendations that cater to diverse user preferences and emotions are essential. However, traditional sales systems struggle to provide product recommendations that consider the user's emotional state, making it difficult to improve customer satisfaction. Furthermore, there is a need to develop methods to deliver an even deeper customer experience through an approach based not only on preferences but also on emotions.

[0217] 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.

[0218] In this invention, the server includes means for acquiring user preference information and generating personalized beverage menus based on said preference information; means for receiving customer inquiries and generating responses based on said inquiries; means for analyzing acquired inventory data and generating reports for optimizing inventory management; means for acquiring market trend data from external sources and proposing marketing campaigns based on said data; means for collecting quality data from the supply chain and generating quality control reports by analyzing said data; and means for recognizing user emotions and recommending products in physical stores based on said emotions. This enables personalized product recommendations that respond to user emotions, and is expected to improve the customer experience.

[0219] "User preference information" refers to data on the preferences and tastes that individual users have for specific products or services.

[0220] A "personalized beverage menu" refers to a list of drinks specially tailored to the individual user's preferences and requests.

[0221] "Customer inquiries" refer to questions or requests from users regarding products or services.

[0222] "Inventory data" refers to information about the quantity and condition of the goods held.

[0223] "Market trend data" refers to the latest information regarding consumer needs, preferences, and purchasing trends in the market.

[0224] A "supply chain" refers to the route by which raw materials and products are delivered from the supplier to the consumer.

[0225] "Quality data" refers to information about the quality of a product or service.

[0226] "User emotions" refers to the sensory or emotional responses that users experience in specific situations or environments.

[0227] "Recommending a product" refers to the act of suggesting a specific product to a user based on certain conditions or preferences.

[0228] The system for realizing this invention mainly consists of a server and user terminals. The server comprehensively processes preference information, emotional information, inventory data, market trend data, and supply chain quality data from the user terminals. Specifically, the "emotion_recognition" library is used for emotion recognition, and the "product_recommendation" module is used for product recommendations.

[0229] The user's device, such as a smartphone or smart glasses, acquires data in real time from its microphone and camera. This data is sent to a server, where an emotion engine analyzes the user's emotional state. Based on the results, products are personalized and recommended according to the user's mood and preferences.

[0230] For example, when a user visits a physical store, the device captures the user's voice and determines that the user's current mood is one of relaxation. In such cases, the server recommends products that promote relaxation, such as herbal teas or aromatherapy products. This product information is displayed on the device and provided to the user.

[0231] An example of a prompt to input into a generative AI model would be: "The user has provided emotional data for today. Based on this data, please suggest relaxing products available for purchase in stores." This makes it possible to provide users with a more personalized and consistent experience.

[0232] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0233] Step 1:

[0234] The user captures on-site data through the device's microphone and camera. Input consists of the user's voice and facial expressions, and the device converts this data into a digital format and sends it to the server. Output is digital data that the server can process.

[0235] Step 2:

[0236] The server analyzes emotions using the "emotion_recognition" library based on digital data received from the terminal. The input is digital data from the terminal, and the user's emotional state is identified through data processing. The output is data containing emotion labels (e.g., relaxed, stressed).

[0237] Step 3:

[0238] The server combines sentiment labels and user preference data, using the "product_recommendation" module to generate a list of products suitable for the user. The input consists of sentiment labels and preference data, and the algorithm generates a list of recommended products. The output is a list of recommended products.

[0239] Step 4:

[0240] The server sends the generated list of products to the user's device. At this stage, the input is a list of recommended products, and the output is product information displayed on the user's device. The device visually presents the information to the user and encourages them to make a purchase.

[0241] Step 5:

[0242] The user uses a terminal to select desired items from the recommended products and indicate their intention to purchase. The input is the user's selection, and the output is the purchase data sent to the server. The server receives this data and prepares to proceed to the next step.

[0243] 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.

[0244] 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.

[0245] 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.

[0246] [Second Embodiment]

[0247] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0248] 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.

[0249] 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).

[0250] 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.

[0251] 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.

[0252] 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).

[0253] 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.

[0254] 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.

[0255] 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.

[0256] 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.

[0257] 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.

[0258] 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".

[0259] This invention provides a system aimed at improving efficient operations and customer satisfaction in the coffee industry. The following describes the specific processing of the program of this system.

[0260] Menu Generation

[0261] The server retrieves user preference information from a database. Based on this, it generates a personalized beverage menu optimized for the user. For example, if the user has a preference for sweets, the server will suggest "caramel macchiato" as a special menu item. The generated menu is then displayed on the user's terminal.

[0262] Handling customer interactions

[0263] The server receives inquiries from users and generates responses appropriate to those inquiries. For example, if the server receives an inquiry such as "What do you recommend?", it creates a menu that reflects the user's preferences and returns it as a response. The response is sent to the user's terminal for the user to review.

[0264] Optimizing inventory management

[0265] The server retrieves and analyzes the latest inventory data from the inventory management system. Based on the analysis, it determines whether the inventory situation is "sufficient" or "insufficient" and generates a report. This report is sent to the store manager's terminal, enabling efficient inventory management.

[0266] Optimizing marketing strategy

[0267] The server collects market trend data from external data sources and analyzes the data to propose marketing campaigns. For example, during the summer months, it might suggest an "iced coffee campaign." This information is then sent to marketing personnel's terminals and used for promotional activities.

[0268] Improving quality control

[0269] The server collects and analyzes quality data from the supply chain. If there are quality issues, the server generates a quality control report indicating that "improvement is needed" and sends it to the administrator's terminal. This helps maintain overall quality and contributes to improved customer satisfaction.

[0270] Through the program processing described above, the present invention aims to unify various operations in the coffee industry, thereby improving customer experience and operational efficiency. This system enables flexible responses to user needs, thereby enhancing a competitive advantage within the industry.

[0271] The process flow will be described below.

[0272] Step 1:

[0273] Based on the user's profile, the server retrieves preference information from the database. In this case, past purchase histories and entered preferences are referenced.

[0274] Step 2:

[0275] Based on the user's preference information, the server selects candidates for special menus from the basic beverage menu. For example, based on the information "likes sweet things", "caramel macchiato" is selected.

[0276] Step 3:

[0277] The server summarizes the selected menus and transmits them to the user's terminal as individualized beverage menus. The user can view this menu on the terminal.

[0278] Step 4:

[0279] The user inputs an inquiry through the terminal. For example, a question such as "What do you recommend?" is entered.

[0280] Step 5:

[0281] The server receives the inquiry from the user and generates a corresponding response. Based on the corresponding menu and information, an accurate response is prepared.

[0282] Step 6:

[0283] The server transmits the generated response to the user's terminal. The user can view the returned response on the terminal.

[0284] Step 7:

[0285] The server collects the current inventory data from the inventory management system. The quantity of each product and the demand forecast data are also checked here.

[0286] Step 8:

[0287] The server analyzes the collected inventory data to determine whether the inventory is sufficient or insufficient. Based on the inventory situation, appropriate management policies are set.

[0288] Step 9:

[0289] The server creates an inventory report based on the analysis results and sends it to the terminal of the store manager. This enables the manager to grasp the inventory situation and take necessary measures.

[0290] Step 10:

[0291] The server obtains market trend data from external data sources. This data includes current consumer behavior and sales trends.

[0292] Step 11:

[0293] The server analyzes the market trend data and proposes an effective marketing campaign. For example, plan a campaign in line with the increasing demand for iced coffee in summer.

[0294] Step 12:

[0295] The server sends the proposed marketing campaign to the terminal of the marketing staff, and the staff proceeds with the preparation to implement the campaign.

[0296] Step 13:

[0297] The server collects quality data from the supply chain and analyzes it. This data includes product ratings and return information, etc. [[ID=四十九]] <00009四十]]

[0298] Step 14:

[0299] The server generates a quality management report based on the quality data. If there are quality problems, the report describes specifically what should be improved.

[0300] Step 15:

[0301] The server transmits the quality management report generated to the administrator's terminal, and the administrator takes quality improvement measures based on the report.

[0302] (Example 1)

[0303] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0304] In the coffee industry, there is a demand for providing services according to individual customer preferences, efficient inventory management, effective marketing based on trends, and quick responses for quality improvement. However, in the conventional system, it is difficult to manage these elements integratively, and customer satisfaction and business efficiency cannot be fully achieved.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0306] In this invention, the server includes means for collecting the preference information of users and generating individualized beverage provision information by using a generation technology that uses the preference information as an input, means for receiving inquiries from customers and generating an automated response based on the inquiries, and means for analyzing the acquired inventory information and generating a notification for optimizing inventory management. Thereby, it becomes possible to provide services according to user preferences, conduct effective inventory management, and respond based on customer needs.

[0307] [[ID=...]] "Preference information" is data indicating specific preferences and interests of individual customers.

[0308] "Generative technology" refers to techniques for automatically constructing specialized information based on collected data.

[0309] "Beverage provision information" refers to information about beverages selected or recommended according to customer preferences.

[0310] An "inquiry" refers to a communication that includes questions or requests from customers.

[0311] "Inventory information" refers to data regarding the quantity and condition of products currently held.

[0312] A "notification" is a digital message sent to inform someone of a specific situation or piece of information.

[0313] "Trends" refer to information that indicates trends that change over time, such as market conditions and consumer preferences.

[0314] A "sales strategy" is a plan of marketing activities formulated to achieve a specific goal.

[0315] "Quality information" refers to data related to the quality of a product or service.

[0316] A "supply chain" is a system that includes a series of processes from the time a product or service reaches the end consumer.

[0317] This invention is a system designed to improve operational efficiency and customer satisfaction in the coffee industry. The specific implementation details are described below.

[0318] The server, which is the heart of the system, integrates and executes multiple functions. First, the server retrieves user preference information from a database. This database uses a common relational database management system (e.g., MySQL). The server inputs the retrieved preference information as prompts into a generative AI model (e.g., a natural language generation model) to generate personalized beverage recommendation information. This generated information is sent to the user terminal (e.g., a smartphone app) and displayed visually on the UI.

[0319] For example, if the user's preference data includes "likes sweets," the input prompt to the generating AI model would be "User preference: likes sweets." As a result, the server generates a list including beverages such as "caramel macchiato" and presents it to the user's terminal.

[0320] Next, the server uses natural language processing techniques (e.g., NLP libraries) through a chatbot interface to generate responses to user inquiries. For example, if a user asks "What do you recommend?", the server refers to preference information and returns a response using appropriate beverage recommendations.

[0321] The server also retrieves inventory information from the ERP system and analyzes real-time inventory status using a Python data analysis library (e.g., Pandas). Based on the analysis results, notifications are sent to store managers' terminals to optimize inventory management.

[0322] Furthermore, the server collects external market trend information and analyzes it using machine learning libraries (e.g., scikit-learn) to propose sales strategies tailored to the season and trends. These proposals are then sent as notifications to marketing personnel's terminals.

[0323] Finally, the server collects quality information from the supply chain and analyzes it using quality control software (e.g., Six Sigma tool). If the analysis reveals areas that do not meet quality standards, it sends a notification to the administrator stating that "improvement is needed" to promote quality improvement.

[0324] Thus, this system integrates multiple functions and provides adaptive and efficient services based on user needs.

[0325] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0326] Step 1:

[0327] The server retrieves user preference information from the database. Given a user ID as input, it uses an SQL query to extract preference information (e.g., "likes sweets") from the database. This preference information will be used in subsequent processing steps.

[0328] Step 2:

[0329] The server inputs the extracted preference information as a prompt into the generative AI model. It generates a prompt sentence (e.g., "User preference: Likes sweets") and inputs it into the generative AI model. Based on the prompt, this model outputs personalized beverage suggestions (e.g., caramel macchiato).

[0330] Step 3:

[0331] The server sends the suggestions generated by the AI ​​model to the user's terminal. The outputted beverage suggestions are displayed on the user's smartphone or tablet application, allowing the user to visually confirm them.

[0332] Step 4:

[0333] Users review beverage suggestions via their device and, if possible, use the chat function to make additional inquiries (e.g., "What do you recommend?"). The inquiry is then sent to the server.

[0334] Step 5:

[0335] The server receives inquiries from users and analyzes their content using natural language processing technology. Based on the analysis, it generates an appropriate response (e.g., recommended menu items) using previously obtained preference information and beverage suggestions, and sends it to the user's terminal.

[0336] Step 6:

[0337] The server retrieves inventory information from the inventory management system and analyzes the data using Pandas. Based on the analysis, it determines whether the inventory is "sufficient" or "insufficient," and generates an inventory management report based on that. This report is then sent to the store manager's terminal.

[0338] Step 7:

[0339] The server retrieves market trend information from an external database and analyzes it using machine learning algorithms. Based on the analysis results, it generates proposals for marketing campaigns (e.g., a summer iced coffee campaign) and notifies marketing personnel.

[0340] Step 8:

[0341] The server collects quality information from the supply chain and analyzes it using quality analysis tools. If a product's quality does not meet the standards, it creates a quality control report indicating that "improvement is needed" and sends it to the administrator. Based on this report, quality improvements are made.

[0342] (Application Example 1)

[0343] 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 glasses 214 will be referred to as the "terminal."

[0344] In modern smart cities, people's needs are becoming increasingly diverse, requiring personalized services. Meanwhile, store operators need efficient and accurate inventory and quality control, as well as improved customer satisfaction. This invention aims to efficiently solve these challenges and bring benefits to both users and stores within smart cities.

[0345] 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.

[0346] In this invention, the server includes means for acquiring user preference information and generating personalized beverage menus based on said preference information; means for receiving customer inquiries and generating responses based on said inquiries; means for analyzing acquired inventory data and generating reports for optimizing inventory management; means for acquiring market trend data from external sources and proposing marketing activities based on said data; means for collecting quality data from supply routes and generating quality control reports by analyzing said data; and means for automatically recognizing customer data using location information and efficiently providing personalized information. This makes it possible for customers to receive personalized services in cafes and stores within smart cities.

[0347] "User preference information" refers to information about the characteristics and taste preferences of individual users regarding beverages they like.

[0348] A "personalized beverage menu" refers to a selection of beverages optimized for each individual, generated based on the user's preference information.

[0349] "Means of receiving inquiries" refers to the method by which a server receives and processes questions and requests from customers.

[0350] A "report for optimizing inventory management" is a detailed report provided to analyze the inventory status of goods and materials and enable their efficient operation.

[0351] "Market trend data" refers to external data that shows current market trends and consumer preferences, and serves as indicator information for marketing activities.

[0352] "Collecting quality data from supply chains" means gathering quality information about the suppliers and distribution channels of goods and materials, and using that data to improve quality.

[0353] A "quality control report" is a document that provides information on maintaining and improving quality, based on the results obtained from analyzing quality data.

[0354] "Automatically recognizing customer data using location information" refers to a method that detects a customer's current location and dynamically provides relevant services and information to the user based on that information.

[0355] "Means for providing personalized information" refers to a mechanism for providing customized information tailored to the preferences and circumstances of each individual user.

[0356] The system for implementing this invention acquires user preference information and generates personalized beverage menus based on that information. The server stores the preference data acquired from the user terminal in a database and analyzes it. This makes it possible to present the most suitable menu for each user. When a user visits a store, the terminal uses location information services to link with the store's system and provides services tailored to the user's preference information and current location.

[0357] The server also assists with inventory management by collecting inventory data in real time and generating reports necessary for efficient management. Furthermore, it generates quality control reports by collecting and analyzing quality data from the supply chain. These reports can be used to improve quality and detect anomalies early. Marketing personnel are provided with campaign suggestions based on market trend data to support promotional activities.

[0358] This system was developed using the Python programming language, with PostgreSQL for database management, Pandas for data analysis, and React Native for the frontend. This results in a simple and scalable system architecture.

[0359] As a concrete example, if a user provides preference information such as "I like strong coffee" and visits a store, the system will recommend menu items such as espresso and ristretto. This process is achieved through prompts to a generative AI model, as shown below.

[0360] An example of a prompt message would be, "Generate a top menu that recommends strong coffee." This allows the user to enjoy an optimized coffee experience.

[0361] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0362] Step 1:

[0363] The server stores preference information received from the user's terminal in a database. The input is the user's preference data, and the output is the preference information stored in the database. This process involves receiving preference information entered by the user through the terminal application and recording it in the database.

[0364] Step 2:

[0365] When a user approaches a store, the terminal automatically connects with the store's system using location services. The input is the user's GPS location data, and the output is the connection status with the store's system. Based on the user's current location, it initiates communication with the nearest store's system and sends and receives the necessary data.

[0366] Step 3:

[0367] The server generates a personalized beverage menu based on acquired preference information. The input is the user's preference information stored in the database, and the output is the personalized beverage menu. The server analyzes the preference information and performs a process to list the most suitable beverage items.

[0368] Step 4:

[0369] The user terminal displays the personalized beverage menu received from the server on its screen. The input is the beverage menu provided by the server, and the output is the menu displayed on the user's screen. The terminal receives the data and provides it to the user visually.

[0370] Step 5:

[0371] The server acquires inventory management data in real time and analyzes it. The input is the latest inventory data, and the output is a report on the inventory status. The server checks inventory levels, detects shortages or surpluses, and generates reports.

[0372] Step 6:

[0373] The server collects quality data from the supply chain and generates quality control reports. The input is quality data from the supply chain, and the output is the quality control report. The server analyzes the data based on quality standards and generates a report indicating areas where quality maintenance or improvement is needed.

[0374] Step 7:

[0375] The server retrieves market trend data and proposes marketing campaigns based on it. The input is the latest market trend data, and the output is campaign proposal information. The server performs trend analysis and provides information to streamline relevant promotional activities.

[0376] Step 8:

[0377] The user terminal utilizes suggestions and information provided by the server as prompts for the generating AI model. The input is data generated by the server, and the output is text as a prompt for the AI ​​model. The user terminal uses this data to generate effective input for the AI ​​model.

[0378] 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.

[0379] This invention is a system that incorporates an emotion engine to recognize user emotions and adjust personalized beverage menus, improve customer service capabilities, and optimize marketing strategies. This system integrates and processes user preference information, emotion information, inventory data, market trend data, and supply chain quality data.

[0380] Menu adjustments based on emotion engine

[0381] The server uses an emotion engine to recognize the user's emotions based on voice and text data from the user's device. If the user is feeling relaxed, it adds relaxing beverages such as chamomile tea to the menu. A unique and personalized beverage menu is generated based on both emotions and preferences.

[0382] Emotion-based customer service

[0383] The server uses an emotion engine to generate emotionally appropriate responses to user inquiries. For example, if it determines that a user is stressed, it will generate a response suggesting a relaxing beverage or a special offer. This response is sent to the user's device, enabling an emotionally empathetic approach.

[0384] Emotionally conscious marketing strategies

[0385] The server analyzes user emotion data obtained by the emotion engine in combination with market trend data. This allows it to predict what kinds of promotions users are interested in and generate emotionally appealing marketing campaigns. For example, if a user is feeling happy, the server will plan campaign messages that emphasize that emotion.

[0386] Thus, the system of the present invention utilizes emotional technology to improve the customer experience and optimize operations. Through appropriate menu provision, customer service, and marketing measures that incorporate user emotions, it becomes possible to build deeper relationships with customers.

[0387] The following describes the processing flow.

[0388] Step 1:

[0389] Users access the system through their devices and input information via voice or text. This input includes information about orders and inquiries.

[0390] Step 2:

[0391] The server receives voice or text data from the user and uses an emotion engine to analyze the user's emotions. This analysis identifies the user's emotional state (e.g., stress, happiness, satisfaction, etc.).

[0392] Step 3:

[0393] The server combines analyzed emotional states with user preference information to create a personalized beverage menu. For example, if it determines that the user is seeking relaxation, it will suggest beverages such as chamomile tea.

[0394] Step 4:

[0395] The server sends a personalized beverage menu to the user's device. The user can then review the suggested menu on their device and proceed with their order.

[0396] Step 5:

[0397] If a user reviews the menu and has further questions, they will re-enter their questions through the terminal. For example, they might enter a question like, "What are some recommended ways to relax?"

[0398] Step 6:

[0399] The server receives a new inquiry from the user and generates an appropriate response using the emotion engine. It takes the user's emotions into consideration and recommends relaxing beverages or offers.

[0400] Step 7:

[0401] The server sends the generated response to the user's terminal. The user can then review the response on their terminal and take further action as needed.

[0402] Step 8:

[0403] The server integrates and analyzes user sentiment data and market trend data to formulate marketing campaigns. It plans promotional content tailored to the emotional state and notifies marketing personnel.

[0404] Step 9:

[0405] The server sends the marketing campaign information it has formulated to the marketing team's terminal, allowing them to prepare to launch an emotionally appealing campaign.

[0406] Through this series of processes, the system makes full use of emotion recognition technology and enables flexible responses tailored to user needs.

[0407] (Example 2)

[0408] 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".

[0409] Traditional beverage delivery systems have struggled to provide services that take into account the emotional state of users, making it difficult to improve customer satisfaction. Furthermore, there has been a lack of emotion-based marketing strategies linked to market trends, resulting in ineffective promotions. Solving these challenges and enabling the provision of more personalized customer experiences is essential.

[0410] 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.

[0411] In this invention, the server includes means for acquiring emotion data from a user information terminal and recognizing emotions using an emotion engine based on said emotion data; means for adjusting a personalized beverage menu based on the recognized emotions and preference information; and means for generating emotion-appropriate responses to user inquiries. This enables the provision of services that take into account the user's emotional state and the optimization of marketing strategies.

[0412] "Emotional data" refers to information that indicates a user's emotional state, and is acquired through means such as voice and text.

[0413] An "emotion engine" is a system that uses generative AI models to analyze user emotions from data and recognize specific states.

[0414] "Preference information" refers to data about users' preferences and habits, and forms the basis for providing personalized services.

[0415] A "personalized beverage menu" is a list of beverages tailored to the user's mood and preferences, and offered individually.

[0416] A "marketing campaign" is a promotional activity planned based on a specific market strategy to attract customer attention.

[0417] "User interaction" is a general term for the communication and operations that take place between the user and the system, and is an important element for improving the user experience.

[0418] This invention utilizes an emotion engine to provide personalized services based on the user's emotional state. In the system's implementation, the user's terminal acquires voice and text data and transmits it to a server. On the server side, a generative AI model is used to analyze the data and recognize emotions. The generative AI model used here is, for example, based on natural language processing technology.

[0419] Specifically, data acquired from the user's device is transferred to a server via the internet. The server inputs the received data into an emotion engine and uses a generative AI model to estimate emotions. Once an emotion is recognized, it is combined with the user's preference information to generate a personalized beverage menu. In addition, appropriate responses are created to user inquiries based on their emotions and sent to the user's device.

[0420] As an example of how the system works, when a user feels the need to relax amidst their busy daily life, they can speak "I want to relax" into their device, and that voice data is sent to the server. The server analyzes the voice data and uses an emotion engine to recognize the emotion of relaxation. Based on the results, a menu is generated that suggests, for example, "chamomile tea," and sent to the user.

[0421] Examples of prompts include instructions such as, "Analyze the user's current emotional state and determine if they want to relax," or "Suggest a special offer that the user might be interested in."

[0422] In this way, it becomes possible to provide services that are tailored to the user's emotional state, thereby increasing user satisfaction.

[0423] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0424] Step 1:

[0425] The user's device collects voice or text data. Data is obtained when the user speaks into the device or types text. The input data includes information about the user's emotional state and preferences. This data forms the basis for subsequent analysis.

[0426] Step 2:

[0427] The user's device sends the collected voice or text data to the server. Specifically, the data is securely transferred to the server via the internet. This prepares the data for further analysis on the server side.

[0428] Step 3:

[0429] The server processes the received data and performs analysis using a generative AI model and an emotion engine. The AI ​​is instructed to "analyze the user's emotions" as a prompt. The input data is analyzed using the emotion recognition function of the generative AI model, and the user's emotional state is output. This emotion data is then used for subsequent personalization processes.

[0430] Step 4:

[0431] The server uses the results of emotion recognition and compares them with the user's preference information to generate a personalized beverage menu. This involves extracting the user's past preferences from a database and combining them with emotion data. As a result, the most suitable beverage menu for the user is output.

[0432] Step 5:

[0433] The server sends the generated beverage menu to the user's device. This communication process allows the user to review their personalized recommendations. Specifically, a notification of the recommendations is displayed on the device.

[0434] Step 6:

[0435] The server combines and analyzes emotional data and market information to generate marketing campaigns. This analysis determines promotional content that matches the user's emotional state. As a result, an effective marketing message is output.

[0436] Step 7:

[0437] Users review the menu and marketing information received on their devices and decide on their actual actions. Their reactions and feedback are collected again for future analysis. Specifically, users view suggestions and take actions such as placing orders.

[0438] (Application Example 2)

[0439] 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."

[0440] In today's brick-and-mortar stores, personalized product recommendations that cater to diverse user preferences and emotions are essential. However, traditional sales systems struggle to provide product recommendations that consider the user's emotional state, making it difficult to improve customer satisfaction. Furthermore, there is a need to develop methods to deliver an even deeper customer experience through an approach based not only on preferences but also on emotions.

[0441] 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.

[0442] In this invention, the server includes means for acquiring user preference information and generating personalized beverage menus based on said preference information; means for receiving customer inquiries and generating responses based on said inquiries; means for analyzing acquired inventory data and generating reports for optimizing inventory management; means for acquiring market trend data from external sources and proposing marketing campaigns based on said data; means for collecting quality data from the supply chain and generating quality control reports by analyzing said data; and means for recognizing user emotions and recommending products in physical stores based on said emotions. This enables personalized product recommendations that respond to user emotions, and is expected to improve the customer experience.

[0443] "User preference information" refers to data on the preferences and tastes that individual users have for specific products or services.

[0444] A "personalized beverage menu" refers to a list of drinks specially tailored to the individual user's preferences and requests.

[0445] "Customer inquiries" refer to questions or requests from users regarding products or services.

[0446] "Inventory data" refers to information about the quantity and condition of the goods held.

[0447] "Market trend data" refers to the latest information regarding consumer needs, preferences, and purchasing trends in the market.

[0448] A "supply chain" refers to the route by which raw materials and products are delivered from the supplier to the consumer.

[0449] "Quality data" refers to information about the quality of a product or service.

[0450] "User emotions" refers to the sensory or emotional responses that users experience in specific situations or environments.

[0451] "Recommending a product" refers to the act of suggesting a specific product to a user based on certain conditions or preferences.

[0452] The system for realizing this invention mainly consists of a server and user terminals. The server comprehensively processes preference information, emotional information, inventory data, market trend data, and supply chain quality data from the user terminals. Specifically, the "emotion_recognition" library is used for emotion recognition, and the "product_recommendation" module is used for product recommendations.

[0453] The user's device, such as a smartphone or smart glasses, acquires data in real time from its microphone and camera. This data is sent to a server, where an emotion engine analyzes the user's emotional state. Based on the results, products are personalized and recommended according to the user's mood and preferences.

[0454] For example, when a user visits a physical store, the device captures the user's voice and determines that the user's current mood is one of relaxation. In such cases, the server recommends products that promote relaxation, such as herbal teas or aromatherapy products. This product information is displayed on the device and provided to the user.

[0455] An example of a prompt to input into a generative AI model would be: "The user has provided emotional data for today. Based on this data, please suggest relaxing products available for purchase in stores." This makes it possible to provide users with a more personalized and consistent experience.

[0456] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0457] Step 1:

[0458] The user captures on-site data through the device's microphone and camera. Input consists of the user's voice and facial expressions, and the device converts this data into a digital format and sends it to the server. Output is digital data that the server can process.

[0459] Step 2:

[0460] The server analyzes emotions using the "emotion_recognition" library based on digital data received from the terminal. The input is digital data from the terminal, and the user's emotional state is identified through data processing. The output is data containing emotion labels (e.g., relaxed, stressed).

[0461] Step 3:

[0462] The server combines sentiment labels and user preference data, using the "product_recommendation" module to generate a list of products suitable for the user. The input consists of sentiment labels and preference data, and the algorithm generates a list of recommended products. The output is a list of recommended products.

[0463] Step 4:

[0464] The server sends the generated list of products to the user's device. At this stage, the input is a list of recommended products, and the output is product information displayed on the user's device. The device visually presents the information to the user and encourages them to make a purchase.

[0465] Step 5:

[0466] The user uses a terminal to select desired items from the recommended products and indicate their intention to purchase. The input is the user's selection, and the output is the purchase data sent to the server. The server receives this data and prepares to proceed to the next step.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] [Third Embodiment]

[0471] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0472] 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.

[0473] 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).

[0474] 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.

[0475] 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.

[0476] 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).

[0477] 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.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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.

[0482] 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".

[0483] This invention provides a system aimed at improving efficient operations and customer satisfaction in the coffee industry. The following describes the specific processing of the program of this system.

[0484] Menu Generation

[0485] The server retrieves user preference information from a database. Based on this, it generates a personalized beverage menu optimized for the user. For example, if the user has a preference for sweets, the server will suggest "caramel macchiato" as a special menu item. The generated menu is then displayed on the user's terminal.

[0486] Handling customer interactions

[0487] The server receives inquiries from users and generates responses appropriate to those inquiries. For example, if the server receives an inquiry such as "What do you recommend?", it creates a menu that reflects the user's preferences and returns it as a response. The response is sent to the user's terminal for the user to review.

[0488] Optimizing inventory management

[0489] The server retrieves and analyzes the latest inventory data from the inventory management system. Based on the analysis, it determines whether the inventory situation is "sufficient" or "insufficient" and generates a report. This report is sent to the store manager's terminal, enabling efficient inventory management.

[0490] Optimizing marketing strategy

[0491] The server collects market trend data from external data sources and analyzes the data to propose marketing campaigns. For example, during the summer months, it might suggest an "iced coffee campaign." This information is then sent to marketing personnel's terminals and used for promotional activities.

[0492] Improving quality control

[0493] The server collects and analyzes quality data from the supply chain. If there are quality issues, the server generates a quality control report indicating that "improvement is needed" and sends it to the administrator's terminal. This helps maintain overall quality and contributes to improved customer satisfaction.

[0494] Through the program processing described above, the present invention aims to unify various operations in the coffee industry, thereby improving customer experience and operational efficiency. This system enables flexible responses to user needs, thereby enhancing a competitive advantage within the industry.

[0495] The following describes the processing flow.

[0496] Step 1:

[0497] The server retrieves preference information from the database based on the user's profile. This process references past purchase history and entered preferences.

[0498] Step 2:

[0499] The server selects special menu options from the basic beverage menu based on the user's preference information. For example, based on the information that the user "likes sweets," it might select "Caramel Macchiato."

[0500] Step 3:

[0501] The server selects menu items and sends them to the user's device as a personalized beverage menu. The user can then view this menu on their device.

[0502] Step 4:

[0503] The user enters their inquiry through their device. For example, they might enter a question like, "What do you recommend?"

[0504] Step 5:

[0505] The server receives inquiries from users and generates corresponding responses. It prepares accurate responses based on the corresponding menus and information.

[0506] Step 6:

[0507] The server sends the generated response to the user's terminal. The user can then view the returned response on their terminal.

[0508] Step 7:

[0509] The server collects current inventory data from the inventory management system. Quantity and demand forecast data for each product are also checked here.

[0510] Step 8:

[0511] The system analyzes inventory data collected by the server to determine whether there is sufficient or insufficient inventory. Based on the inventory status, it sets appropriate management policies.

[0512] Step 9:

[0513] The server generates an inventory report based on the analysis results and sends it to the store manager's terminal. This allows the manager to understand the inventory situation and take necessary actions.

[0514] Step 10:

[0515] The server retrieves market trend data from external data sources. This data includes current consumer behavior and sales trends.

[0516] Step 11:

[0517] The server analyzes market trend data and proposes effective marketing campaigns. For example, it might plan a campaign tailored to the increased demand for iced coffee during the summer months.

[0518] Step 12:

[0519] The server sends the proposed marketing campaign to the marketing team's terminal, and the team then prepares to implement the campaign.

[0520] Step 13:

[0521] The server collects and analyzes quality data from the supply chain. This data includes product ratings and return information.

[0522] Step 14:

[0523] The server generates a quality control report based on quality data. If there are quality issues, the report will specify what needs to be improved.

[0524] Step 15:

[0525] The server generates a quality control report which is then sent to the administrator's terminal, and the administrator uses that report to implement quality improvement measures.

[0526] (Example 1)

[0527] 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."

[0528] The coffee industry demands services tailored to individual customer preferences, efficient inventory management, effective marketing based on trends, and rapid responses to quality improvements. However, traditional systems have struggled to integrate and manage these elements, resulting in insufficient improvements in customer satisfaction and operational efficiency.

[0529] 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.

[0530] In this invention, the server includes means for collecting user preference information and generating personalized beverage provision information using generation technology that uses said preference information as input; means for receiving customer inquiries and generating automated responses based on said inquiries; and means for analyzing acquired inventory information and generating notifications to optimize inventory management. This enables the provision of services tailored to user preferences, effective inventory management, and responses based on customer needs.

[0531] "Preference information" refers to data that indicates the specific preferences and interests of individual customers.

[0532] "Generative technology" refers to techniques for automatically constructing specialized information based on collected data.

[0533] "Beverage provision information" refers to information about beverages selected or recommended according to customer preferences.

[0534] An "inquiry" refers to a communication that includes questions or requests from customers.

[0535] "Inventory information" refers to data regarding the quantity and condition of products currently held.

[0536] A "notification" is a digital message sent to inform someone of a specific situation or piece of information.

[0537] "Trends" refer to information that indicates trends that change over time, such as market conditions and consumer preferences.

[0538] A "sales strategy" is a plan of marketing activities formulated to achieve a specific goal.

[0539] "Quality information" refers to data related to the quality of a product or service.

[0540] A "supply chain" is a system that includes a series of processes from the time a product or service reaches the end consumer.

[0541] This invention is a system designed to improve operational efficiency and customer satisfaction in the coffee industry. The specific implementation details are described below.

[0542] The server, which is the heart of the system, integrates and executes multiple functions. First, the server retrieves user preference information from a database. This database uses a common relational database management system (e.g., MySQL). The server inputs the retrieved preference information as prompts into a generative AI model (e.g., a natural language generation model) to generate personalized beverage recommendation information. This generated information is sent to the user terminal (e.g., a smartphone app) and displayed visually on the UI.

[0543] For example, if the user's preference data includes "likes sweets," the input prompt to the generating AI model would be "User preference: likes sweets." As a result, the server generates a list including beverages such as "caramel macchiato" and presents it to the user's terminal.

[0544] Next, the server uses natural language processing techniques (e.g., NLP libraries) through a chatbot interface to generate responses to user inquiries. For example, if a user asks "What do you recommend?", the server refers to preference information and returns a response using appropriate beverage recommendations.

[0545] The server also retrieves inventory information from the ERP system and analyzes real-time inventory status using a Python data analysis library (e.g., Pandas). Based on the analysis results, notifications are sent to store managers' terminals to optimize inventory management.

[0546] Furthermore, the server collects external market trend information and analyzes it using machine learning libraries (e.g., scikit-learn) to propose sales strategies tailored to the season and trends. These proposals are then sent as notifications to marketing personnel's terminals.

[0547] Finally, the server collects quality information from the supply chain and analyzes it using quality control software (e.g., Six Sigma tool). If the analysis reveals areas that do not meet quality standards, it sends a notification to the administrator stating that "improvement is needed" to promote quality improvement.

[0548] Thus, this system integrates multiple functions and provides adaptive and efficient services based on user needs.

[0549] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0550] Step 1:

[0551] The server retrieves user preference information from the database. Given a user ID as input, it uses an SQL query to extract preference information (e.g., "likes sweets") from the database. This preference information will be used in subsequent processing steps.

[0552] Step 2:

[0553] The server inputs the extracted preference information as a prompt into the generative AI model. It generates a prompt sentence (e.g., "User preference: Likes sweets") and inputs it into the generative AI model. Based on the prompt, this model outputs personalized beverage suggestions (e.g., caramel macchiato).

[0554] Step 3:

[0555] The server sends the suggestions generated by the AI ​​model to the user's terminal. The outputted beverage suggestions are displayed on the user's smartphone or tablet application, allowing the user to visually confirm them.

[0556] Step 4:

[0557] Users review beverage suggestions via their device and, if possible, use the chat function to make additional inquiries (e.g., "What do you recommend?"). The inquiry is then sent to the server.

[0558] Step 5:

[0559] The server receives inquiries from users and analyzes their content using natural language processing technology. Based on the analysis, it uses previously obtained preference information and beverage suggestions to generate an appropriate response (e.g., recommended menu items) and sends it to the user's terminal.

[0560] Step 6:

[0561] The server retrieves inventory information from the inventory management system and analyzes the data using Pandas. Based on the analysis, it determines whether the inventory is "sufficient" or "insufficient," and generates an inventory management report based on that. This report is then sent to the store manager's terminal.

[0562] Step 7:

[0563] The server retrieves market trend information from an external database and analyzes it using machine learning algorithms. Based on the analysis results, it generates proposals for marketing campaigns (e.g., a summer iced coffee campaign) and notifies marketing personnel.

[0564] Step 8:

[0565] The server collects quality information from the supply chain and analyzes it using quality analysis tools. If a product's quality does not meet the standards, it creates a quality control report indicating that "improvement is needed" and sends it to the administrator. Based on this report, quality improvements are made.

[0566] (Application Example 1)

[0567] 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."

[0568] In modern smart cities, people's needs are becoming increasingly diverse, requiring personalized services. Meanwhile, store operators need efficient and accurate inventory and quality control, as well as improved customer satisfaction. This invention aims to efficiently solve these challenges and bring benefits to both users and stores within smart cities.

[0569] 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.

[0570] In this invention, the server includes means for acquiring user preference information and generating personalized beverage menus based on said preference information; means for receiving customer inquiries and generating responses based on said inquiries; means for analyzing acquired inventory data and generating reports for optimizing inventory management; means for acquiring market trend data from external sources and proposing marketing activities based on said data; means for collecting quality data from supply routes and generating quality control reports by analyzing said data; and means for automatically recognizing customer data using location information and efficiently providing personalized information. This makes it possible for customers to receive personalized services in cafes and stores within smart cities.

[0571] "User preference information" refers to information about the characteristics and taste preferences of individual users regarding beverages they like.

[0572] A "personalized beverage menu" refers to a selection of beverages optimized for each individual, generated based on the user's preference information.

[0573] "Means of receiving inquiries" refers to the method by which a server receives and processes questions and requests from customers.

[0574] A "report for optimizing inventory management" is a detailed report provided to analyze the inventory status of goods and materials and enable their efficient operation.

[0575] "Market trend data" refers to external data that shows current market trends and consumer preferences, and serves as indicator information for marketing activities.

[0576] "Collecting quality data from supply chains" means gathering quality information about the suppliers and distribution channels of goods and materials, and using that data to improve quality.

[0577] A "quality control report" is a document that provides information on maintaining and improving quality, based on the results obtained from analyzing quality data.

[0578] "Automatically recognizing customer data using location information" refers to a method that detects a customer's current location and dynamically provides relevant services and information to the user based on that information.

[0579] "Means for providing personalized information" refers to a mechanism for providing customized information tailored to the preferences and circumstances of each individual user.

[0580] The system for implementing this invention acquires user preference information and generates personalized beverage menus based on that information. The server stores the preference data acquired from the user terminal in a database and analyzes it. This makes it possible to present the most suitable menu for each user. When a user visits a store, the terminal uses location information services to link with the store's system and provides services tailored to the user's preference information and current location.

[0581] The server also assists with inventory management by collecting inventory data in real time and generating reports necessary for efficient management. Furthermore, it generates quality control reports by collecting and analyzing quality data from the supply chain. These reports can be used to improve quality and detect anomalies early. Marketing personnel are provided with campaign suggestions based on market trend data to support promotional activities.

[0582] This system was developed using the Python programming language, with PostgreSQL for database management, Pandas for data analysis, and React Native for the frontend. This results in a simple and scalable system architecture.

[0583] As a concrete example, if a user provides preference information such as "I like strong coffee" and visits a store, the system will recommend menu items such as espresso and ristretto. This process is achieved through prompts to a generative AI model, as shown below.

[0584] An example of a prompt message would be, "Generate a top menu that recommends strong coffee." This allows the user to enjoy an optimized coffee experience.

[0585] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0586] Step 1:

[0587] The server stores preference information received from the user's terminal in a database. The input is the user's preference data, and the output is the preference information stored in the database. This process receives preference information entered by the user through the terminal application and records it in the database.

[0588] Step 2:

[0589] When a user approaches a store, the terminal automatically connects with the store's system using location services. The input is the user's GPS location data, and the output is the connection status with the store's system. Based on the user's current location, it initiates communication with the nearest store's system and sends and receives the necessary data.

[0590] Step 3:

[0591] The server generates a personalized beverage menu based on acquired preference information. The input is the user's preference information stored in the database, and the output is the personalized beverage menu. The server analyzes the preference information and performs a process to list the most suitable beverage items.

[0592] Step 4:

[0593] The user terminal displays the personalized beverage menu received from the server on its screen. The input is the beverage menu provided by the server, and the output is the menu displayed on the user's screen. The terminal receives the data and visually presents it to the user.

[0594] Step 5:

[0595] The server acquires inventory management data in real time and analyzes it. The input is the latest inventory data, and the output is a report on the inventory status. The server checks inventory levels, detects shortages or surpluses, and generates reports.

[0596] Step 6:

[0597] The server collects quality data from the supply chain and generates quality control reports. The input is quality data from the supply chain, and the output is the quality control report. The server analyzes the data based on quality standards and generates a report indicating areas where quality maintenance or improvement is needed.

[0598] Step 7:

[0599] The server retrieves market trend data and proposes marketing campaigns based on it. The input is the latest market trend data, and the output is campaign proposal information. The server performs trend analysis and provides information to streamline relevant promotional activities.

[0600] Step 8:

[0601] The user terminal utilizes suggestions and information provided by the server as prompts for the generating AI model. The input is data generated by the server, and the output is text as a prompt for the AI ​​model. The user terminal uses this data to generate effective input for the AI ​​model.

[0602] 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.

[0603] This invention is a system that incorporates an emotion engine to recognize user emotions and adjust personalized beverage menus, improve customer service capabilities, and optimize marketing strategies. This system integrates and processes user preference information, emotion information, inventory data, market trend data, and supply chain quality data.

[0604] Menu adjustments based on emotion engine

[0605] The server uses an emotion engine to recognize the user's emotions based on voice and text data from the user's device. If the user is feeling relaxed, it adds relaxing beverages such as chamomile tea to the menu. A unique and personalized beverage menu is generated based on both emotions and preferences.

[0606] Emotion-based customer service

[0607] The server uses an emotion engine to generate emotionally appropriate responses to user inquiries. For example, if it determines that a user is stressed, it will generate a response suggesting a relaxing beverage or a special offer. This response is sent to the user's device, enabling an emotionally empathetic approach.

[0608] Emotionally conscious marketing strategies

[0609] The server analyzes user emotion data obtained by the emotion engine in combination with market trend data. This allows it to predict what kinds of promotions users are interested in and generate emotionally appealing marketing campaigns. For example, if a user is feeling happy, the server will plan campaign messages that emphasize that emotion.

[0610] Thus, the system of the present invention utilizes emotional technology to improve the customer experience and optimize operations. Through appropriate menu provision, customer service, and marketing measures that incorporate user emotions, it becomes possible to build deeper relationships with customers.

[0611] The following describes the processing flow.

[0612] Step 1:

[0613] Users access the system through their devices and input information via voice or text. This input includes information about orders and inquiries.

[0614] Step 2:

[0615] The server receives voice or text data from the user and uses an emotion engine to analyze the user's emotions. This analysis identifies the user's emotional state (e.g., stress, happiness, satisfaction, etc.).

[0616] Step 3:

[0617] The server combines analyzed emotional states with user preference information to create a personalized beverage menu. For example, if it determines that the user is seeking relaxation, it will suggest beverages such as chamomile tea.

[0618] Step 4:

[0619] The server sends a personalized beverage menu to the user's device. The user can then review the suggested menu on their device and proceed with their order.

[0620] Step 5:

[0621] If a user reviews the menu and has further questions, they will re-enter their questions through the terminal. For example, they might enter a question like, "What are some recommended ways to relax?"

[0622] Step 6:

[0623] The server receives a new inquiry from the user and generates an appropriate response using the emotion engine. It takes the user's emotions into consideration and recommends relaxing beverages or offers.

[0624] Step 7:

[0625] The server sends the generated response to the user's terminal. The user can then review the response on their terminal and take further action as needed.

[0626] Step 8:

[0627] The server integrates and analyzes user sentiment data and market trend data to formulate marketing campaigns. It plans promotional content tailored to the emotional state and notifies marketing personnel.

[0628] Step 9:

[0629] The server sends the marketing campaign information it has formulated to the marketing team's terminal, allowing them to prepare to launch an emotionally appealing campaign.

[0630] Through this series of processes, the system makes full use of emotion recognition technology and enables flexible responses that meet user needs.

[0631] (Example 2)

[0632] 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."

[0633] Traditional beverage delivery systems have struggled to provide services that take into account the emotional state of users, making it difficult to improve customer satisfaction. Furthermore, there has been a lack of emotion-based marketing strategies linked to market trends, resulting in ineffective promotions. Solving these challenges and enabling the provision of more personalized customer experiences is essential.

[0634] 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.

[0635] In this invention, the server includes means for acquiring emotion data from a user information terminal and recognizing emotions using an emotion engine based on said emotion data; means for adjusting a personalized beverage menu based on the recognized emotions and preference information; and means for generating emotion-appropriate responses to user inquiries. This enables the provision of services that take into account the user's emotional state and the optimization of marketing strategies.

[0636] "Emotional data" refers to information that indicates a user's emotional state, and is acquired through means such as voice and text.

[0637] An "emotion engine" is a system that uses generative AI models to analyze user emotions from data and recognize specific states.

[0638] "Preference information" refers to data about users' preferences and habits, and forms the basis for providing personalized services.

[0639] A "personalized beverage menu" is a list of beverages tailored to the user's mood and preferences, and offered individually.

[0640] A "marketing campaign" is a promotional activity planned based on a specific market strategy to attract customer attention.

[0641] "User interaction" is a general term for the communication and operations that take place between the user and the system, and is an important element for improving the user experience.

[0642] This invention utilizes an emotion engine to provide personalized services based on the user's emotional state. In the system's implementation, the user's terminal acquires voice and text data and transmits it to a server. On the server side, a generative AI model is used to analyze the data and recognize emotions. The generative AI model used here is, for example, based on natural language processing technology.

[0643] Specifically, data acquired from the user's device is transferred to a server via the internet. The server inputs the received data into an emotion engine and uses a generative AI model to estimate emotions. Once an emotion is recognized, it is combined with the user's preference information to generate a personalized beverage menu. In addition, appropriate responses are created to user inquiries based on their emotions and sent to the user's device.

[0644] As an example of how the system works, when a user feels the need to relax amidst their busy daily life, they can speak "I want to relax" into their device, and that voice data is sent to the server. The server analyzes the voice data and uses an emotion engine to recognize the emotion of relaxation. Based on the results, a menu is generated that suggests, for example, "chamomile tea," and sent to the user.

[0645] Examples of prompts include instructions such as, "Analyze the user's current emotional state and determine if they want to relax," or "Suggest a special offer that the user might be interested in."

[0646] In this way, it becomes possible to provide services tailored to the user's emotional state, thereby increasing user satisfaction.

[0647] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0648] Step 1:

[0649] The user's device collects voice or text data. Data is obtained when the user speaks into the device or types text. The input data includes information about the user's emotional state and preferences. This data forms the basis for subsequent analysis.

[0650] Step 2:

[0651] The user's device sends the collected voice or text data to the server. Specifically, the data is securely transferred to the server via the internet. This prepares the data for further analysis on the server side.

[0652] Step 3:

[0653] The server processes the received data and performs analysis using a generative AI model and an emotion engine. The AI ​​is instructed to "analyze the user's emotions" as a prompt. The input data is analyzed using the emotion recognition function of the generative AI model, and the user's emotional state is output. This emotion data is then used for subsequent personalization processes.

[0654] Step 4:

[0655] The server uses the results of emotion recognition and compares them with the user's preference information to generate a personalized beverage menu. This involves extracting the user's past preferences from a database and combining them with emotion data. As a result, the most suitable beverage menu for the user is output.

[0656] Step 5:

[0657] The server sends the generated beverage menu to the user's device. This communication process allows the user to review their personalized recommendations. Specifically, a notification of the recommendations is displayed on the device.

[0658] Step 6:

[0659] The server combines and analyzes emotional data and market information to generate marketing campaigns. This analysis determines promotional content that matches the user's emotional state. As a result, an effective marketing message is output.

[0660] Step 7:

[0661] Users review the menu and marketing information received on their devices and decide on their actual actions. Their reactions and feedback are collected again for future analysis. Specifically, users view suggestions and take actions such as placing orders.

[0662] (Application Example 2)

[0663] 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."

[0664] In today's brick-and-mortar stores, personalized product recommendations that cater to diverse user preferences and emotions are essential. However, traditional sales systems struggle to provide product recommendations that consider the user's emotional state, making it difficult to improve customer satisfaction. Furthermore, there is a need to develop methods to deliver an even deeper customer experience through an approach based not only on preferences but also on emotions.

[0665] 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.

[0666] In this invention, the server includes means for acquiring user preference information and generating personalized beverage menus based on said preference information; means for receiving customer inquiries and generating responses based on said inquiries; means for analyzing acquired inventory data and generating reports for optimizing inventory management; means for acquiring market trend data from external sources and proposing marketing campaigns based on said data; means for collecting quality data from the supply chain and generating quality control reports by analyzing said data; and means for recognizing user emotions and recommending products in physical stores based on said emotions. This enables personalized product recommendations that respond to user emotions, and is expected to improve the customer experience.

[0667] "User preference information" refers to data on the preferences and tastes that individual users have for specific products or services.

[0668] A "personalized beverage menu" refers to a list of drinks specially tailored to the individual user's preferences and requests.

[0669] "Customer inquiries" refer to questions or requests from users regarding products or services.

[0670] "Inventory data" refers to information about the quantity and condition of the goods held.

[0671] "Market trend data" refers to the latest information regarding consumer needs, preferences, and purchasing trends in the market.

[0672] A "supply chain" refers to the route by which raw materials and products are delivered from the supplier to the consumer.

[0673] "Quality data" refers to information about the quality of a product or service.

[0674] "User emotions" refers to the sensory or emotional responses that users experience in specific situations or environments.

[0675] "Recommending a product" refers to the act of suggesting a specific product to a user based on certain conditions or preferences.

[0676] The system for realizing this invention mainly consists of a server and user terminals. The server comprehensively processes preference information, emotional information, inventory data, market trend data, and supply chain quality data from the user terminals. Specifically, the "emotion_recognition" library is used for emotion recognition, and the "product_recommendation" module is used for product recommendations.

[0677] The user's device, such as a smartphone or smart glasses, acquires data in real time from its microphone and camera. This data is sent to a server, where an emotion engine analyzes the user's emotional state. Based on the results, products are personalized and recommended according to the user's mood and preferences.

[0678] For example, when a user visits a physical store, the device captures the user's voice and determines that the user's current mood is one of relaxation. In such cases, the server recommends products that promote relaxation, such as herbal teas or aromatherapy products. This product information is displayed on the device and provided to the user.

[0679] An example of a prompt to input into a generative AI model would be: "The user has provided emotional data for today. Based on this data, please suggest relaxing products available for purchase in stores." This makes it possible to provide users with a more personalized and consistent experience.

[0680] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0681] Step 1:

[0682] The user captures on-site data through the device's microphone and camera. Input consists of the user's voice and facial expressions, and the device converts this data into a digital format and sends it to the server. Output is digital data that the server can process.

[0683] Step 2:

[0684] The server analyzes emotions using the "emotion_recognition" library based on digital data received from the terminal. The input is digital data from the terminal, and the user's emotional state is identified through data processing. The output is data containing emotion labels (e.g., relaxed, stressed).

[0685] Step 3:

[0686] The server combines sentiment labels and user preference data, using the "product_recommendation" module to generate a list of products suitable for the user. The input consists of sentiment labels and preference data, and the algorithm generates a list of recommended products. The output is a list of recommended products.

[0687] Step 4:

[0688] The server sends the generated list of products to the user's device. At this stage, the input is a list of recommended products, and the output is product information displayed on the user's device. The device visually presents the information to the user and encourages them to make a purchase.

[0689] Step 5:

[0690] The user uses a terminal to select desired items from the recommended products and indicate their intention to purchase. The input is the user's selection, and the output is the purchase data sent to the server. The server receives this data and prepares to proceed to the next step.

[0691] 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.

[0692] 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.

[0693] 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.

[0694] [Fourth Embodiment]

[0695] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0696] 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.

[0697] 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).

[0698] 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.

[0699] 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.

[0700] 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).

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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.

[0705] 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.

[0706] 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.

[0707] 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".

[0708] This invention provides a system aimed at improving efficient operations and customer satisfaction in the coffee industry. The following describes the specific processing of the program of this system.

[0709] Menu Generation

[0710] The server retrieves user preference information from a database. Based on this, it generates a personalized beverage menu optimized for the user. For example, if the user has a preference for sweets, the server will suggest "caramel macchiato" as a special menu item. The generated menu is then displayed on the user's terminal.

[0711] Handling customer interactions

[0712] The server receives inquiries from users and generates responses appropriate to those inquiries. For example, if the server receives an inquiry such as "What do you recommend?", it creates a menu that reflects the user's preferences and returns it as a response. The response is sent to the user's terminal for the user to review.

[0713] Optimizing inventory management

[0714] The server retrieves and analyzes the latest inventory data from the inventory management system. Based on the analysis, it determines whether the inventory situation is "sufficient" or "insufficient" and generates a report. This report is sent to the store manager's terminal, enabling efficient inventory management.

[0715] Optimizing marketing strategy

[0716] The server collects market trend data from external data sources and analyzes the data to propose marketing campaigns. For example, during the summer months, it might suggest an "iced coffee campaign." This information is then sent to marketing personnel's terminals and used for promotional activities.

[0717] Improving quality control

[0718] The server collects and analyzes quality data from the supply chain. If there are quality issues, the server generates a quality control report indicating that "improvement is needed" and sends it to the administrator's terminal. This helps maintain overall quality and contributes to improved customer satisfaction.

[0719] Through the program processing described above, the present invention aims to unify various operations in the coffee industry, thereby improving customer experience and operational efficiency. This system enables flexible responses to user needs, thereby enhancing a competitive advantage within the industry.

[0720] The following describes the processing flow.

[0721] Step 1:

[0722] The server retrieves preference information from the database based on the user's profile. This process references past purchase history and entered preferences.

[0723] Step 2:

[0724] The server selects special menu options from the basic beverage menu based on the user's preference information. For example, based on the information that the user "likes sweets," it might select "Caramel Macchiato."

[0725] Step 3:

[0726] The server selects menu items and sends them to the user's device as a personalized beverage menu. The user can then view this menu on their device.

[0727] Step 4:

[0728] The user enters their inquiry through their device. For example, they might enter a question like, "What do you recommend?"

[0729] Step 5:

[0730] The server receives inquiries from users and generates corresponding responses. It prepares accurate responses based on the corresponding menus and information.

[0731] Step 6:

[0732] The server sends the generated response to the user's terminal. The user can then view the returned response on their terminal.

[0733] Step 7:

[0734] The server collects current inventory data from the inventory management system. Quantity and demand forecast data for each product are also checked here.

[0735] Step 8:

[0736] The system analyzes inventory data collected by the server to determine whether there is sufficient or insufficient inventory. Based on the inventory status, it sets appropriate management policies.

[0737] Step 9:

[0738] The server generates an inventory report based on the analysis results and sends it to the store manager's terminal. This allows the manager to understand the inventory situation and take necessary actions.

[0739] Step 10:

[0740] The server retrieves market trend data from external data sources. This data includes current consumer behavior and sales trends.

[0741] Step 11:

[0742] The server analyzes market trend data and proposes effective marketing campaigns. For example, it might plan a campaign tailored to the increased demand for iced coffee during the summer months.

[0743] Step 12:

[0744] The server sends the proposed marketing campaign to the marketing team's terminal, and the team then prepares to implement the campaign.

[0745] Step 13:

[0746] The server collects and analyzes quality data from the supply chain. This data includes product ratings and return information.

[0747] Step 14:

[0748] The server generates a quality control report based on quality data. If there are quality issues, the report will specify what needs to be improved.

[0749] Step 15:

[0750] The server generates a quality control report which is then sent to the administrator's terminal, and the administrator uses that report to implement quality improvement measures.

[0751] (Example 1)

[0752] 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".

[0753] The coffee industry demands services tailored to individual customer preferences, efficient inventory management, effective marketing based on trends, and rapid responses to quality improvements. However, traditional systems have struggled to integrate and manage these elements, resulting in insufficient improvements in customer satisfaction and operational efficiency.

[0754] 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.

[0755] In this invention, the server includes means for collecting user preference information and generating personalized beverage provision information using generation technology that uses said preference information as input; means for receiving customer inquiries and generating automated responses based on said inquiries; and means for analyzing acquired inventory information and generating notifications to optimize inventory management. This enables the provision of services tailored to user preferences, effective inventory management, and responses based on customer needs.

[0756] "Preference information" refers to data that indicates the specific preferences and interests of individual customers.

[0757] "Generative technology" refers to techniques for automatically constructing specialized information based on collected data.

[0758] "Beverage provision information" refers to information about beverages selected or recommended according to customer preferences.

[0759] An "inquiry" refers to a communication that includes questions or requests from customers.

[0760] "Inventory information" refers to data regarding the quantity and condition of products currently held.

[0761] A "notification" is a digital message sent to inform someone of a specific situation or piece of information.

[0762] "Trends" refer to information that indicates trends that change over time, such as market conditions and consumer preferences.

[0763] A "sales strategy" is a plan of marketing activities formulated to achieve a specific goal.

[0764] "Quality information" refers to data related to the quality of a product or service.

[0765] A "supply chain" is a system that includes a series of processes from the time a product or service reaches the end consumer.

[0766] This invention is a system designed to improve operational efficiency and customer satisfaction in the coffee industry. The specific implementation details are described below.

[0767] The server, which is the heart of the system, integrates and executes multiple functions. First, the server retrieves user preference information from a database. This database uses a common relational database management system (e.g., MySQL). The server inputs the retrieved preference information as prompts into a generative AI model (e.g., a natural language generation model) to generate personalized beverage recommendation information. This generated information is sent to the user terminal (e.g., a smartphone app) and displayed visually on the UI.

[0768] For example, if the user's preference data includes "likes sweets," the input prompt to the generating AI model would be "User preference: likes sweets." As a result, the server generates a list including beverages such as "caramel macchiato" and presents it to the user's terminal.

[0769] Next, the server uses natural language processing techniques (e.g., NLP libraries) through a chatbot interface to generate responses to user inquiries. For example, if a user asks "What do you recommend?", the server refers to preference information and returns a response using appropriate beverage recommendations.

[0770] The server also retrieves inventory information from the ERP system and analyzes real-time inventory status using a Python data analysis library (e.g., Pandas). Based on the analysis results, notifications are sent to store managers' terminals to optimize inventory management.

[0771] Furthermore, the server collects external market trend information and analyzes it using machine learning libraries (e.g., scikit-learn) to propose sales strategies tailored to the season and trends. These proposals are then sent as notifications to marketing personnel's terminals.

[0772] Finally, the server collects quality information from the supply chain and analyzes it using quality control software (e.g., Six Sigma tool). If the analysis reveals areas that do not meet quality standards, it sends a notification to the administrator stating that "improvement is needed" to promote quality improvement.

[0773] Thus, this system integrates multiple functions and provides adaptive and efficient services based on user needs.

[0774] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0775] Step 1:

[0776] The server retrieves user preference information from the database. Given a user ID as input, it uses an SQL query to extract preference information (e.g., "likes sweets") from the database. This preference information will be used in subsequent processing steps.

[0777] Step 2:

[0778] The server inputs the extracted preference information as a prompt into the generative AI model. It generates a prompt sentence (e.g., "User preference: Likes sweets") and inputs it into the generative AI model. Based on the prompt, this model outputs personalized beverage suggestions (e.g., caramel macchiato).

[0779] Step 3:

[0780] The server sends the suggestions generated by the AI ​​model to the user's terminal. The outputted beverage suggestions are displayed on the user's smartphone or tablet application, allowing the user to visually confirm them.

[0781] Step 4:

[0782] Users review beverage suggestions via their device and, if possible, use the chat function to make additional inquiries (e.g., "What do you recommend?"). The inquiry is then sent to the server.

[0783] Step 5:

[0784] The server receives inquiries from users and analyzes their content using natural language processing technology. Based on the analysis, it uses previously obtained preference information and beverage suggestions to generate an appropriate response (e.g., recommended menu items) and sends it to the user's terminal.

[0785] Step 6:

[0786] The server retrieves inventory information from the inventory management system and analyzes the data using Pandas. Based on the analysis, it determines whether the inventory is "sufficient" or "insufficient," and generates an inventory management report based on that. This report is then sent to the store manager's terminal.

[0787] Step 7:

[0788] The server retrieves market trend information from an external database and analyzes it using machine learning algorithms. Based on the analysis results, it generates proposals for marketing campaigns (e.g., a summer iced coffee campaign) and notifies marketing personnel.

[0789] Step 8:

[0790] The server collects quality information from the supply chain and analyzes it using quality analysis tools. If a product's quality does not meet the standards, it creates a quality control report indicating that "improvement is needed" and sends it to the administrator. Based on this report, quality improvements are made.

[0791] (Application Example 1)

[0792] 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".

[0793] In modern smart cities, people's needs are becoming increasingly diverse, requiring personalized services. Meanwhile, store operators need efficient and accurate inventory and quality control, as well as improved customer satisfaction. This invention aims to efficiently solve these challenges and bring benefits to both users and stores within smart cities.

[0794] 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.

[0795] In this invention, the server includes means for acquiring user preference information and generating personalized beverage menus based on said preference information; means for receiving customer inquiries and generating responses based on said inquiries; means for analyzing acquired inventory data and generating reports for optimizing inventory management; means for acquiring market trend data from external sources and proposing marketing activities based on said data; means for collecting quality data from supply routes and generating quality control reports by analyzing said data; and means for automatically recognizing customer data using location information and efficiently providing personalized information. This makes it possible for customers to receive personalized services in cafes and stores within smart cities.

[0796] "User preference information" refers to information about the characteristics and taste preferences of individual users regarding beverages they like.

[0797] A "personalized beverage menu" refers to a selection of beverages optimized for each individual, generated based on the user's preference information.

[0798] "Means of receiving inquiries" refers to the method by which a server receives and processes questions and requests from customers.

[0799] A "report for optimizing inventory management" is a detailed report provided to analyze the inventory status of goods and materials and enable their efficient operation.

[0800] "Market trend data" refers to external data that shows current market trends and consumer preferences, and serves as indicator information for marketing activities.

[0801] "Collecting quality data from supply chains" means gathering quality information about the suppliers and distribution channels of goods and materials, and using that data to improve quality.

[0802] A "quality control report" is a document that provides information on maintaining and improving quality, based on the results obtained from analyzing quality data.

[0803] "Automatically recognizing customer data using location information" refers to a method that detects a customer's current location and dynamically provides relevant services and information to the user based on that information.

[0804] "Means for providing personalized information" refers to a mechanism for providing customized information tailored to the preferences and circumstances of each individual user.

[0805] The system for implementing this invention acquires user preference information and generates personalized beverage menus based on that information. The server stores the preference data acquired from the user terminal in a database and analyzes it. This makes it possible to present the most suitable menu for each user. When a user visits a store, the terminal uses location information services to link with the store's system and provides services tailored to the user's preference information and current location.

[0806] The server also assists with inventory management by collecting inventory data in real time and generating reports necessary for efficient management. Furthermore, it generates quality control reports by collecting and analyzing quality data from the supply chain. These reports can be used to improve quality and detect anomalies early. Marketing personnel are provided with campaign suggestions based on market trend data to support promotional activities.

[0807] This system was developed using the Python programming language, with PostgreSQL for database management, Pandas for data analysis, and React Native for the frontend. This results in a simple and scalable system architecture.

[0808] As a concrete example, if a user provides preference information such as "I like strong coffee" and visits a store, the system will recommend menu items such as espresso and ristretto. This process is achieved through prompts to a generative AI model, as shown below.

[0809] An example of a prompt message would be, "Generate a top menu that recommends strong coffee." This allows the user to enjoy an optimized coffee experience.

[0810] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0811] Step 1:

[0812] The server stores preference information received from the user's terminal in a database. The input is the user's preference data, and the output is the preference information stored in the database. This process receives preference information entered by the user through the terminal application and records it in the database.

[0813] Step 2:

[0814] When a user approaches a store, the terminal automatically connects with the store's system using location services. The input is the user's GPS location data, and the output is the connection status with the store's system. Based on the user's current location, it initiates communication with the nearest store's system and sends and receives the necessary data.

[0815] Step 3:

[0816] The server generates a personalized beverage menu based on acquired preference information. The input is the user's preference information stored in the database, and the output is the personalized beverage menu. The server analyzes the preference information and performs a process to list the most suitable beverage items.

[0817] Step 4:

[0818] The user terminal displays the personalized beverage menu received from the server on its screen. The input is the beverage menu provided by the server, and the output is the menu displayed on the user's screen. The terminal receives the data and visually presents it to the user.

[0819] Step 5:

[0820] The server acquires inventory management data in real time and analyzes it. The input is the latest inventory data, and the output is a report on the inventory status. The server checks inventory levels, detects shortages or surpluses, and generates reports.

[0821] Step 6:

[0822] The server collects quality data from the supply chain and generates quality control reports. The input is quality data from the supply chain, and the output is the quality control report. The server analyzes the data based on quality standards and generates a report indicating areas where quality maintenance or improvement is needed.

[0823] Step 7:

[0824] The server retrieves market trend data and proposes marketing campaigns based on it. The input is the latest market trend data, and the output is campaign proposal information. The server performs trend analysis and provides information to streamline relevant promotional activities.

[0825] Step 8:

[0826] The user terminal utilizes suggestions and information provided by the server as prompts for the generating AI model. The input is data generated by the server, and the output is text as a prompt for the AI ​​model. The user terminal uses this data to generate effective input for the AI ​​model.

[0827] 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.

[0828] This invention is a system that incorporates an emotion engine to recognize user emotions and adjust personalized beverage menus, improve customer service capabilities, and optimize marketing strategies. This system integrates and processes user preference information, emotion information, inventory data, market trend data, and supply chain quality data.

[0829] Menu adjustments based on emotion engine

[0830] The server uses an emotion engine to recognize the user's emotions based on voice and text data from the user's device. If the user is feeling relaxed, it adds relaxing beverages such as chamomile tea to the menu. A unique and personalized beverage menu is generated based on both emotions and preferences.

[0831] Emotion-based customer service

[0832] The server uses an emotion engine to generate emotionally appropriate responses to user inquiries. For example, if it determines that a user is stressed, it will generate a response suggesting a relaxing beverage or a special offer. This response is sent to the user's device, enabling an emotionally empathetic approach.

[0833] Emotionally conscious marketing strategies

[0834] The server analyzes user emotion data obtained by the emotion engine in combination with market trend data. This allows it to predict what kinds of promotions users are interested in and generate emotionally appealing marketing campaigns. For example, if a user is feeling happy, the server will plan campaign messages that emphasize that emotion.

[0835] Thus, the system of the present invention utilizes emotional technology to improve the customer experience and optimize operations. Through appropriate menu provision, customer service, and marketing measures that incorporate user emotions, it becomes possible to build deeper relationships with customers.

[0836] The following describes the processing flow.

[0837] Step 1:

[0838] Users access the system through their devices and input information via voice or text. This input includes information about orders and inquiries.

[0839] Step 2:

[0840] The server receives voice or text data from the user and uses an emotion engine to analyze the user's emotions. This analysis identifies the user's emotional state (e.g., stress, happiness, satisfaction, etc.).

[0841] Step 3:

[0842] The server combines analyzed emotional states with user preference information to create a personalized beverage menu. For example, if it determines that the user is seeking relaxation, it will suggest beverages such as chamomile tea.

[0843] Step 4:

[0844] The server sends a personalized beverage menu to the user's device. The user can then review the suggested menu on their device and proceed with their order.

[0845] Step 5:

[0846] If a user reviews the menu and has further questions, they will re-enter their questions through the terminal. For example, they might enter a question like, "What are some recommended ways to relax?"

[0847] Step 6:

[0848] The server receives a new inquiry from the user and generates an appropriate response using the emotion engine. It takes the user's emotions into consideration and recommends relaxing beverages or offers.

[0849] Step 7:

[0850] The server sends the generated response to the user's terminal. The user can then review the response on their terminal and take further action as needed.

[0851] Step 8:

[0852] The server integrates and analyzes user sentiment data and market trend data to formulate marketing campaigns. It plans promotional content tailored to the emotional state and notifies marketing personnel.

[0853] Step 9:

[0854] The server sends the marketing campaign information it has formulated to the marketing team's terminal, allowing them to prepare to launch an emotionally appealing campaign.

[0855] Through this series of processes, the system makes full use of emotion recognition technology and enables flexible responses that meet user needs.

[0856] (Example 2)

[0857] 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".

[0858] Traditional beverage delivery systems have struggled to provide services that take into account the emotional state of users, making it difficult to improve customer satisfaction. Furthermore, there has been a lack of emotion-based marketing strategies linked to market trends, resulting in ineffective promotions. Solving these challenges and enabling the provision of more personalized customer experiences is essential.

[0859] 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.

[0860] In this invention, the server includes means for acquiring emotion data from a user information terminal and recognizing emotions using an emotion engine based on said emotion data; means for adjusting a personalized beverage menu based on the recognized emotions and preference information; and means for generating emotion-appropriate responses to user inquiries. This enables the provision of services that take into account the user's emotional state and the optimization of marketing strategies.

[0861] "Emotional data" refers to information that indicates a user's emotional state, and is acquired through means such as voice and text.

[0862] An "emotion engine" is a system that uses generative AI models to analyze user emotions from data and recognize specific states.

[0863] "Preference information" refers to data about users' preferences and habits, and forms the basis for providing personalized services.

[0864] A "personalized beverage menu" is a list of beverages tailored to the user's mood and preferences, and offered individually.

[0865] A "marketing campaign" is a promotional activity planned based on a specific market strategy to attract customer attention.

[0866] "User interaction" is a general term for the communication and operations that take place between the user and the system, and is an important element for improving the user experience.

[0867] This invention utilizes an emotion engine to provide personalized services based on the user's emotional state. In the system's implementation, the user's terminal acquires voice and text data and transmits it to a server. On the server side, a generative AI model is used to analyze the data and recognize emotions. The generative AI model used here is, for example, based on natural language processing technology.

[0868] Specifically, data acquired from the user's device is transferred to a server via the internet. The server inputs the received data into an emotion engine and uses a generative AI model to estimate emotions. Once an emotion is recognized, it is combined with the user's preference information to generate a personalized beverage menu. In addition, appropriate responses are created to user inquiries based on their emotions and sent to the user's device.

[0869] As an example of how the system works, when a user feels the need to relax amidst their busy daily life, they can speak "I want to relax" into their device, and that voice data is sent to the server. The server analyzes the voice data and uses an emotion engine to recognize the emotion of relaxation. Based on the results, a menu is generated that suggests, for example, "chamomile tea," and sent to the user.

[0870] Examples of prompts include instructions such as, "Analyze the user's current emotional state and determine if they want to relax," or "Suggest a special offer that the user might be interested in."

[0871] In this way, it becomes possible to provide services tailored to the user's emotional state, thereby increasing user satisfaction.

[0872] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0873] Step 1:

[0874] The user's device collects voice or text data. Data is obtained when the user speaks into the device or types text. The input data includes information about the user's emotional state and preferences. This data forms the basis for subsequent analysis.

[0875] Step 2:

[0876] The user's device sends the collected voice or text data to the server. Specifically, the data is securely transferred to the server via the internet. This prepares the data for further analysis on the server side.

[0877] Step 3:

[0878] The server processes the received data and performs analysis using a generative AI model and an emotion engine. The AI ​​is instructed to "analyze the user's emotions" as a prompt. The input data is analyzed using the emotion recognition function of the generative AI model, and the user's emotional state is output. This emotion data is then used for subsequent personalization processes.

[0879] Step 4:

[0880] The server uses the results of emotion recognition and compares them with the user's preference information to generate a personalized beverage menu. This involves extracting the user's past preferences from a database and combining them with emotion data. As a result, the most suitable beverage menu for the user is output.

[0881] Step 5:

[0882] The server sends the generated beverage menu to the user's device. This communication process allows the user to review their personalized recommendations. Specifically, a notification of the recommendations is displayed on the device.

[0883] Step 6:

[0884] The server combines and analyzes emotional data and market information to generate marketing campaigns. This analysis determines promotional content that matches the user's emotional state. As a result, an effective marketing message is output.

[0885] Step 7:

[0886] Users review the menu and marketing information received on their devices and decide on their actual actions. Their reactions and feedback are collected again for future analysis. Specifically, users view suggestions and take actions such as placing orders.

[0887] (Application Example 2)

[0888] 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".

[0889] In today's brick-and-mortar stores, personalized product recommendations that cater to diverse user preferences and emotions are essential. However, traditional sales systems struggle to provide product recommendations that consider the user's emotional state, making it difficult to improve customer satisfaction. Furthermore, there is a need to develop methods to deliver an even deeper customer experience through an approach based not only on preferences but also on emotions.

[0890] 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.

[0891] In this invention, the server includes means for acquiring user preference information and generating personalized beverage menus based on said preference information; means for receiving customer inquiries and generating responses based on said inquiries; means for analyzing acquired inventory data and generating reports for optimizing inventory management; means for acquiring market trend data from external sources and proposing marketing campaigns based on said data; means for collecting quality data from the supply chain and generating quality control reports by analyzing said data; and means for recognizing user emotions and recommending products in physical stores based on said emotions. This enables personalized product recommendations that respond to user emotions, and is expected to improve the customer experience.

[0892] "User preference information" refers to data on the preferences and tastes that individual users have for specific products or services.

[0893] A "personalized beverage menu" refers to a list of drinks specially tailored to the individual user's preferences and requests.

[0894] "Customer inquiries" refer to questions or requests from users regarding products or services.

[0895] "Inventory data" refers to information about the quantity and condition of the goods held.

[0896] "Market trend data" refers to the latest information regarding consumer needs, preferences, and purchasing trends in the market.

[0897] A "supply chain" refers to the route by which raw materials and products are delivered from the supplier to the consumer.

[0898] "Quality data" refers to information about the quality of a product or service.

[0899] "User emotions" refers to the sensory or emotional responses that users experience in specific situations or environments.

[0900] "Recommending a product" refers to the act of suggesting a specific product to a user based on certain conditions or preferences.

[0901] The system for realizing this invention mainly consists of a server and user terminals. The server comprehensively processes preference information, emotional information, inventory data, market trend data, and supply chain quality data from the user terminals. Specifically, the "emotion_recognition" library is used for emotion recognition, and the "product_recommendation" module is used for product recommendations.

[0902] The user's device, such as a smartphone or smart glasses, acquires data in real time from its microphone and camera. This data is sent to a server, where an emotion engine analyzes the user's emotional state. Based on the results, products are personalized and recommended according to the user's mood and preferences.

[0903] For example, when a user visits a physical store, the device captures the user's voice and determines that the user's current mood is one of relaxation. In such cases, the server recommends products that promote relaxation, such as herbal teas or aromatherapy products. This product information is displayed on the device and provided to the user.

[0904] An example of a prompt to input into a generative AI model would be: "The user has provided emotional data for today. Based on this data, please suggest relaxing products available for purchase in stores." This makes it possible to provide users with a more personalized and consistent experience.

[0905] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0906] Step 1:

[0907] The user captures on-site data through the device's microphone and camera. Input consists of the user's voice and facial expressions, and the device converts this data into a digital format and sends it to the server. Output is digital data that the server can process.

[0908] Step 2:

[0909] The server analyzes emotions using the "emotion_recognition" library based on digital data received from the terminal. The input is digital data from the terminal, and the user's emotional state is identified through data processing. The output is data containing emotion labels (e.g., relaxed, stressed).

[0910] Step 3:

[0911] The server combines sentiment labels and user preference data, using the "product_recommendation" module to generate a list of products suitable for the user. The input consists of sentiment labels and preference data, and the algorithm generates a list of recommended products. The output is a list of recommended products.

[0912] Step 4:

[0913] The server sends the generated list of products to the user's device. At this stage, the input is a list of recommended products, and the output is product information displayed on the user's device. The device visually presents the information to the user and encourages them to make a purchase.

[0914] Step 5:

[0915] The user uses a terminal to select desired items from the recommended products and indicate their intention to purchase. The input is the user's selection, and the output is the purchase data sent to the server. The server receives this data and prepares to proceed to the next step.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] 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.

[0921] 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.

[0922] 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.

[0923] 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.

[0924] 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."

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] 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.

[0932] 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.

[0933] 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.

[0934] 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.

[0935] 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.

[0936] 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.

[0937] The following is further disclosed regarding the embodiments described above.

[0938] (Claim 1)

[0939] A means for acquiring user preference information and generating personalized beverage menus based on said preference information,

[0940] A means for receiving customer inquiries and generating responses based on those inquiries,

[0941] A means of analyzing acquired inventory data and generating reports to optimize inventory management,

[0942] A means of obtaining market trend data from external sources and proposing marketing campaigns based on that data,

[0943] A means for collecting quality data from the supply chain and generating a quality control report by analyzing the data,

[0944] A system that includes this.

[0945] (Claim 2)

[0946] The system according to claim 1, which selects special menu items based on user preference information.

[0947] (Claim 3)

[0948] The system according to claim 1, which generates a quality control report that suggests improvement when the quality evaluation of the supply chain is low.

[0949] "Example 1"

[0950] (Claim 1)

[0951] A means for collecting user preference information and generating personalized beverage provision information using generation technology that uses said preference information as input,

[0952] A means for receiving customer inquiries and generating automated responses based on those inquiries,

[0953] A means for analyzing acquired inventory information and generating notifications to optimize inventory management,

[0954] A means of collecting market trend information from external sources and proposing sales strategies by analyzing that information,

[0955] A means for collecting quality information from the supply chain and generating quality control notifications by analyzing said information,

[0956] A system that includes this.

[0957] (Claim 2)

[0958] The system according to claim 1, which selects specialized information to be provided based on user preference information.

[0959] (Claim 3)

[0960] The system according to claim 1, which generates a quality control notification indicating improvement when the quality evaluation of the supply chain falls below a standard.

[0961] "Application Example 1"

[0962] (Claim 1)

[0963] A means for acquiring user preference information and generating personalized beverage menus based on said preference information,

[0964] A means for receiving customer inquiries and generating responses based on those inquiries,

[0965] A means of analyzing acquired inventory data and generating reports to optimize inventory management,

[0966] A means of obtaining market trend data from external sources and proposing marketing activities based on that data,

[0967] A means for collecting quality data from supply routes and generating a quality control report by analyzing said data,

[0968] A means to automatically recognize customer data using location information and efficiently provide personalized information,

[0969] A system that includes this.

[0970] (Claim 2)

[0971] The system according to claim 1, which selects special menu items based on user preference information and location information.

[0972] (Claim 3)

[0973] The system according to claim 1, which generates a quality control report suggesting improvement when the quality evaluation of the supply route is low, and further generates a report that improves service quality through location coordination with the user.

[0974] "Example 2 of combining an emotion engine"

[0975] (Claim 1)

[0976] A means for acquiring emotion data from a user information terminal and recognizing emotions using an emotion engine based on said emotion data,

[0977] A means of adjusting a personalized beverage menu based on recognized emotional and preference information,

[0978] A means of generating emotionally appropriate responses to user inquiries,

[0979] A method for proposing emotionally appealing marketing campaigns that analyze external market information and combine it with sentiment data,

[0980] A means for transmitting the aforementioned response to a user information terminal via a communication device and constructing an emotion-focused user interaction,

[0981] A system that includes this.

[0982] (Claim 2)

[0983] The system according to claim 1, which optimizes beverage recommendations based on user emotional information.

[0984] (Claim 3)

[0985] The system according to claim 1, which generates campaigns to improve psychological satisfaction based on emotional patterns shown by user data.

[0986] "Application example 2 when combining with an emotional engine"

[0987] (Claim 1)

[0988] A means for acquiring user preference information and generating personalized beverage menus based on said preference information,

[0989] A means for receiving customer inquiries and generating responses based on those inquiries,

[0990] A means of analyzing acquired inventory data and generating reports to optimize inventory management,

[0991] A means of obtaining market trend data from external sources and proposing marketing campaigns based on that data,

[0992] A means for collecting quality data from the supply chain and generating a quality control report by analyzing the data,

[0993] A means of recognizing user emotions and recommending products in physical stores based on those emotions,

[0994] A system that includes this.

[0995] (Claim 2)

[0996] The system according to claim 1, which selects special product items based on user preference information and emotional information.

[0997] (Claim 3)

[0998] The system according to claim 1, which generates a quality control report that suggests improvement when the quality evaluation of the supply chain is low. [Explanation of symbols]

[0999] 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. A means for acquiring user preference information and generating personalized beverage menus based on said preference information, A means for receiving customer inquiries and generating responses based on those inquiries, A means of analyzing acquired inventory data and generating reports to optimize inventory management, A means of obtaining market trend data from external sources and proposing marketing activities based on that data, A means for collecting quality data from supply routes and generating a quality control report by analyzing said data, A means to automatically recognize customer data using location information and efficiently provide personalized information, A system that includes this.

2. The system according to claim 1, which selects special menu items based on user preference information and location information.

3. The system according to claim 1, which generates a quality control report suggesting improvement when the quality evaluation of the supply route is low, and further generates a report that improves service quality through location coordination with the user.

Images