system

Abstract

We provide the system. [Solution] A data acquisition method for obtaining data on unsold products, A generation means for generating cooking procedures based on the acquired data, A presentation means for presenting the generated cooking procedure, A means of receiving feedback from customers, An improvement means for improving the generation means based on the evaluation, 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 method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 a supermarket, the occurrence of unsold products has become a problem, such as an increase in disposal costs and food loss. On the consumer side, there is a large burden when considering daily meal menus, and they are troubled by the monotony of cooking. In such a situation, it is required to provide value to both by making new food proposals to consumers while effectively utilizing unsold products.

Means for Solving the Problems

[0005] This invention provides a system that acquires data on unsold products in real time and generates cooking instructions based on that data. Specifically, a data acquisition means acquires data on unsold products, and a generation means generates cooking instructions that will attract customers' attention based on that data. The generated cooking instructions are then displayed on in-store display devices and information terminals by a presentation means, and customer evaluations are received by a feedback receiving means. Finally, the generation means is improved based on the received evaluations to continuously improve the system. This makes it possible to simultaneously achieve effective utilization of unsold products and improved consumer satisfaction.

[0006] "Unsold product data" refers to data that shows information about products that remain unsold within a specific period, and includes product name, category, inventory quantity, and expiration date.

[0007] A "data acquisition method" is an element that has the function of collecting unsold product data in real time, and acquires information in conjunction with an inventory management system.

[0008] A "generation method" is an element that has the function of creating new cooking procedures based on acquired unsold product data, and typically uses a generation AI model.

[0009] "Presentation means" refers to elements that have the function of visually displaying the generated cooking procedure to the customer, and includes in-store display devices and information terminals.

[0010] A "feedback receiving mechanism" is an element that has the function of receiving ratings and comments provided by customers, and accepts input from users through an interface.

[0011] "Improvement measures" are elements that have the function of improving the performance and accuracy of the generation method based on the customer feedback received. [Brief explanation of the drawing]

[0012] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] 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.

[0016] 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.

[0017] 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, and the like.

[0018] In the following embodiments, a labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] To implement this invention, a system is constructed in which three entities—a server, a terminal, and a user—work in cooperation.

[0034] First, the server connects with the inventory management system to collect data on unsold products in real time. This provides information on the current inventory status and product expiration dates. Based on this data, the server uses a generative AI model to automatically generate cooking instructions that utilize the unsold products. For example, if there is a large amount of tomatoes and cheese in stock, it can generate a cooking instruction for "Caprese Salad with Tomatoes and Cheese."

[0035] Next, the terminal receives cooking instructions sent from the server and displays them on in-store display devices and the customer's smartphone app. The in-store display devices use visually-oriented presentations to attract the consumer's attention. The smartphone app provides detailed recipe information for users to refer to at any time, displaying the necessary ingredients and cooking steps.

[0036] Users can review the provided cooking instructions and purchase the necessary ingredients. After trying the recipe at home, users can submit feedback via their device. This feedback includes evaluations of the taste of the dish and the difficulty of the process.

[0037] Finally, the server analyzes the collected feedback data and uses it as training data to improve the generated AI model. This improves the overall accuracy of the system so that the cooking instructions generated in the future are more in line with customer preferences. By repeating this cycle, it is possible to sustainably achieve effective utilization of unsold products and improved customer satisfaction.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The server accesses the inventory management system via an API to retrieve inventory data for unsold items and other necessary products. This data includes important information such as product name, category, inventory quantity, and expiration date.

[0041] Step 2:

[0042] The server inputs the acquired unsold product data into a generating AI model. This model uses natural language processing and machine learning techniques to generate appropriate cooking procedures based on combinations of unsold products. For example, it can devise new menus using leftover ingredients.

[0043] Step 3:

[0044] The server sends the generated cooking instructions to the terminal. These instructions include a list of required ingredients, cooking time, and step-by-step cooking instructions.

[0045] Step 4:

[0046] The terminal displays cooking instructions received from the server on digital signage in the store and on a smartphone app. The digital signage shows recipes with eye-catching images and text, while the smartphone app allows users to check details and save the recipes.

[0047] Step 5:

[0048] Users can review the presented cooking instructions and add the necessary ingredients to their cart if they are interested. Furthermore, users can try cooking at home based on the recipes displayed on the smartphone app.

[0049] Step 6:

[0050] After a user tries a recipe, they send feedback about it via their device. This feedback includes information such as the difficulty level of the recipe, the taste, and suggestions for improvement.

[0051] Step 7:

[0052] The server stores and analyzes the collected feedback data in a database. This data is used to retrain the generative AI model, improving the accuracy of future recipe suggestions. The goal is to generate new recipes that are better suited to the user's preferences based on the feedback.

[0053] (Example 1)

[0054] 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."

[0055] The increasing amount of unsold goods presents significant challenges, including inventory management, waste management, and the resulting increase in costs. Furthermore, a lack of recipe suggestions tailored to consumer preferences is hindering effective product consumption. Therefore, there is a need for a system that effectively utilizes inventory while automatically generating cooking suggestions that meet consumer needs.

[0056] 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.

[0057] In this invention, the server includes a data collection means for acquiring data on unsold products, a generation means using artificial intelligence to automatically generate cooking procedures based on the data, and a means for presenting the generated cooking procedures via an information display means. This enables the effective use of inventory and improved consumer satisfaction by collecting data on unsold products in real time and efficiently generating and providing cooking procedures based on that data.

[0058] "Unsold goods" refer to products that have not been sold in the market and remain as inventory, and which may be discarded.

[0059] "Data collection means" refers to functions and devices for acquiring and aggregating information about inventory and unsold goods.

[0060] "Generation means" refers to a function or system that uses artificial intelligence to automatically generate cooking procedures from the collected data.

[0061] "Information display means" refers to devices or software that visually present the generated cooking instructions to consumers.

[0062] "Feedback collection methods" refer to functions or devices for receiving feedback, evaluations, and other reactions from consumers.

[0063] "Information analysis and learning tools" refer to functions and systems for analyzing feedback and improving or adjusting the accuracy of generation tools.

[0064] This system is built around three main components: a server, terminals, and users, each working in cooperation with the others. First, the server integrates with the inventory management system to collect real-time data on unsold goods. Inventory management software is used for this data collection, obtaining information on the inventory status and expiration dates of unsold items. Specifically, the server retrieves this information from a database and utilizes artificial intelligence technology to process it.

[0065] The server uses a generative AI model to automatically generate cooking instructions from collected data on unsold products. This AI model includes models that utilize natural language processing techniques. Specific examples of the AI ​​models used include commonly used language generation models, which have the ability to generate new content based on input data. As an example of a specific cooking instruction to be generated, if the prompt message is "There are 50 tomatoes and 20 packs of cheese in stock," it is possible to automatically generate a recipe for "Caprese salad with tomatoes and cheese."

[0066] Next, the terminal receives cooking instructions transmitted from the server and displays the suggested recipe on in-store display devices and the consumer's smartphone application. The in-store display devices are expected to utilize a digital signage system to provide visually appealing information. The smartphone application displays detailed recipe information, allowing users to check the necessary ingredients and cooking steps.

[0067] Users check the cooking instructions displayed on their device and apply the provided information to their daily lives. They can try out the suggested recipes by purchasing the necessary ingredients and cooking at home. After cooking, they can send feedback through their device, including their evaluation of the taste of the dish and their opinions on the cooking process.

[0068] Ultimately, the server collects and analyzes this feedback data to improve the generated AI model. This analysis utilizes data analysis tools, incorporating the results obtained from the feedback as training data for the model. Through this entire process, the system is continuously improved, and the generated cooking instructions are adjusted to better suit consumer preferences.

[0069] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0070] Step 1:

[0071] The server interacts with the inventory management system to retrieve real-time data on unsold items. This data includes product name, inventory quantity, and expiration date. The server retrieves this information via the inventory management software's API and stores it in a database. The input data is a list of products provided by the inventory system, and the output is an organized inventory database.

[0072] Step 2:

[0073] The server generates prompt statements based on the collected inventory data and inputs them into the generative AI model. The input prompt statements are in the format of "There are 50 tomatoes and 20 packs of cheese." The server creates these prompt statements and passes them to the generative AI model. The data processing performed here is the process of converting inventory information into natural language, and the output is a suggestion of cooking procedures.

[0074] Step 3:

[0075] The server sends cooking instructions derived from the output of the generated AI model to the terminal. These instructions include the necessary ingredients and specific cooking steps. The terminal then reformats this into a format suitable for in-store display devices and smartphone applications. The output is visually appealing recipe information.

[0076] Step 4:

[0077] The terminal receives cooking instructions sent from the server and displays them on in-store digital signage and a smartphone app. Users can then review the cooking instructions and purchase the necessary ingredients through this display. The terminal dynamically updates the digital content based on user input. The output is detailed recipe information available to consumers.

[0078] Step 5:

[0079] After a user cooks a meal at home, they submit feedback via their device. The application allows users to input their opinions on the taste, cooking time, and difficulty of the dish into a feedback form. The input is the user's rating, and the output is feedback data sent to the server.

[0080] Step 6:

[0081] The server collects user feedback data and analyzes it using data analysis tools. This analysis includes processing the text data of the feedback to identify frequently mentioned keywords and evaluations. The input is user feedback, and the output is training data used to improve the generative AI model. The server uses this to improve the accuracy of the AI ​​model.

[0082] (Application Example 1)

[0083] 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."

[0084] Unsold products in physical stores pose inventory management challenges and contribute to decreased profitability. Furthermore, the lack of new recipe suggestions for consumers makes it difficult to improve customer satisfaction. Therefore, there is a need for a system that can effectively utilize unsold products and sustainably provide attractive services to consumers.

[0085] 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.

[0086] In this invention, the server includes an information acquisition means for acquiring attributes of unsold products, a generation mechanism for generating cooking procedures based on the acquired attributes, and a presentation mechanism for presenting the generated cooking procedures to the consumer's communication terminal. This makes it possible to generate cooking procedures in real time based on the attributes of unsold products and to instantly provide consumers with new cooking suggestions.

[0087] "Unsold product attributes" refer to data that indicates specific characteristics of products that remain in inventory, such as identification information, classification information, quantity, and expiration date.

[0088] "Information acquisition means" refers to a mechanism for collecting data on the attributes of unsold products and supplying it to the system.

[0089] A "generation mechanism" is a device that manages the process of creating new value by designing cooking procedures and suggestions based on acquired information.

[0090] A "presentation mechanism" refers to a device and method for displaying and appropriately presenting the generated cooking instructions on a consumer's communication terminal.

[0091] A "feedback receiving mechanism" is a device and method for receiving feedback information from consumers, and for analyzing and processing it.

[0092] The "improvement mechanism" is a mechanism that reviews the system's generation method based on the received feedback information, and aims to optimize and improve it.

[0093] To implement this invention, a system is constructed in which three entities—a server, a terminal, and a consumer—work in cooperation.

[0094] The server first uses an information retrieval mechanism to collect attributes of unsold products from a database. This data includes product identification, category, inventory quantity, and expiration date. The collected information is then analyzed by a generative AI model to design cooking instructions to suggest to consumers. This generative AI model uses advanced natural language processing techniques; for example, if tomatoes and basil are in stock, it can generate a new recipe such as "Tomato and Basil Pasta."

[0095] The terminal receives cooking instructions transmitted from the server and displays them on the consumer's communication device. The application runs on iOS and Android® smartphones and provides generated recipes in real time. By using this application, consumers can check the suggested new recipes and immediately purchase the necessary ingredients at the store.

[0096] After consumers prepare a dish based on a recipe, they send feedback to the server through an evaluation receiving mechanism. This feedback includes items such as the quality of the dish and their understanding of the procedure. Based on this, the server's improvement mechanism improves the generated AI model and uses it to create future suggestions. An example of a specific prompt is, "Please suggest a new Italian recipe using tomatoes and basil."

[0097] This approach allows consumers to utilize unsold products, creating new value and improving customer satisfaction.

[0098] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0099] Step 1:

[0100] The server retrieves unsold product attributes from the inventory management database. It uses database connection information from the inventory management system as input and outputs unsold product attribute data including product identification, category, inventory quantity, and expiration date. This step involves extracting the necessary data using database queries.

[0101] Step 2:

[0102] The server runs an AI model based on the attributes of unsold products to design cooking procedures. The product attribute data obtained in step 1 is used as input. The output generates cooking procedures and recipes based on this data. Specifically, it generates a prompt message for the AI ​​model, "Please suggest a new Italian recipe using tomatoes and basil," and uses natural language processing technology to create new cooking suggestions.

[0103] Step 3:

[0104] The server sends the generated cooking instructions to the terminal. It uses the recipe data generated in step 2 as input. As output, it sends the cooking instructions data to the terminal. Specifically, it performs communication processing to send data via API calls or messaging protocols.

[0105] Step 4:

[0106] The terminal displays the received cooking instructions on the consumer's communication device. It uses the data sent in step 3 as input and displays the recipe on the user interface as output. Specifically, it uses the GUI display function of a smartphone app to allow consumers to easily view the recipe.

[0107] Step 5:

[0108] Users try cooking a dish based on the cooking instructions and input the results as feedback into their device. Consumer evaluation information is collected as input, and the collected feedback data is generated as output. Specifically, the process involves collecting information entered in the feedback form of the smartphone app.

[0109] Step 6:

[0110] The server improves the generated AI model based on the feedback information received from the terminal. It uses the feedback data obtained in step 5 as input and obtains the improved AI model as output. Specifically, it uses the feedback data as training data and performs data analysis and model optimization processing to retrain the AI ​​model.

[0111] 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.

[0112] The embodiment of this invention consists of a system configuration centered on a server, terminal, and user, and in particular, by combining it with an emotion engine, it provides a more advanced user experience.

[0113] First, the server collects data on unsold products from the inventory management system. This data includes information such as product name, category, inventory quantity, and expiration date. Based on this information, the server uses an AI model as a generation tool to generate cooking instructions using the unsold products.

[0114] Once the cooking instructions are generated, the server sends them to a terminal. The terminal can be a digital signage display in the store or a user's smartphone app. The terminal visually presents the received cooking instructions to the user and provides detailed instructions.

[0115] During this process, the emotion engine analyzes the user's reactions. Assuming a scenario where the user is operating a smartphone app, it analyzes the user's facial expressions and voice through the camera and microphone to identify their emotions. For example, if the user shows interest or confusion, this emotional state is sent to the server as feedback.

[0116] Based on the provided cooking instructions, users can purchase the necessary ingredients if they find a dish that interests them. Users can also provide feedback and sentiment data about the dishes they have tried through their device.

[0117] The server receives user ratings and sentiment analysis results as a means of receiving feedback and stores them in a database. Furthermore, as part of the improvement process, the server aims to retrain the generative AI model to provide more appropriate cooking instructions that take user sentiment data into account. This will improve the accuracy of recipe suggestions and create a system that better meets user expectations.

[0118] The following describes the processing flow.

[0119] Step 1:

[0120] The server works in conjunction with the inventory management system to retrieve data on unsold products. This data includes product name, category, inventory quantity, and expiration date.

[0121] Step 2:

[0122] The server inputs data on unsold products into an AI model that generates cooking instructions. This model utilizes combinations of products in the data to create appealing recipes. For example, if there are leftover tomatoes and pasta, it will devise a recipe for tomato sauce pasta.

[0123] Step 3:

[0124] The server sends the generated cooking instructions to a terminal. This terminal includes in-store digital signage and smartphone apps, providing users with a means to visually obtain information.

[0125] Step 4:

[0126] The terminal displays the received cooking instructions on digital signage. Additionally, a smartphone app provides detailed steps and a list of necessary ingredients, guiding the user through the cooking process.

[0127] Step 5:

[0128] The device uses its built-in camera and microphone to collect facial expressions and voices as the user views or selects cooking instructions. This allows the emotion engine to analyze the user's reactions and identify their emotions. For example, if the user smiles, it is recorded as a positive emotion.

[0129] Step 6:

[0130] Based on the information provided, users can purchase ingredients for recipes that interest them and actually cook them at home. During this process, they send feedback via their device regarding their reactions and feelings towards the presented information.

[0131] Step 7:

[0132] The server receives user feedback and sentiment data sent from the terminal and stores it in a database.

[0133] Step 8:

[0134] As a means of improvement, the server analyzes the collected feedback data and retrains the generative AI model. In this process, the results of sentiment analysis are taken into consideration, and the system's accuracy is improved so that it can provide cooking instructions that better match the user's preferences.

[0135] (Example 2)

[0136] 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".

[0137] Traditional inventory management methods have limitations in effectively utilizing unsold products, and it has been difficult to make suggestions that meet consumer interests and preferences. Furthermore, the mechanisms for quickly incorporating consumer feedback have been insufficient, making it necessary to realize a more refined consumer experience.

[0138] 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.

[0139] In this invention, the server includes an information acquisition means for acquiring information about unsold products, a generation means for using a generative artificial intelligence model to generate cooking procedures based on the acquired information, and a display means for visually presenting the generated cooking procedures. This enables the effective utilization of unsold products and the provision of personalized cooking procedures to consumers.

[0140] "Information acquisition methods" refer to means of collecting information about unsold goods.

[0141] A "generative artificial intelligence model" is an artificial intelligence model used to generate cooking procedures based on acquired information.

[0142] "Display means" refers to devices or methods for visually presenting the generated cooking procedure to consumers.

[0143] "Analytical tools" are means of analyzing consumer emotions and obtaining information accordingly.

[0144] A "feedback receiving method" is a means of receiving opinions and evaluations from users.

[0145] "Improvement measures" refer to methods for improving the generation process based on the feedback received and the results of sentiment analysis.

[0146] An "electronic display device" is an electronic device used to display information in digital format.

[0147] A "portable information terminal" is an electronic device that is portable and capable of receiving and displaying information.

[0148] In this system, which is designed to implement the invention, a server, terminals, and users work together. The server is responsible for acquiring information about unsold products. Specifically, it works in conjunction with an inventory management system and collects data such as product name, classification, inventory quantity, and expiration date using APIs or database queries.

[0149] Next, the server uses a generative AI model to generate cooking instructions based on the acquired information. Natural language processing models such as "GPT-3 (registered trademark)" are used as the generative AI model. This automatically creates cooking instructions based on data of unsold products. An example of a prompt used as input to the generative AI model is, "I have leftover tomatoes and basil, so please come up with a simple cooking recipe."

[0150] The generated cooking instructions are sent from the server to a terminal. The terminal includes electronic display devices and personal digital assistants (PDAs), through which the information is presented to the user visually. For example, it can be displayed as visual advertising in the store on digital signage, or as detailed recipe information on a smartphone app.

[0151] Users can view cooking instructions presented via the device and try cooking based on recipes that interest them. The device also performs sentiment analysis, analyzing user reactions through its camera and microphone. This allows the system to understand the user's emotional state and provide data to the server to improve their interest and satisfaction.

[0152] Ultimately, users can provide feedback on the cooking process, including their opinions and impressions. This feedback information is sent to the server and used to improve the generated AI model. This makes it possible to provide cooking instructions that better meet user needs.

[0153] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0154] Step 1:

[0155] The server retrieves information about unsold products from the inventory management system. Specifically, it uses an API or database query to inquire about and collect information such as product name, category, inventory quantity, and expiration date. The input for this step is the unsold product data from the inventory management system, and the output is a list of the collected information about the relevant products.

[0156] Step 2:

[0157] The server uses a generative AI model to generate cooking instructions based on the collected product information. The input includes a list of product information and prompts for the generative AI model. For example, the prompt "I have leftover tomatoes and basil, so please come up with a simple recipe" is input to the AI ​​model. The AI ​​model performs natural language processing based on this prompt and outputs appropriate cooking instructions in text format. The output of this step is the generated cooking instructions.

[0158] Step 3:

[0159] The server sends the generated cooking instructions to the terminal. The input is the cooking instructions generated in the previous step, and the output is the cooking instructions information delivered to the terminal. The terminal includes electronic display devices and personal digital assistants, through which the cooking instructions are displayed to the user.

[0160] Step 4:

[0161] The terminal visually presents the received cooking instructions to the user. The input is the cooking instructions received from the server, and the output is the recipe information presented to the user. Specific actions include displaying detailed recipes on a smartphone app and presenting recipes on digital signage screens.

[0162] Step 5:

[0163] Users can attempt to cook based on the presented cooking instructions. Specific actions include selecting a recipe of interest and preparing to purchase the necessary ingredients. While there are no quantitative inputs or outputs here, the user's choices influence the next steps.

[0164] Step 6:

[0165] The device performs emotion analysis to analyze the user's emotions. Input includes the user's facial expressions and voice data acquired from the camera and microphone. This data is processed by an analysis algorithm, and the output is data representing the user's emotional state.

[0166] Step 7:

[0167] Users provide feedback on cooking procedures via a terminal. Input includes the user's opinions and impressions. This feedback, along with the sentiment analysis results, is sent to the server. Output is the feedback information sent to the server.

[0168] Step 8:

[0169] The server aggregates feedback data received from users and retrains the generative AI model. The input is feedback information and sentiment analysis data, and the output is the improved AI model. This ensures that future cooking procedure suggestions are more closely aligned with the user's preferences.

[0170] (Application Example 2)

[0171] 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".

[0172] The problem this invention aims to solve is to reduce food waste by efficiently utilizing unsold products, while simultaneously improving the user experience. Current systems have limited value propositions based on products that remain in inventory, and new methods are needed to further utilize them.

[0173] 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.

[0174] In this invention, the server includes information acquisition means for acquiring information related to unsold products, generation means for creating creative cooking processes based on the information, display means for visually presenting the generated cooking processes, emotion analysis means for analyzing the emotional state of the user, feedback receiving means for recording customer reactions and receiving evaluations, and adjustment means for adjusting and improving the generation means based on the customer reactions. This makes it possible to increase the added value of unsold products and make attractive proposals to a wider range of users.

[0175] "Information acquisition methods" refer to means of collecting information about unsold goods, such as the items, types, storage quantities, and expiration dates.

[0176] A "generation method" is a means for creating a new cooking process based on acquired information.

[0177] "Display means" refers to a means of visually presenting the generated cooking process to the user.

[0178] "Emotional analysis methods" are techniques for analyzing data such as a user's facial expressions and voice to identify their emotional state.

[0179] A "feedback receiving method" is a means of recording and receiving user reactions and evaluations.

[0180] "Adjustment means" refers to means for improving and adjusting the generation means based on user feedback.

[0181] The system that realizes this invention includes a series of processes for effectively utilizing unsold products and providing users with new cooking suggestions. First, the server collects data on unsold products using information acquisition means. This data includes items, types, storage quantities, and expiration dates. Next, the server uses generation means to generate creative cooking processes based on this data. It utilizes a generation AI model to convert the acquired information into cooking processes in a creative way. Here, the prompt message used is "Generate a creative and simple recipe using the stocked products. For example, generate a recipe using chicken, tomatoes, and spices."

[0182] The terminal uses a display device to visually present the generated cooking process to the user. This can be done using a smartphone or a digital display in the store. Furthermore, an emotion analysis device analyzes the user's facial expressions and voice using a digital device to identify their emotional state. This analysis utilizes emotion analysis technologies such as the Emotion API. The user's reactions are recorded and transmitted to the server via a feedback receiving device.

[0183] When a user finds a cooking process that interests them, they can purchase the necessary ingredients on the spot. User feedback serves as data for improvement. Based on this feedback, the server uses adjustment mechanisms to improve the generation process, aiming to provide recipes that better meet user expectations. This increases the added value of unsold products and enhances the customer experience in physical stores.

[0184] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0185] Step 1:

[0186] The server uses an information acquisition method to retrieve data on unsold products from the inventory management system. Inputs include information such as item name, type, storage quantity, and expiration date, while output is a dataset containing this organized information. Based on this dataset, the server prepares to determine what kinds of dishes can be prepared using it.

[0187] Step 2:

[0188] The server inputs the prompt message "Generate a creative and simple recipe using inventory items. For example, generate a recipe using chicken, tomatoes, and spices." into the generation AI model, which is the generation means, and generates cooking steps. The input consists of the prompt message and pre-processed data on unsold items, and the AI ​​model performs data calculations based on this data to output a new cooking step.

[0189] Step 3:

[0190] The terminal uses a display mechanism to visually present the generated cooking process to the user. The cooking process is displayed as visual information on devices such as smartphones and tablets, making it easy for the user to understand. The input is the generated cooking process, and the output is the visual information presented to the user.

[0191] Step 4:

[0192] The device uses emotion analysis techniques to collect the user's facial expressions and voice using a camera and microphone, and analyzes their emotional state using technologies such as the Emotion API. The input is emotional data from the user, and the output is the analyzed emotional state. This information is transmitted to the server in real time.

[0193] Step 5:

[0194] The user inputs feedback on cooking processes they are interested in via a terminal, and this information is sent to the server through a feedback receiving device. The input is the feedback entered by the user, and the output is the feedback data sent to the server.

[0195] Step 6:

[0196] Based on the feedback, the server adjusts the generative AI model using adjustment mechanisms, aiming to generate even more appropriate cooking processes. The input is user feedback data, which is used to adjust the generative mechanisms, and the output is the improved generative model.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] [Second Embodiment]

[0201] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0202] 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.

[0203] 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).

[0204] 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.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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".

[0213] To implement this invention, a system is constructed in which three entities—a server, a terminal, and a user—work in cooperation.

[0214] First, the server connects with the inventory management system to collect data on unsold products in real time. This provides information on the current inventory status and product expiration dates. Based on this data, the server uses a generative AI model to automatically generate cooking instructions that utilize the unsold products. For example, if there is a large amount of tomatoes and cheese in stock, it can generate a cooking instruction for "Caprese Salad with Tomatoes and Cheese."

[0215] Next, the terminal receives cooking instructions sent from the server and displays them on in-store display devices and the customer's smartphone app. The in-store display devices use visually-oriented presentations to attract the consumer's attention. The smartphone app provides detailed recipe information for users to refer to at any time, displaying the necessary ingredients and cooking steps.

[0216] Users can review the provided cooking instructions and purchase the necessary ingredients. After trying the recipe at home, users can submit feedback via their device. This feedback includes evaluations of the taste of the dish and the difficulty of the process.

[0217] Finally, the server analyzes the collected feedback data and uses it as training data to improve the generated AI model. This improves the overall accuracy of the system so that the cooking instructions generated in the future are more in line with customer preferences. By repeating this cycle, it is possible to sustainably achieve effective utilization of unsold products and improved customer satisfaction.

[0218] The following describes the processing flow.

[0219] Step 1:

[0220] The server accesses the inventory management system via an API to retrieve inventory data for unsold items and other necessary products. This data includes important information such as product name, category, inventory quantity, and expiration date.

[0221] Step 2:

[0222] The server inputs the acquired unsold product data into a generating AI model. This model uses natural language processing and machine learning techniques to generate appropriate cooking procedures based on combinations of unsold products. For example, it can devise new menus using leftover ingredients.

[0223] Step 3:

[0224] The server sends the generated cooking instructions to the terminal. These instructions include a list of required ingredients, cooking time, and step-by-step cooking instructions.

[0225] Step 4:

[0226] The terminal displays cooking instructions received from the server on digital signage in the store and on a smartphone app. The digital signage shows recipes with eye-catching images and text, while the smartphone app allows users to check details and save the recipes.

[0227] Step 5:

[0228] Users can review the presented cooking instructions and add the necessary ingredients to their cart if they are interested. Furthermore, users can try cooking at home based on the recipes displayed on the smartphone app.

[0229] Step 6:

[0230] After a user tries a recipe, they send feedback about it via their device. This feedback includes information such as the difficulty level of the recipe, the taste, and suggestions for improvement.

[0231] Step 7:

[0232] The server stores and analyzes the collected feedback data in a database. This data is used to retrain the generative AI model, improving the accuracy of future recipe suggestions. The goal is to generate new recipes that are better suited to the user's preferences based on the feedback.

[0233] (Example 1)

[0234] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0235] The increasing amount of unsold goods presents significant challenges, including inventory management, waste management, and the resulting increase in costs. Furthermore, a lack of recipe suggestions tailored to consumer preferences is hindering effective product consumption. Therefore, there is a need for a system that effectively utilizes inventory while automatically generating cooking suggestions that meet consumer needs.

[0236] 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.

[0237] In this invention, the server includes a data collection means for acquiring data on unsold products, a generation means using artificial intelligence to automatically generate cooking procedures based on the data, and a means for presenting the generated cooking procedures via an information display means. This enables the effective use of inventory and improved consumer satisfaction by collecting data on unsold products in real time and efficiently generating and providing cooking procedures based on that data.

[0238] "Unsold goods" refer to products that have not been sold in the market and remain as inventory, and which may be discarded.

[0239] "Data collection means" refers to functions and devices for acquiring and aggregating information about inventory and unsold goods.

[0240] "Generation means" refers to a function or system that uses artificial intelligence to automatically generate cooking procedures from the collected data.

[0241] "Information display means" refers to devices or software that visually present the generated cooking instructions to consumers.

[0242] "Feedback collection methods" refer to functions or devices for receiving feedback, evaluations, and other reactions from consumers.

[0243] "Information analysis and learning tools" refer to functions and systems for analyzing feedback and improving or adjusting the accuracy of generation tools.

[0244] This system is built around three main components: a server, terminals, and users, each working in cooperation with the others. First, the server integrates with the inventory management system to collect real-time data on unsold goods. Inventory management software is used for this data collection, obtaining information on the inventory status and expiration dates of unsold items. Specifically, the server retrieves this information from a database and utilizes artificial intelligence technology to process it.

[0245] The server uses a generative AI model to automatically generate cooking instructions from collected data on unsold products. This AI model includes models that utilize natural language processing techniques. Specific examples of the AI ​​models used include commonly used language generation models, which have the ability to generate new content based on input data. As an example of a specific cooking instruction to be generated, if the prompt message is "There are 50 tomatoes and 20 packs of cheese in stock," it is possible to automatically generate a recipe for "Caprese salad with tomatoes and cheese."

[0246] Next, the terminal receives cooking instructions transmitted from the server and displays the suggested recipe on in-store display devices and the consumer's smartphone application. The in-store display devices are expected to utilize a digital signage system to provide visually appealing information. The smartphone application displays detailed recipe information, allowing users to check the necessary ingredients and cooking steps.

[0247] Users check the cooking instructions displayed on their device and apply the provided information to their daily lives. They can try out the suggested recipes by purchasing the necessary ingredients and cooking at home. After cooking, they can send feedback through their device, including their evaluation of the taste of the dish and their opinions on the cooking process.

[0248] Ultimately, the server collects and analyzes this feedback data to improve the generated AI model. This analysis utilizes data analysis tools, incorporating the results obtained from the feedback as training data for the model. Through this entire process, the system is continuously improved, and the generated cooking instructions are adjusted to better suit consumer preferences.

[0249] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0250] Step 1:

[0251] The server interacts with the inventory management system to retrieve real-time data on unsold items. This data includes product name, inventory quantity, and expiration date. The server retrieves this information via the inventory management software's API and stores it in a database. The input data is a list of products provided by the inventory system, and the output is an organized inventory database.

[0252] Step 2:

[0253] The server generates prompt statements based on the collected inventory data and inputs them into the generative AI model. The input prompt statements are in the format of "There are 50 tomatoes and 20 packs of cheese." The server creates these prompt statements and passes them to the generative AI model. The data processing performed here is the process of converting inventory information into natural language, and the output is a suggestion of cooking procedures.

[0254] Step 3:

[0255] The server sends cooking instructions derived from the output of the generated AI model to the terminal. These instructions include the necessary ingredients and specific cooking steps. The terminal then reformats this into a format suitable for in-store display devices and smartphone applications. The output is visually appealing recipe information.

[0256] Step 4:

[0257] The terminal receives cooking instructions sent from the server and displays them on in-store digital signage and a smartphone app. Users can then review the cooking instructions and purchase the necessary ingredients through this display. The terminal dynamically updates the digital content based on user input. The output is detailed recipe information available to consumers.

[0258] Step 5:

[0259] After a user cooks a meal at home, they submit feedback via their device. The application allows users to input their opinions on the taste, cooking time, and difficulty of the dish into a feedback form. The input is the user's rating, and the output is feedback data sent to the server.

[0260] Step 6:

[0261] The server collects user feedback data and analyzes it using data analysis tools. This analysis includes processing the text data of the feedback to identify frequently mentioned keywords and evaluations. The input is user feedback, and the output is training data used to improve the generative AI model. The server uses this to improve the accuracy of the AI ​​model.

[0262] (Application Example 1)

[0263] 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."

[0264] Unsold products in physical stores pose inventory management challenges and contribute to decreased profitability. Furthermore, the lack of new recipe suggestions for consumers makes it difficult to improve customer satisfaction. Therefore, there is a need for a system that can effectively utilize unsold products and sustainably provide attractive services to consumers.

[0265] 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.

[0266] In this invention, the server includes an information acquisition means for acquiring attributes of unsold products, a generation mechanism for generating cooking procedures based on the acquired attributes, and a presentation mechanism for presenting the generated cooking procedures to the consumer's communication terminal. This makes it possible to generate cooking procedures in real time based on the attributes of unsold products and to instantly provide consumers with new cooking suggestions.

[0267] "Unsold product attributes" refer to data that indicates specific characteristics of products that remain in inventory, such as identification information, classification information, quantity, and expiration date.

[0268] "Information acquisition means" refers to a mechanism for collecting data on the attributes of unsold products and supplying it to the system.

[0269] A "generation mechanism" is a device that manages the process of creating new value by designing cooking procedures and suggestions based on acquired information.

[0270] A "presentation mechanism" refers to a device and method for displaying and appropriately presenting the generated cooking instructions on a consumer's communication terminal.

[0271] A "feedback receiving mechanism" is a device and method for receiving feedback information from consumers, and for analyzing and processing it.

[0272] The "improvement mechanism" is a mechanism that reviews the system's generation method based on the received feedback information, and aims to optimize and improve it.

[0273] To implement this invention, a system is constructed in which three entities—a server, a terminal, and a consumer—work in cooperation.

[0274] The server first uses an information retrieval mechanism to collect attributes of unsold products from a database. This data includes product identification, category, inventory quantity, and expiration date. The collected information is then analyzed by a generative AI model to design cooking instructions to suggest to consumers. This generative AI model uses advanced natural language processing techniques; for example, if tomatoes and basil are in stock, it can generate a new recipe such as "Tomato and Basil Pasta."

[0275] The terminal receives cooking instructions sent from the server and displays them on the consumer's communication device. The application runs on iOS and Android smartphones and provides generated recipes in real time. By using this application, consumers can check the suggested new recipes and immediately purchase the necessary ingredients at the store.

[0276] After consumers prepare a dish based on a recipe, they send feedback to the server through an evaluation receiving mechanism. This feedback includes items such as the quality of the dish and their understanding of the procedure. Based on this, the server's improvement mechanism improves the generated AI model and uses it to create future suggestions. An example of a specific prompt is, "Please suggest a new Italian recipe using tomatoes and basil."

[0277] This approach allows consumers to utilize unsold products, creating new value and improving customer satisfaction.

[0278] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0279] Step 1:

[0280] The server obtains the remaining inventory item attributes from the inventory management database. Using the database connection information from the inventory management system as input, it obtains the remaining inventory item attribute data including item identification, category, inventory quantity, and expiration date as output. In this step, a process of extracting the necessary data using a database query is performed.

[0281] Step 2:

[0282] The server executes the AI model generated based on the remaining inventory item attributes to design cooking procedures. Using the item attribute data obtained in Step 1 as input, it generates cooking procedures and recipes based on that as output. As a specific operation, a prompt sentence such as "Please propose a new Italian recipe using tomatoes and basil." is generated for the AI model, and a process of creating a new cooking proposal by utilizing natural language processing technology is performed.

[0283] Step 3:

[0284] The server sends the generated cooking procedures to the terminal. Using the recipe data generated in Step 2 as input, it sends the cooking procedure data to the terminal as output. As a specific operation, a communication process of sending data through an API call or a messaging protocol is performed.

[0285] Step 4:

[0286] The terminal displays the received cooking procedures on the consumer's communication terminal. Using the data sent in Step 3 as input, it displays the recipe on the user interface as output. As a specific operation, a process of enabling the consumer to easily view the recipe using the GUI display function in a smartphone app is performed.

[0287] Step 5:

[0288] Users try cooking a dish based on the cooking instructions and input the results as feedback into their device. Consumer evaluation information is collected as input, and the collected feedback data is generated as output. Specifically, the process involves collecting information entered in the feedback form of the smartphone app.

[0289] Step 6:

[0290] The server improves the generated AI model based on the feedback information received from the terminal. It uses the feedback data obtained in step 5 as input and obtains the improved AI model as output. Specifically, it uses the feedback data as training data and performs data analysis and model optimization processing to retrain the AI ​​model.

[0291] 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.

[0292] The embodiment of this invention consists of a system configuration centered on a server, terminal, and user, and in particular, by combining it with an emotion engine, it provides a more advanced user experience.

[0293] First, the server collects data on unsold products from the inventory management system. This data includes information such as product name, category, inventory quantity, and expiration date. Based on this information, the server uses an AI model as a generation tool to generate cooking instructions using the unsold products.

[0294] Once the cooking instructions are generated, the server sends them to a terminal. The terminal can be a digital signage display in the store or a user's smartphone app. The terminal visually presents the received cooking instructions to the user and provides detailed instructions.

[0295] During this process, the emotion engine analyzes the user's reactions. Assuming a scenario where the user is operating a smartphone app, it analyzes the user's facial expressions and voice through the camera and microphone to identify their emotions. For example, if the user shows interest or confusion, this emotional state is sent to the server as feedback.

[0296] Based on the provided cooking instructions, users can purchase the necessary ingredients if they find a dish that interests them. Users can also provide feedback and sentiment data about the dishes they have tried through their device.

[0297] The server receives user ratings and sentiment analysis results as a means of receiving feedback and stores them in a database. Furthermore, as part of the improvement process, the server aims to retrain the generative AI model to provide more appropriate cooking instructions that take user sentiment data into account. This will improve the accuracy of recipe suggestions and create a system that better meets user expectations.

[0298] The following describes the processing flow.

[0299] Step 1:

[0300] The server works in conjunction with the inventory management system to retrieve data on unsold products. This data includes product name, category, inventory quantity, and expiration date.

[0301] Step 2:

[0302] The server inputs data on unsold products into an AI model that generates cooking instructions. This model utilizes combinations of products in the data to create appealing recipes. For example, if there are leftover tomatoes and pasta, it will devise a recipe for tomato sauce pasta.

[0303] Step 3:

[0304] The server sends the generated cooking procedure to the terminal. This terminal includes in-store digital signage and a smartphone app, providing means for users to visually obtain information.

[0305] Step 4:

[0306] The terminal displays the received cooking procedure on the digital signage. Also, the smartphone app provides detailed steps and a list of required ingredients, showing users how to proceed with the cooking.

[0307] Step 5:

[0308] The terminal uses its built-in camera and microphone to collect the expressions and voices of users when they view or select the cooking procedure. Based on this, the emotion engine analyzes the users' reactions and identifies their emotions. For example, if a user shows a smiling face, it is recorded as a positive emotion.

[0309] Step 6:

[0310] Based on the provided information, users can purchase the ingredients for the recipes they are interested in and actually cook at home. At this time, they send feedback on their reactions and emotions towards the presented information through the terminal.

[0311] Step 7:

[0312] The server receives the user feedback and emotion data sent from the terminal and stores them in the database.

[0313] Step 8:

[0314] As an improvement measure, the server analyzes the collected feedback data and retrains the generated AI model. In this process, considering the emotion analysis results, it improves the accuracy of the system to be able to provide cooking procedures that match the users' preferences.

[0315] (Example 2)

[0316] 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".

[0317] Traditional inventory management methods have limitations in effectively utilizing unsold products, and it has been difficult to make suggestions that meet consumer interests and preferences. Furthermore, the mechanisms for quickly incorporating consumer feedback have been insufficient, making it necessary to realize a more refined consumer experience.

[0318] 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.

[0319] In this invention, the server includes an information acquisition means for acquiring information about unsold products, a generation means for using a generative artificial intelligence model to generate cooking procedures based on the acquired information, and a display means for visually presenting the generated cooking procedures. This enables the effective utilization of unsold products and the provision of personalized cooking procedures to consumers.

[0320] "Information acquisition methods" refer to means of collecting information about unsold goods.

[0321] A "generative artificial intelligence model" is an artificial intelligence model used to generate cooking procedures based on acquired information.

[0322] "Display means" refers to devices or methods for visually presenting the generated cooking procedure to consumers.

[0323] "Analytical tools" are means of analyzing consumer emotions and obtaining information accordingly.

[0324] A "feedback receiving method" is a means of receiving opinions and evaluations from users.

[0325] "Improvement measures" refer to methods for improving the generation process based on the feedback received and the results of sentiment analysis.

[0326] An "electronic display device" is an electronic device used to display information in digital format.

[0327] A "portable information terminal" is an electronic device that is portable and capable of receiving and displaying information.

[0328] In this system, which is designed to implement the invention, a server, terminals, and users work together. The server is responsible for acquiring information about unsold products. Specifically, it works in conjunction with an inventory management system and collects data such as product name, classification, inventory quantity, and expiration date using APIs or database queries.

[0329] Next, the server uses a generative AI model to generate cooking instructions based on the acquired information. Natural language processing models such as "GPT-3" are used as the generative AI model. This automatically creates cooking instructions based on data of unsold products. An example of a prompt used as input to the generative AI model is, "I have leftover tomatoes and basil, so please come up with a simple cooking recipe."

[0330] The generated cooking instructions are sent from the server to a terminal. The terminal includes electronic display devices and personal digital assistants (PDAs), through which the information is presented to the user visually. For example, it can be displayed as visual advertising in the store on digital signage, or as detailed recipe information on a smartphone app.

[0331] Users can view cooking instructions presented via the device and try cooking based on recipes that interest them. The device also performs sentiment analysis, analyzing user reactions through its camera and microphone. This allows the system to understand the user's emotional state and provide data to the server to improve their interest and satisfaction.

[0332] Ultimately, users can provide feedback on the cooking process, including their opinions and impressions. This feedback information is sent to the server and used to improve the generated AI model. This makes it possible to provide cooking instructions that better meet user needs.

[0333] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0334] Step 1:

[0335] The server retrieves information about unsold products from the inventory management system. Specifically, it uses an API or database query to inquire about and collect information such as product name, category, inventory quantity, and expiration date. The input for this step is the unsold product data from the inventory management system, and the output is a list of the collected information about the relevant products.

[0336] Step 2:

[0337] The server uses a generative AI model to generate cooking instructions based on the collected product information. The input includes a list of product information and prompts for the generative AI model. For example, the prompt "I have leftover tomatoes and basil, so please come up with a simple recipe" is input to the AI ​​model. The AI ​​model performs natural language processing based on this prompt and outputs appropriate cooking instructions in text format. The output of this step is the generated cooking instructions.

[0338] Step 3:

[0339] The server sends the generated cooking instructions to the terminal. The input is the cooking instructions generated in the previous step, and the output is the cooking instructions information delivered to the terminal. The terminal includes electronic display devices and personal digital assistants, through which the cooking instructions are displayed to the user.

[0340] Step 4:

[0341] The terminal visually presents the received cooking instructions to the user. The input is the cooking instructions received from the server, and the output is the recipe information presented to the user. Specific actions include displaying detailed recipes on a smartphone app and presenting recipes on digital signage screens.

[0342] Step 5:

[0343] Users can attempt to cook based on the presented cooking instructions. Specific actions include selecting a recipe of interest and preparing to purchase the necessary ingredients. While there are no quantitative inputs or outputs here, the user's choices influence the next steps.

[0344] Step 6:

[0345] The device performs emotion analysis to analyze the user's emotions. Input includes the user's facial expressions and voice data acquired from the camera and microphone. This data is processed by an analysis algorithm, and the output is data representing the user's emotional state.

[0346] Step 7:

[0347] Users provide feedback on cooking procedures via a terminal. Input includes the user's opinions and impressions. This feedback, along with the sentiment analysis results, is sent to the server. Output is the feedback information sent to the server.

[0348] Step 8:

[0349] The server aggregates feedback data received from users and retrains the generative AI model. The input is feedback information and sentiment analysis data, and the output is the improved AI model. This ensures that future cooking procedure suggestions are more closely aligned with the user's preferences.

[0350] (Application Example 2)

[0351] 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."

[0352] The problem this invention aims to solve is to reduce food waste by efficiently utilizing unsold products, while simultaneously improving the user experience. Current systems have limited value propositions based on products that remain in inventory, and new methods are needed to further utilize them.

[0353] 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.

[0354] In this invention, the server includes information acquisition means for acquiring information related to unsold products, generation means for creating creative cooking processes based on the information, display means for visually presenting the generated cooking processes, emotion analysis means for analyzing the emotional state of the user, feedback receiving means for recording customer reactions and receiving evaluations, and adjustment means for adjusting and improving the generation means based on the customer reactions. This makes it possible to increase the added value of unsold products and make attractive proposals to a wider range of users.

[0355] "Information acquisition methods" refer to means of collecting information about unsold goods, such as the items, types, storage quantities, and expiration dates.

[0356] A "generation method" is a means for creating a new cooking process based on acquired information.

[0357] "Display means" refers to a means of visually presenting the generated cooking process to the user.

[0358] "Emotional analysis methods" are techniques for analyzing data such as a user's facial expressions and voice to identify their emotional state.

[0359] A "feedback receiving method" is a means of recording and receiving user reactions and evaluations.

[0360] "Adjustment means" refers to means for improving and adjusting the generation means based on user feedback.

[0361] The system that realizes this invention includes a series of processes for effectively utilizing unsold products and providing users with new cooking suggestions. First, the server collects data on unsold products using information acquisition means. This data includes items, types, storage quantities, and expiration dates. Next, the server uses generation means to generate creative cooking processes based on this data. It utilizes a generation AI model to convert the acquired information into cooking processes in a creative way. Here, the prompt message used is "Generate a creative and simple recipe using the stocked products. For example, generate a recipe using chicken, tomatoes, and spices."

[0362] The terminal uses a display device to visually present the generated cooking process to the user. This can be done using a smartphone or a digital display in the store. Furthermore, an emotion analysis device analyzes the user's facial expressions and voice using a digital device to identify their emotional state. This analysis utilizes emotion analysis technologies such as the Emotion API. The user's reactions are recorded and transmitted to the server via a feedback receiving device.

[0363] When a user finds a cooking process that interests them, they can purchase the necessary ingredients on the spot. User feedback serves as data for improvement. Based on this feedback, the server uses adjustment mechanisms to improve the generation process, aiming to provide recipes that better meet user expectations. This increases the added value of unsold products and enhances the customer experience in physical stores.

[0364] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0365] Step 1:

[0366] The server uses an information acquisition method to retrieve data on unsold products from the inventory management system. Inputs include information such as item name, type, storage quantity, and expiration date, while output is a dataset containing this organized information. Based on this dataset, the server prepares to determine what kinds of dishes can be prepared using it.

[0367] Step 2:

[0368] The server inputs the prompt message "Generate a creative and simple recipe using inventory items. For example, generate a recipe using chicken, tomatoes, and spices." into the generation AI model, which is the generation means, and generates cooking steps. The input consists of the prompt message and pre-processed data on unsold items, and the AI ​​model performs data calculations based on this data to output a new cooking step.

[0369] Step 3:

[0370] The terminal uses a display mechanism to visually present the generated cooking process to the user. The cooking process is displayed as visual information on devices such as smartphones and tablets, making it easy for the user to understand. The input is the generated cooking process, and the output is the visual information presented to the user.

[0371] Step 4:

[0372] The device uses emotion analysis techniques to collect the user's facial expressions and voice using a camera and microphone, and analyzes their emotional state using technologies such as the Emotion API. The input is emotional data from the user, and the output is the analyzed emotional state. This information is transmitted to the server in real time.

[0373] Step 5:

[0374] The user inputs feedback on cooking processes they are interested in via a terminal, and this information is sent to the server through a feedback receiving device. The input is the feedback entered by the user, and the output is the feedback data sent to the server.

[0375] Step 6:

[0376] Based on the feedback, the server adjusts the generative AI model using adjustment mechanisms, aiming to generate even more appropriate cooking processes. The input is user feedback data, which is used to adjust the generative mechanisms, and the output is the improved generative model.

[0377] 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.

[0378] 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.

[0379] 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.

[0380] [Third Embodiment]

[0381] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0382] 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.

[0383] 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).

[0384] 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.

[0385] 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.

[0386] 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).

[0387] 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.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] 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.

[0392] 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".

[0393] To implement this invention, a system is constructed in which three entities—a server, a terminal, and a user—work in cooperation.

[0394] First, the server connects with the inventory management system to collect data on unsold products in real time. This provides information on the current inventory status and product expiration dates. Based on this data, the server uses a generative AI model to automatically generate cooking instructions that utilize the unsold products. For example, if there is a large amount of tomatoes and cheese in stock, it can generate a cooking instruction for "Caprese Salad with Tomatoes and Cheese."

[0395] Next, the terminal receives cooking instructions sent from the server and displays them on in-store display devices and the customer's smartphone app. The in-store display devices use visually-oriented presentations to attract the consumer's attention. The smartphone app provides detailed recipe information for users to refer to at any time, displaying the necessary ingredients and cooking steps.

[0396] Users can review the provided cooking instructions and purchase the necessary ingredients. After trying the recipe at home, users can submit feedback via their device. This feedback includes evaluations of the taste of the dish and the difficulty of the process.

[0397] Finally, the server analyzes the collected feedback data and uses it as training data to improve the generated AI model. This improves the overall accuracy of the system so that the cooking instructions generated in the future are more in line with customer preferences. By repeating this cycle, it is possible to sustainably achieve effective utilization of unsold products and improved customer satisfaction.

[0398] The following describes the processing flow.

[0399] Step 1:

[0400] The server accesses the inventory management system via an API to retrieve inventory data for unsold items and other necessary products. This data includes important information such as product name, category, inventory quantity, and expiration date.

[0401] Step 2:

[0402] The server inputs the acquired unsold product data into a generating AI model. This model uses natural language processing and machine learning techniques to generate appropriate cooking procedures based on combinations of unsold products. For example, it can devise new menus using leftover ingredients.

[0403] Step 3:

[0404] The server sends the generated cooking instructions to the terminal. These instructions include a list of required ingredients, cooking time, and step-by-step cooking instructions.

[0405] Step 4:

[0406] The terminal displays cooking instructions received from the server on digital signage in the store and on a smartphone app. The digital signage shows recipes with eye-catching images and text, while the smartphone app allows users to check details and save the recipes.

[0407] Step 5:

[0408] Users can review the presented cooking instructions and add the necessary ingredients to their cart if they are interested. Furthermore, users can try cooking at home based on the recipes displayed on the smartphone app.

[0409] Step 6:

[0410] After a user tries a recipe, they send feedback about it via their device. This feedback includes information such as the difficulty level of the recipe, the taste, and suggestions for improvement.

[0411] Step 7:

[0412] The server stores and analyzes the collected feedback data in a database. This data is used to retrain the generative AI model, improving the accuracy of future recipe suggestions. The goal is to generate new recipes that are better suited to the user's preferences based on the feedback.

[0413] (Example 1)

[0414] 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."

[0415] The increasing amount of unsold goods presents significant challenges, including inventory management, waste management, and the resulting increase in costs. Furthermore, a lack of recipe suggestions tailored to consumer preferences is hindering effective product consumption. Therefore, there is a need for a system that effectively utilizes inventory while automatically generating cooking suggestions that meet consumer needs.

[0416] 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.

[0417] In this invention, the server includes a data collection means for acquiring data on unsold products, a generation means using artificial intelligence to automatically generate cooking procedures based on the data, and a means for presenting the generated cooking procedures via an information display means. This enables the effective use of inventory and improved consumer satisfaction by collecting data on unsold products in real time and efficiently generating and providing cooking procedures based on that data.

[0418] "Unsold goods" refer to products that have not been sold in the market and remain as inventory, and which may be discarded.

[0419] "Data collection means" refers to functions and devices for acquiring and aggregating information about inventory and unsold goods.

[0420] "Generation means" refers to a function or system that uses artificial intelligence to automatically generate cooking procedures from the collected data.

[0421] "Information display means" refers to devices or software that visually present the generated cooking instructions to consumers.

[0422] "Feedback collection methods" refer to functions or devices for receiving feedback, evaluations, and other reactions from consumers.

[0423] "Information analysis and learning tools" refer to functions and systems for analyzing feedback and improving or adjusting the accuracy of generation tools.

[0424] This system is built around three main components: a server, terminals, and users, each working in cooperation with the others. First, the server integrates with the inventory management system to collect real-time data on unsold goods. Inventory management software is used for this data collection, obtaining information on the inventory status and expiration dates of unsold items. Specifically, the server retrieves this information from a database and utilizes artificial intelligence technology to process it.

[0425] The server uses a generative AI model to automatically generate cooking instructions from collected data on unsold products. This AI model includes models that utilize natural language processing techniques. Specific examples of the AI ​​models used include commonly used language generation models, which have the ability to generate new content based on input data. As an example of a specific cooking instruction to be generated, if the prompt message is "There are 50 tomatoes and 20 packs of cheese in stock," it is possible to automatically generate a recipe for "Caprese salad with tomatoes and cheese."

[0426] Next, the terminal receives cooking instructions transmitted from the server and displays the suggested recipe on in-store display devices and the consumer's smartphone application. The in-store display devices are expected to utilize a digital signage system to provide visually appealing information. The smartphone application displays detailed recipe information, allowing users to check the necessary ingredients and cooking steps.

[0427] Users check the cooking instructions displayed on their device and apply the provided information to their daily lives. They can try out the suggested recipes by purchasing the necessary ingredients and cooking at home. After cooking, they can send feedback through their device, including their evaluation of the taste of the dish and their opinions on the cooking process.

[0428] Ultimately, the server collects and analyzes this feedback data to improve the generated AI model. This analysis utilizes data analysis tools, incorporating the results obtained from the feedback as training data for the model. Through this entire process, the system is continuously improved, and the generated cooking instructions are adjusted to better suit consumer preferences.

[0429] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0430] Step 1:

[0431] The server interacts with the inventory management system to retrieve real-time data on unsold items. This data includes product name, inventory quantity, and expiration date. The server retrieves this information via the inventory management software's API and stores it in a database. The input data is a list of products provided by the inventory system, and the output is an organized inventory database.

[0432] Step 2:

[0433] The server generates prompt statements based on the collected inventory data and inputs them into the generative AI model. The input prompt statements are in the format of "There are 50 tomatoes and 20 packs of cheese." The server creates these prompt statements and passes them to the generative AI model. The data processing performed here is the process of converting inventory information into natural language, and the output is a suggestion of cooking procedures.

[0434] Step 3:

[0435] The server sends cooking instructions derived from the output of the generated AI model to the terminal. These instructions include the necessary ingredients and specific cooking steps. The terminal then reformats this into a format suitable for in-store display devices and smartphone applications. The output is visually appealing recipe information.

[0436] Step 4:

[0437] The terminal receives cooking instructions sent from the server and displays them on in-store digital signage and a smartphone app. Users can then review the cooking instructions and purchase the necessary ingredients through this display. The terminal dynamically updates the digital content based on user input. The output is detailed recipe information available to consumers.

[0438] Step 5:

[0439] After a user cooks a meal at home, they submit feedback via their device. The application allows users to input their opinions on the taste, cooking time, and difficulty of the dish into a feedback form. The input is the user's rating, and the output is feedback data sent to the server.

[0440] Step 6:

[0441] The server collects user feedback data and analyzes it using data analysis tools. This analysis includes processing the text data of the feedback to identify frequently mentioned keywords and evaluations. The input is user feedback, and the output is training data used to improve the generative AI model. The server uses this to improve the accuracy of the AI ​​model.

[0442] (Application Example 1)

[0443] 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."

[0444] Unsold products in physical stores pose inventory management challenges and contribute to decreased profitability. Furthermore, the lack of new recipe suggestions for consumers makes it difficult to improve customer satisfaction. Therefore, there is a need for a system that can effectively utilize unsold products and sustainably provide attractive services to consumers.

[0445] 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.

[0446] In this invention, the server includes an information acquisition means for acquiring attributes of unsold products, a generation mechanism for generating cooking procedures based on the acquired attributes, and a presentation mechanism for presenting the generated cooking procedures to the consumer's communication terminal. This makes it possible to generate cooking procedures in real time based on the attributes of unsold products and to instantly provide consumers with new cooking suggestions.

[0447] "Unsold product attributes" refer to data that indicates specific characteristics of products that remain in inventory, such as identification information, classification information, quantity, and expiration date.

[0448] "Information acquisition means" refers to a mechanism for collecting data on the attributes of unsold products and supplying it to the system.

[0449] A "generation mechanism" is a device that manages the process of creating new value by designing cooking procedures and suggestions based on acquired information.

[0450] A "presentation mechanism" refers to a device and method for displaying and appropriately presenting the generated cooking instructions on a consumer's communication terminal.

[0451] A "feedback receiving mechanism" is a device and method for receiving feedback information from consumers, and for analyzing and processing it.

[0452] The "improvement mechanism" is a mechanism that reviews the system's generation method based on the received feedback information, and aims to optimize and improve it.

[0453] To implement this invention, a system is constructed in which three entities—a server, a terminal, and a consumer—work in cooperation.

[0454] The server first uses an information retrieval mechanism to collect attributes of unsold products from a database. This data includes product identification, category, inventory quantity, and expiration date. The collected information is then analyzed by a generative AI model to design cooking instructions to suggest to consumers. This generative AI model uses advanced natural language processing techniques; for example, if tomatoes and basil are in stock, it can generate a new recipe such as "Tomato and Basil Pasta."

[0455] The terminal receives cooking instructions sent from the server and displays them on the consumer's communication device. The application runs on iOS and Android smartphones and provides generated recipes in real time. By using this application, consumers can check the suggested new recipes and immediately purchase the necessary ingredients at the store.

[0456] After consumers prepare a dish based on a recipe, they send feedback to the server through an evaluation receiving mechanism. This feedback includes items such as the quality of the dish and their understanding of the procedure. Based on this, the server's improvement mechanism improves the generated AI model and uses it to create future suggestions. An example of a specific prompt is, "Please suggest a new Italian recipe using tomatoes and basil."

[0457] This approach allows consumers to utilize unsold products, creating new value and improving customer satisfaction.

[0458] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0459] Step 1:

[0460] The server retrieves unsold product attributes from the inventory management database. It uses database connection information from the inventory management system as input and outputs unsold product attribute data including product identification, category, inventory quantity, and expiration date. This step involves extracting the necessary data using database queries.

[0461] Step 2:

[0462] The server runs an AI model based on the attributes of unsold products to design cooking procedures. The product attribute data obtained in step 1 is used as input. The output generates cooking procedures and recipes based on this data. Specifically, it generates a prompt message for the AI ​​model, "Please suggest a new Italian recipe using tomatoes and basil," and uses natural language processing technology to create new cooking suggestions.

[0463] Step 3:

[0464] The server sends the generated cooking instructions to the terminal. It uses the recipe data generated in step 2 as input. As output, it sends the cooking instructions data to the terminal. Specifically, it performs communication processing to send data via API calls or messaging protocols.

[0465] Step 4:

[0466] The terminal displays the received cooking instructions on the consumer's communication device. It uses the data sent in step 3 as input and displays the recipe on the user interface as output. Specifically, it uses the GUI display function of a smartphone app to allow consumers to easily view the recipe.

[0467] Step 5:

[0468] Users try cooking a dish based on the cooking instructions and input the results as feedback into their device. Consumer evaluation information is collected as input, and the collected feedback data is generated as output. Specifically, the process involves collecting information entered in the feedback form of the smartphone app.

[0469] Step 6:

[0470] The server improves the generated AI model based on the feedback information received from the terminal. It uses the feedback data obtained in step 5 as input and obtains the improved AI model as output. Specifically, it uses the feedback data as training data and performs data analysis and model optimization processing to retrain the AI ​​model.

[0471] 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.

[0472] The embodiment of this invention consists of a system configuration centered on a server, terminal, and user, and in particular, by combining it with an emotion engine, it provides a more advanced user experience.

[0473] First, the server collects data on unsold products from the inventory management system. This data includes information such as product name, category, inventory quantity, and expiration date. Based on this information, the server uses an AI model as a generation tool to generate cooking instructions using the unsold products.

[0474] Once the cooking instructions are generated, the server sends them to a terminal. The terminal can be a digital signage display in the store or a user's smartphone app. The terminal visually presents the received cooking instructions to the user and provides detailed instructions.

[0475] During this process, the emotion engine analyzes the user's reactions. Assuming a scenario where the user is operating a smartphone app, it analyzes the user's facial expressions and voice through the camera and microphone to identify their emotions. For example, if the user shows interest or confusion, this emotional state is sent to the server as feedback.

[0476] Based on the provided cooking instructions, users can purchase the necessary ingredients if they find a dish that interests them. Users can also provide feedback and sentiment data about the dishes they have tried through their device.

[0477] The server receives user ratings and sentiment analysis results as a means of receiving feedback and stores them in a database. Furthermore, as part of the improvement process, the server aims to retrain the generative AI model to provide more appropriate cooking instructions that take user sentiment data into account. This will improve the accuracy of recipe suggestions and create a system that better meets user expectations.

[0478] The following describes the processing flow.

[0479] Step 1:

[0480] The server works in conjunction with the inventory management system to retrieve data on unsold products. This data includes product name, category, inventory quantity, and expiration date.

[0481] Step 2:

[0482] The server inputs data on unsold products into an AI model that generates cooking instructions. This model utilizes combinations of products in the data to create appealing recipes. For example, if there are leftover tomatoes and pasta, it will devise a recipe for tomato sauce pasta.

[0483] Step 3:

[0484] The server sends the generated cooking instructions to a terminal. This terminal includes in-store digital signage and smartphone apps, providing users with a means to visually obtain information.

[0485] Step 4:

[0486] The terminal displays the received cooking instructions on digital signage. Additionally, a smartphone app provides detailed steps and a list of necessary ingredients, guiding the user through the cooking process.

[0487] Step 5:

[0488] The device uses its built-in camera and microphone to collect facial expressions and voices as the user views or selects cooking instructions. This allows the emotion engine to analyze the user's reactions and identify their emotions. For example, if the user smiles, it is recorded as a positive emotion.

[0489] Step 6:

[0490] Based on the information provided, users can purchase ingredients for recipes that interest them and actually cook them at home. During this process, they send feedback via their device regarding their reactions and feelings towards the presented information.

[0491] Step 7:

[0492] The server receives user feedback and sentiment data sent from the terminal and stores it in a database.

[0493] Step 8:

[0494] As a means of improvement, the server analyzes the collected feedback data and retrains the generative AI model. In this process, the results of sentiment analysis are taken into consideration, and the system's accuracy is improved so that it can provide cooking instructions that better match the user's preferences.

[0495] (Example 2)

[0496] 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."

[0497] Traditional inventory management methods have limitations in effectively utilizing unsold products, and it has been difficult to make suggestions that meet consumer interests and preferences. Furthermore, the mechanisms for quickly incorporating consumer feedback have been insufficient, making it necessary to realize a more refined consumer experience.

[0498] 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.

[0499] In this invention, the server includes an information acquisition means for acquiring information about unsold products, a generation means for using a generative artificial intelligence model to generate cooking procedures based on the acquired information, and a display means for visually presenting the generated cooking procedures. This enables the effective utilization of unsold products and the provision of personalized cooking procedures to consumers.

[0500] "Information acquisition methods" refer to means of collecting information about unsold goods.

[0501] A "generative artificial intelligence model" is an artificial intelligence model used to generate cooking procedures based on acquired information.

[0502] "Display means" refers to devices or methods for visually presenting the generated cooking procedure to consumers.

[0503] "Analytical tools" are means of analyzing consumer emotions and obtaining information accordingly.

[0504] A "feedback receiving method" is a means of receiving opinions and evaluations from users.

[0505] "Improvement measures" refer to methods for improving the generation process based on the feedback received and the results of sentiment analysis.

[0506] An "electronic display device" is an electronic device used to display information in digital format.

[0507] A "portable information terminal" is an electronic device that is portable and capable of receiving and displaying information.

[0508] In this system, which is designed to implement the invention, a server, terminals, and users work together. The server is responsible for acquiring information about unsold products. Specifically, it works in conjunction with an inventory management system and collects data such as product name, classification, inventory quantity, and expiration date using APIs or database queries.

[0509] Next, the server uses a generative AI model to generate cooking instructions based on the acquired information. Natural language processing models such as "GPT-3" are used as the generative AI model. This automatically creates cooking instructions based on data of unsold products. An example of a prompt used as input to the generative AI model is, "I have leftover tomatoes and basil, so please come up with a simple cooking recipe."

[0510] The generated cooking instructions are sent from the server to a terminal. The terminal includes electronic display devices and personal digital assistants (PDAs), through which the information is presented to the user visually. For example, it can be displayed as visual advertising in the store on digital signage, or as detailed recipe information on a smartphone app.

[0511] Users can view cooking instructions presented via the device and try cooking based on recipes that interest them. The device also performs sentiment analysis, analyzing user reactions through its camera and microphone. This allows the system to understand the user's emotional state and provide data to the server to improve their interest and satisfaction.

[0512] Ultimately, users can provide feedback on the cooking process, including their opinions and impressions. This feedback information is sent to the server and used to improve the generated AI model. This makes it possible to provide cooking instructions that better meet user needs.

[0513] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0514] Step 1:

[0515] The server retrieves information about unsold products from the inventory management system. Specifically, it uses an API or database query to inquire about and collect information such as product name, category, inventory quantity, and expiration date. The input for this step is the unsold product data from the inventory management system, and the output is a list of the collected information about the relevant products.

[0516] Step 2:

[0517] The server uses a generative AI model to generate cooking instructions based on the collected product information. The input includes a list of product information and prompts for the generative AI model. For example, the prompt "I have leftover tomatoes and basil, so please come up with a simple recipe" is input to the AI ​​model. The AI ​​model performs natural language processing based on this prompt and outputs appropriate cooking instructions in text format. The output of this step is the generated cooking instructions.

[0518] Step 3:

[0519] The server sends the generated cooking instructions to the terminal. The input is the cooking instructions generated in the previous step, and the output is the cooking instructions information delivered to the terminal. The terminal includes electronic display devices and personal digital assistants, through which the cooking instructions are displayed to the user.

[0520] Step 4:

[0521] The terminal visually presents the received cooking instructions to the user. The input is the cooking instructions received from the server, and the output is the recipe information presented to the user. Specific actions include displaying detailed recipes on a smartphone app and presenting recipes on digital signage screens.

[0522] Step 5:

[0523] Users can attempt to cook based on the presented cooking instructions. Specific actions include selecting a recipe of interest and preparing to purchase the necessary ingredients. While there are no quantitative inputs or outputs here, the user's choices influence the next steps.

[0524] Step 6:

[0525] The device performs emotion analysis to analyze the user's emotions. Input includes the user's facial expressions and voice data acquired from the camera and microphone. This data is processed by an analysis algorithm, and the output is data representing the user's emotional state.

[0526] Step 7:

[0527] Users provide feedback on cooking procedures via a terminal. Input includes the user's opinions and impressions. This feedback, along with the sentiment analysis results, is sent to the server. Output is the feedback information sent to the server.

[0528] Step 8:

[0529] The server aggregates feedback data received from users and retrains the generative AI model. The input is feedback information and sentiment analysis data, and the output is the improved AI model. This ensures that future cooking procedure suggestions are more closely aligned with the user's preferences.

[0530] (Application Example 2)

[0531] 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."

[0532] The problem this invention aims to solve is to reduce food waste by efficiently utilizing unsold products, while simultaneously improving the user experience. Current systems have limited value propositions based on products that remain in inventory, and new methods are needed to further utilize them.

[0533] 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.

[0534] In this invention, the server includes information acquisition means for acquiring information related to unsold products, generation means for creating creative cooking processes based on the information, display means for visually presenting the generated cooking processes, emotion analysis means for analyzing the emotional state of the user, feedback receiving means for recording customer reactions and receiving evaluations, and adjustment means for adjusting and improving the generation means based on the customer reactions. This makes it possible to increase the added value of unsold products and make attractive proposals to a wider range of users.

[0535] "Information acquisition methods" refer to means of collecting information about unsold goods, such as the items, types, storage quantities, and expiration dates.

[0536] A "generation method" is a means for creating a new cooking process based on acquired information.

[0537] "Display means" refers to a means of visually presenting the generated cooking process to the user.

[0538] "Emotional analysis methods" are techniques for analyzing data such as a user's facial expressions and voice to identify their emotional state.

[0539] A "feedback receiving method" is a means of recording and receiving user reactions and evaluations.

[0540] "Adjustment means" refers to means for improving and adjusting the generation means based on user feedback.

[0541] The system that realizes this invention includes a series of processes for effectively utilizing unsold products and providing users with new cooking suggestions. First, the server collects data on unsold products using information acquisition means. This data includes items, types, storage quantities, and expiration dates. Next, the server uses generation means to generate creative cooking processes based on this data. It utilizes a generation AI model to convert the acquired information into cooking processes in a creative way. Here, the prompt message used is "Generate a creative and simple recipe using the stocked products. For example, generate a recipe using chicken, tomatoes, and spices."

[0542] The terminal uses a display device to visually present the generated cooking process to the user. This can be done using a smartphone or a digital display in the store. Furthermore, an emotion analysis device analyzes the user's facial expressions and voice using a digital device to identify their emotional state. This analysis utilizes emotion analysis technologies such as the Emotion API. The user's reactions are recorded and transmitted to the server via a feedback receiving device.

[0543] When a user finds a cooking process that interests them, they can purchase the necessary ingredients on the spot. User feedback serves as data for improvement. Based on this feedback, the server uses adjustment mechanisms to improve the generation process, aiming to provide recipes that better meet user expectations. This increases the added value of unsold products and enhances the customer experience in physical stores.

[0544] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0545] Step 1:

[0546] The server uses an information acquisition method to retrieve data on unsold products from the inventory management system. Inputs include information such as item name, type, storage quantity, and expiration date, while output is a dataset containing this organized information. Based on this dataset, the server prepares to determine what kinds of dishes can be prepared using it.

[0547] Step 2:

[0548] The server inputs the prompt message "Generate a creative and simple recipe using inventory items. For example, generate a recipe using chicken, tomatoes, and spices." into the generation AI model, which is the generation means, and generates cooking steps. The input consists of the prompt message and pre-processed data on unsold items, and the AI ​​model performs data calculations based on this data to output a new cooking step.

[0549] Step 3:

[0550] The terminal uses a display mechanism to visually present the generated cooking process to the user. The cooking process is displayed as visual information on devices such as smartphones and tablets, making it easy for the user to understand. The input is the generated cooking process, and the output is the visual information presented to the user.

[0551] Step 4:

[0552] The device uses emotion analysis techniques to collect the user's facial expressions and voice using a camera and microphone, and analyzes their emotional state using technologies such as the Emotion API. The input is emotional data from the user, and the output is the analyzed emotional state. This information is transmitted to the server in real time.

[0553] Step 5:

[0554] The user inputs feedback on cooking processes they are interested in via a terminal, and this information is sent to the server through a feedback receiving device. The input is the feedback entered by the user, and the output is the feedback data sent to the server.

[0555] Step 6:

[0556] Based on the feedback, the server adjusts the generative AI model using adjustment mechanisms, aiming to generate even more appropriate cooking processes. The input is user feedback data, which is used to adjust the generative mechanisms, and the output is the improved generative model.

[0557] 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.

[0558] 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.

[0559] 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.

[0560] [Fourth Embodiment]

[0561] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0562] 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.

[0563] 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).

[0564] 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.

[0565] 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.

[0566] 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).

[0567] 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.

[0568] 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.

[0569] 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.

[0570] 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.

[0571] 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.

[0572] 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.

[0573] 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".

[0574] To implement this invention, a system is constructed in which three entities—a server, a terminal, and a user—work in cooperation.

[0575] First, the server connects with the inventory management system to collect data on unsold products in real time. This provides information on the current inventory status and product expiration dates. Based on this data, the server uses a generative AI model to automatically generate cooking instructions that utilize the unsold products. For example, if there is a large amount of tomatoes and cheese in stock, it can generate a cooking instruction for "Caprese Salad with Tomatoes and Cheese."

[0576] Next, the terminal receives cooking instructions sent from the server and displays them on in-store display devices and the customer's smartphone app. The in-store display devices use visually-oriented presentations to attract the consumer's attention. The smartphone app provides detailed recipe information for users to refer to at any time, displaying the necessary ingredients and cooking steps.

[0577] Users can review the provided cooking instructions and purchase the necessary ingredients. After trying the recipe at home, users can submit feedback via their device. This feedback includes evaluations of the taste of the dish and the difficulty of the process.

[0578] Finally, the server analyzes the collected feedback data and uses it as training data to improve the generated AI model. This improves the overall accuracy of the system so that the cooking instructions generated in the future are more in line with customer preferences. By repeating this cycle, it is possible to sustainably achieve effective utilization of unsold products and improved customer satisfaction.

[0579] The following describes the processing flow.

[0580] Step 1:

[0581] The server accesses the inventory management system via an API to retrieve inventory data for unsold items and other necessary products. This data includes important information such as product name, category, inventory quantity, and expiration date.

[0582] Step 2:

[0583] The server inputs the acquired unsold product data into a generating AI model. This model uses natural language processing and machine learning techniques to generate appropriate cooking procedures based on combinations of unsold products. For example, it can devise new menus using leftover ingredients.

[0584] Step 3:

[0585] The server sends the generated cooking instructions to the terminal. These instructions include a list of required ingredients, cooking time, and step-by-step cooking instructions.

[0586] Step 4:

[0587] The terminal displays cooking instructions received from the server on digital signage in the store and on a smartphone app. The digital signage shows recipes with eye-catching images and text, while the smartphone app allows users to check details and save the recipes.

[0588] Step 5:

[0589] Users can review the presented cooking instructions and add the necessary ingredients to their cart if they are interested. Furthermore, users can try cooking at home based on the recipes displayed on the smartphone app.

[0590] Step 6:

[0591] After a user tries a recipe, they send feedback about it via their device. This feedback includes information such as the difficulty level of the recipe, the taste, and suggestions for improvement.

[0592] Step 7:

[0593] The server stores and analyzes the collected feedback data in a database. This data is used to retrain the generative AI model, improving the accuracy of future recipe suggestions. The goal is to generate new recipes that are better suited to the user's preferences based on the feedback.

[0594] (Example 1)

[0595] 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".

[0596] The increasing amount of unsold goods presents significant challenges, including inventory management, waste management, and the resulting increase in costs. Furthermore, a lack of recipe suggestions tailored to consumer preferences is hindering effective product consumption. Therefore, there is a need for a system that effectively utilizes inventory while automatically generating cooking suggestions that meet consumer needs.

[0597] 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.

[0598] In this invention, the server includes a data collection means for acquiring data on unsold products, a generation means using artificial intelligence to automatically generate cooking procedures based on the data, and a means for presenting the generated cooking procedures via an information display means. This enables the effective use of inventory and improved consumer satisfaction by collecting data on unsold products in real time and efficiently generating and providing cooking procedures based on that data.

[0599] "Unsold goods" refer to products that have not been sold in the market and remain as inventory, and which may be discarded.

[0600] "Data collection means" refers to functions and devices for acquiring and aggregating information about inventory and unsold goods.

[0601] "Generation means" refers to a function or system that uses artificial intelligence to automatically generate cooking procedures from the collected data.

[0602] "Information display means" refers to devices or software that visually present the generated cooking instructions to consumers.

[0603] "Feedback collection methods" refer to functions or devices for receiving feedback, evaluations, and other reactions from consumers.

[0604] "Information analysis and learning tools" refer to functions and systems for analyzing feedback and improving or adjusting the accuracy of generation tools.

[0605] This system is built around three main components: a server, terminals, and users, each working in cooperation with the others. First, the server integrates with the inventory management system to collect real-time data on unsold goods. Inventory management software is used for this data collection, obtaining information on the inventory status and expiration dates of unsold items. Specifically, the server retrieves this information from a database and utilizes artificial intelligence technology to process it.

[0606] The server uses a generative AI model to automatically generate cooking instructions from collected data on unsold products. This AI model includes models that utilize natural language processing techniques. Specific examples of the AI ​​models used include commonly used language generation models, which have the ability to generate new content based on input data. As an example of a specific cooking instruction to be generated, if the prompt message is "There are 50 tomatoes and 20 packs of cheese in stock," it is possible to automatically generate a recipe for "Caprese salad with tomatoes and cheese."

[0607] Next, the terminal receives cooking instructions transmitted from the server and displays the suggested recipe on in-store display devices and the consumer's smartphone application. The in-store display devices are expected to utilize a digital signage system to provide visually appealing information. The smartphone application displays detailed recipe information, allowing users to check the necessary ingredients and cooking steps.

[0608] Users check the cooking instructions displayed on their device and apply the provided information to their daily lives. They can try out the suggested recipes by purchasing the necessary ingredients and cooking at home. After cooking, they can send feedback through their device, including their evaluation of the taste of the dish and their opinions on the cooking process.

[0609] Ultimately, the server collects and analyzes this feedback data to improve the generated AI model. This analysis utilizes data analysis tools, incorporating the results obtained from the feedback as training data for the model. Through this entire process, the system is continuously improved, and the generated cooking instructions are adjusted to better suit consumer preferences.

[0610] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0611] Step 1:

[0612] The server interacts with the inventory management system to retrieve real-time data on unsold items. This data includes product name, inventory quantity, and expiration date. The server retrieves this information via the inventory management software's API and stores it in a database. The input data is a list of products provided by the inventory system, and the output is an organized inventory database.

[0613] Step 2:

[0614] The server generates prompt statements based on the collected inventory data and inputs them into the generative AI model. The input prompt statements are in the format of "There are 50 tomatoes and 20 packs of cheese." The server creates these prompt statements and passes them to the generative AI model. The data processing performed here is the process of converting inventory information into natural language, and the output is a suggestion of cooking procedures.

[0615] Step 3:

[0616] The server sends cooking instructions derived from the output of the generated AI model to the terminal. These instructions include the necessary ingredients and specific cooking steps. The terminal then reformats this into a format suitable for in-store display devices and smartphone applications. The output is visually appealing recipe information.

[0617] Step 4:

[0618] The terminal receives cooking instructions sent from the server and displays them on in-store digital signage and a smartphone app. Users can then review the cooking instructions and purchase the necessary ingredients through this display. The terminal dynamically updates the digital content based on user input. The output is detailed recipe information available to consumers.

[0619] Step 5:

[0620] After a user cooks a meal at home, they submit feedback via their device. The application allows users to input their opinions on the taste, cooking time, and difficulty of the dish into a feedback form. The input is the user's rating, and the output is feedback data sent to the server.

[0621] Step 6:

[0622] The server collects user feedback data and analyzes it using data analysis tools. This analysis includes processing the text data of the feedback to identify frequently mentioned keywords and evaluations. The input is user feedback, and the output is training data used to improve the generative AI model. The server uses this to improve the accuracy of the AI ​​model.

[0623] (Application Example 1)

[0624] 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".

[0625] Unsold products in physical stores pose inventory management challenges and contribute to decreased profitability. Furthermore, the lack of new recipe suggestions for consumers makes it difficult to improve customer satisfaction. Therefore, there is a need for a system that can effectively utilize unsold products and sustainably provide attractive services to consumers.

[0626] 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.

[0627] In this invention, the server includes an information acquisition means for acquiring attributes of unsold products, a generation mechanism for generating cooking procedures based on the acquired attributes, and a presentation mechanism for presenting the generated cooking procedures to the consumer's communication terminal. This makes it possible to generate cooking procedures in real time based on the attributes of unsold products and to instantly provide consumers with new cooking suggestions.

[0628] "Unsold product attributes" refer to data that indicates specific characteristics of products that remain in inventory, such as identification information, classification information, quantity, and expiration date.

[0629] "Information acquisition means" refers to a mechanism for collecting data on the attributes of unsold products and supplying it to the system.

[0630] A "generation mechanism" is a device that manages the process of creating new value by designing cooking procedures and suggestions based on acquired information.

[0631] A "presentation mechanism" refers to a device and method for displaying and appropriately presenting the generated cooking instructions on a consumer's communication terminal.

[0632] A "feedback receiving mechanism" is a device and method for receiving feedback information from consumers, and for analyzing and processing it.

[0633] The "improvement mechanism" is a mechanism that reviews the system's generation method based on the received feedback information, and aims to optimize and improve it.

[0634] To implement this invention, a system is constructed in which three entities—a server, a terminal, and a consumer—work in cooperation.

[0635] The server first uses an information retrieval mechanism to collect attributes of unsold products from a database. This data includes product identification, category, inventory quantity, and expiration date. The collected information is then analyzed by a generative AI model to design cooking instructions to suggest to consumers. This generative AI model uses advanced natural language processing techniques; for example, if tomatoes and basil are in stock, it can generate a new recipe such as "Tomato and Basil Pasta."

[0636] The terminal receives cooking instructions sent from the server and displays them on the consumer's communication device. The application runs on iOS and Android smartphones and provides generated recipes in real time. By using this application, consumers can check the suggested new recipes and immediately purchase the necessary ingredients at the store.

[0637] After consumers prepare a dish based on a recipe, they send feedback to the server through an evaluation receiving mechanism. This feedback includes items such as the quality of the dish and their understanding of the procedure. Based on this, the server's improvement mechanism improves the generated AI model and uses it to create future suggestions. An example of a specific prompt is, "Please suggest a new Italian recipe using tomatoes and basil."

[0638] This approach allows consumers to utilize unsold products, creating new value and improving customer satisfaction.

[0639] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0640] Step 1:

[0641] The server retrieves unsold product attributes from the inventory management database. It uses database connection information from the inventory management system as input and outputs unsold product attribute data including product identification, category, inventory quantity, and expiration date. This step involves extracting the necessary data using database queries.

[0642] Step 2:

[0643] The server runs an AI model based on the attributes of unsold products to design cooking procedures. The product attribute data obtained in step 1 is used as input. The output generates cooking procedures and recipes based on this data. Specifically, it generates a prompt message for the AI ​​model, "Please suggest a new Italian recipe using tomatoes and basil," and uses natural language processing technology to create new cooking suggestions.

[0644] Step 3:

[0645] The server sends the generated cooking instructions to the terminal. It uses the recipe data generated in step 2 as input. As output, it sends the cooking instructions data to the terminal. Specifically, it performs communication processing to send data via API calls or messaging protocols.

[0646] Step 4:

[0647] The terminal displays the received cooking instructions on the consumer's communication device. It uses the data sent in step 3 as input and displays the recipe on the user interface as output. Specifically, it uses the GUI display function of a smartphone app to allow consumers to easily view the recipe.

[0648] Step 5:

[0649] Users try cooking a dish based on the cooking instructions and input the results as feedback into their device. Consumer evaluation information is collected as input, and the collected feedback data is generated as output. Specifically, the process involves collecting information entered in the feedback form of the smartphone app.

[0650] Step 6:

[0651] The server improves the generated AI model based on the feedback information received from the terminal. It uses the feedback data obtained in step 5 as input and obtains the improved AI model as output. Specifically, it uses the feedback data as training data and performs data analysis and model optimization processing to retrain the AI ​​model.

[0652] 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.

[0653] The embodiment of this invention consists of a system configuration centered on a server, terminal, and user, and in particular, by combining it with an emotion engine, it provides a more advanced user experience.

[0654] First, the server collects data on unsold products from the inventory management system. This data includes information such as product name, category, inventory quantity, and expiration date. Based on this information, the server uses an AI model as a generation tool to generate cooking instructions using the unsold products.

[0655] Once the cooking instructions are generated, the server sends them to a terminal. The terminal can be a digital signage display in the store or a user's smartphone app. The terminal visually presents the received cooking instructions to the user and provides detailed instructions.

[0656] During this process, the emotion engine analyzes the user's reactions. Assuming a scenario where the user is operating a smartphone app, it analyzes the user's facial expressions and voice through the camera and microphone to identify their emotions. For example, if the user shows interest or confusion, this emotional state is sent to the server as feedback.

[0657] Based on the provided cooking instructions, users can purchase the necessary ingredients if they find a dish that interests them. Users can also provide feedback and sentiment data about the dishes they have tried through their device.

[0658] The server receives user ratings and sentiment analysis results as a means of receiving feedback and stores them in a database. Furthermore, as part of the improvement process, the server aims to retrain the generative AI model to provide more appropriate cooking instructions that take user sentiment data into account. This will improve the accuracy of recipe suggestions and create a system that better meets user expectations.

[0659] The following describes the processing flow.

[0660] Step 1:

[0661] The server works in conjunction with the inventory management system to retrieve data on unsold products. This data includes product name, category, inventory quantity, and expiration date.

[0662] Step 2:

[0663] The server inputs data on unsold products into an AI model that generates cooking instructions. This model utilizes combinations of products in the data to create appealing recipes. For example, if there are leftover tomatoes and pasta, it will devise a recipe for tomato sauce pasta.

[0664] Step 3:

[0665] The server sends the generated cooking instructions to a terminal. This terminal includes in-store digital signage and smartphone apps, providing users with a means to visually obtain information.

[0666] Step 4:

[0667] The terminal displays the received cooking instructions on digital signage. Additionally, a smartphone app provides detailed steps and a list of necessary ingredients, guiding the user through the cooking process.

[0668] Step 5:

[0669] The device uses its built-in camera and microphone to collect facial expressions and voices as the user views or selects cooking instructions. This allows the emotion engine to analyze the user's reactions and identify their emotions. For example, if the user smiles, it is recorded as a positive emotion.

[0670] Step 6:

[0671] Based on the information provided, users can purchase ingredients for recipes that interest them and actually cook them at home. During this process, they send feedback via their device regarding their reactions and feelings towards the presented information.

[0672] Step 7:

[0673] The server receives user feedback and sentiment data sent from the terminal and stores it in a database.

[0674] Step 8:

[0675] As a means of improvement, the server analyzes the collected feedback data and retrains the generative AI model. In this process, the results of sentiment analysis are taken into consideration, and the system's accuracy is improved so that it can provide cooking instructions that better match the user's preferences.

[0676] (Example 2)

[0677] 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".

[0678] Traditional inventory management methods have limitations in effectively utilizing unsold products, and it has been difficult to make suggestions that meet consumer interests and preferences. Furthermore, the mechanisms for quickly incorporating consumer feedback have been insufficient, making it necessary to realize a more refined consumer experience.

[0679] 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.

[0680] In this invention, the server includes an information acquisition means for acquiring information about unsold products, a generation means for using a generative artificial intelligence model to generate cooking procedures based on the acquired information, and a display means for visually presenting the generated cooking procedures. This enables the effective utilization of unsold products and the provision of personalized cooking procedures to consumers.

[0681] "Information acquisition methods" refer to means of collecting information about unsold goods.

[0682] A "generative artificial intelligence model" is an artificial intelligence model used to generate cooking procedures based on acquired information.

[0683] "Display means" refers to devices or methods for visually presenting the generated cooking procedure to consumers.

[0684] "Analytical tools" are means of analyzing consumer emotions and obtaining information accordingly.

[0685] A "feedback receiving method" is a means of receiving opinions and evaluations from users.

[0686] "Improvement measures" refer to methods for improving the generation process based on the feedback received and the results of sentiment analysis.

[0687] An "electronic display device" is an electronic device used to display information in digital format.

[0688] A "portable information terminal" is an electronic device that is portable and capable of receiving and displaying information.

[0689] In this system, which is designed to implement the invention, a server, terminals, and users work together. The server is responsible for acquiring information about unsold products. Specifically, it works in conjunction with an inventory management system and collects data such as product name, classification, inventory quantity, and expiration date using APIs or database queries.

[0690] Next, the server uses a generative AI model to generate cooking instructions based on the acquired information. Natural language processing models such as "GPT-3" are used as the generative AI model. This automatically creates cooking instructions based on data of unsold products. An example of a prompt used as input to the generative AI model is, "I have leftover tomatoes and basil, so please come up with a simple cooking recipe."

[0691] The generated cooking instructions are sent from the server to a terminal. The terminal includes electronic display devices and personal digital assistants (PDAs), through which the information is presented to the user visually. For example, it can be displayed as visual advertising in the store on digital signage, or as detailed recipe information on a smartphone app.

[0692] Users can view cooking instructions presented via the device and try cooking based on recipes that interest them. The device also performs sentiment analysis, analyzing user reactions through its camera and microphone. This allows the system to understand the user's emotional state and provide data to the server to improve their interest and satisfaction.

[0693] Ultimately, users can provide feedback on the cooking process, including their opinions and impressions. This feedback information is sent to the server and used to improve the generated AI model. This makes it possible to provide cooking instructions that better meet user needs.

[0694] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0695] Step 1:

[0696] The server retrieves information about unsold products from the inventory management system. Specifically, it uses an API or database query to inquire about and collect information such as product name, category, inventory quantity, and expiration date. The input for this step is the unsold product data from the inventory management system, and the output is a list of the collected information about the relevant products.

[0697] Step 2:

[0698] The server uses a generative AI model to generate cooking instructions based on the collected product information. The input includes a list of product information and prompts for the generative AI model. For example, the prompt "I have leftover tomatoes and basil, so please come up with a simple recipe" is input to the AI ​​model. The AI ​​model performs natural language processing based on this prompt and outputs appropriate cooking instructions in text format. The output of this step is the generated cooking instructions.

[0699] Step 3:

[0700] The server sends the generated cooking instructions to the terminal. The input is the cooking instructions generated in the previous step, and the output is the cooking instructions information delivered to the terminal. The terminal includes electronic display devices and personal digital assistants, through which the cooking instructions are displayed to the user.

[0701] Step 4:

[0702] The terminal visually presents the received cooking instructions to the user. The input is the cooking instructions received from the server, and the output is the recipe information presented to the user. Specific actions include displaying detailed recipes on a smartphone app and presenting recipes on digital signage screens.

[0703] Step 5:

[0704] Users can attempt to cook based on the presented cooking instructions. Specific actions include selecting a recipe of interest and preparing to purchase the necessary ingredients. While there are no quantitative inputs or outputs here, the user's choices influence the next steps.

[0705] Step 6:

[0706] The device performs emotion analysis to analyze the user's emotions. Input includes the user's facial expressions and voice data acquired from the camera and microphone. This data is processed by an analysis algorithm, and the output is data representing the user's emotional state.

[0707] Step 7:

[0708] Users provide feedback on cooking procedures via a terminal. Input includes the user's opinions and impressions. This feedback, along with the sentiment analysis results, is sent to the server. Output is the feedback information sent to the server.

[0709] Step 8:

[0710] The server aggregates feedback data received from users and retrains the generative AI model. The input is feedback information and sentiment analysis data, and the output is the improved AI model. This ensures that future cooking procedure suggestions are more closely aligned with the user's preferences.

[0711] (Application Example 2)

[0712] 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".

[0713] The problem this invention aims to solve is to reduce food waste by efficiently utilizing unsold products, while simultaneously improving the user experience. Current systems have limited value propositions based on products that remain in inventory, and new methods are needed to further utilize them.

[0714] 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.

[0715] In this invention, the server includes information acquisition means for acquiring information related to unsold products, generation means for creating creative cooking processes based on the information, display means for visually presenting the generated cooking processes, emotion analysis means for analyzing the emotional state of the user, feedback receiving means for recording customer reactions and receiving evaluations, and adjustment means for adjusting and improving the generation means based on the customer reactions. This makes it possible to increase the added value of unsold products and make attractive proposals to a wider range of users.

[0716] "Information acquisition methods" refer to means of collecting information about unsold goods, such as the items, types, storage quantities, and expiration dates.

[0717] A "generation method" is a means for creating a new cooking process based on acquired information.

[0718] "Display means" refers to a means of visually presenting the generated cooking process to the user.

[0719] "Emotional analysis methods" are techniques for analyzing data such as a user's facial expressions and voice to identify their emotional state.

[0720] A "feedback receiving method" is a means of recording and receiving user reactions and evaluations.

[0721] "Adjustment means" refers to means for improving and adjusting the generation means based on user feedback.

[0722] The system that realizes this invention includes a series of processes for effectively utilizing unsold products and providing users with new cooking suggestions. First, the server collects data on unsold products using information acquisition means. This data includes items, types, storage quantities, and expiration dates. Next, the server uses generation means to generate creative cooking processes based on this data. It utilizes a generation AI model to convert the acquired information into cooking processes in a creative way. Here, the prompt message used is "Generate a creative and simple recipe using the stocked products. For example, generate a recipe using chicken, tomatoes, and spices."

[0723] The terminal uses a display device to visually present the generated cooking process to the user. This can be done using a smartphone or a digital display in the store. Furthermore, an emotion analysis device analyzes the user's facial expressions and voice using a digital device to identify their emotional state. This analysis utilizes emotion analysis technologies such as the Emotion API. The user's reactions are recorded and transmitted to the server via a feedback receiving device.

[0724] When a user finds a cooking process that interests them, they can purchase the necessary ingredients on the spot. User feedback serves as data for improvement. Based on this feedback, the server uses adjustment mechanisms to improve the generation process, aiming to provide recipes that better meet user expectations. This increases the added value of unsold products and enhances the customer experience in physical stores.

[0725] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0726] Step 1:

[0727] The server uses an information acquisition method to retrieve data on unsold products from the inventory management system. Inputs include information such as item name, type, storage quantity, and expiration date, while output is a dataset containing this organized information. Based on this dataset, the server prepares to determine what kinds of dishes can be prepared using it.

[0728] Step 2:

[0729] The server inputs the prompt message "Generate a creative and simple recipe using inventory items. For example, generate a recipe using chicken, tomatoes, and spices." into the generation AI model, which is the generation means, and generates cooking steps. The input consists of the prompt message and pre-processed data on unsold items, and the AI ​​model performs data calculations based on this data to output a new cooking step.

[0730] Step 3:

[0731] The terminal uses a display mechanism to visually present the generated cooking process to the user. The cooking process is displayed as visual information on devices such as smartphones and tablets, making it easy for the user to understand. The input is the generated cooking process, and the output is the visual information presented to the user.

[0732] Step 4:

[0733] The device uses emotion analysis techniques to collect the user's facial expressions and voice using a camera and microphone, and analyzes their emotional state using technologies such as the Emotion API. The input is emotional data from the user, and the output is the analyzed emotional state. This information is transmitted to the server in real time.

[0734] Step 5:

[0735] The user inputs feedback on cooking processes they are interested in via a terminal, and this information is sent to the server through a feedback receiving device. The input is the feedback entered by the user, and the output is the feedback data sent to the server.

[0736] Step 6:

[0737] Based on the feedback, the server adjusts the generative AI model using adjustment mechanisms, aiming to generate even more appropriate cooking processes. The input is user feedback data, which is used to adjust the generative mechanisms, and the output is the improved generative model.

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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."

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] The following is further disclosed regarding the embodiments described above.

[0760] (Claim 1)

[0761] A data acquisition method for obtaining data on unsold products,

[0762] A generation means for generating cooking procedures based on the acquired data,

[0763] A presentation means for presenting the generated cooking procedure,

[0764] A means of receiving feedback from customers,

[0765] An improvement means for improving the generation means based on the evaluation,

[0766] A system that includes this.

[0767] (Claim 2)

[0768] The system according to claim 1, wherein the display means includes a power display device and an information terminal.

[0769] (Claim 3)

[0770] The system according to claim 1, wherein the unsold product data includes product name, category, inventory quantity, and expiration date.

[0771] "Example 1"

[0772] (Claim 1)

[0773] A data collection method for obtaining data on unsold products,

[0774] A generation means using artificial intelligence to automatically generate cooking procedures based on the aforementioned data,

[0775] A means for presenting the generated cooking procedure via an information display means,

[0776] A means of collecting feedback to receive customer opinions and evaluations,

[0777] Information analysis and learning means to improve the generation means based on the received feedback,

[0778] A system that includes this.

[0779] (Claim 2)

[0780] The system according to claim 1, wherein the information display means includes a display device and a portable information terminal within the store.

[0781] (Claim 3)

[0782] The system according to claim 1, wherein the unsold product data includes item name, type, inventory quantity, and expiration date.

[0783] "Application Example 1"

[0784] (Claim 1)

[0785] Information acquisition methods for obtaining attributes of unsold products,

[0786] A generation mechanism that generates cooking procedures based on the acquired attributes,

[0787] A presentation mechanism that presents the generated cooking procedure to the consumer's communication terminal,

[0788] An evaluation receiving mechanism that receives feedback information from consumers,

[0789] An improved mechanism for improving the generation mechanism based on the feedback information,

[0790] A system that includes this.

[0791] (Claim 2)

[0792] The system according to claim 1, wherein the presentation mechanism includes a display device and a portable information terminal.

[0793] (Claim 3)

[0794] The system according to claim 1, wherein the attributes of unsold goods include product identification, category, inventory quantity, and expiration date.

[0795] "Example 2 of combining an emotion engine"

[0796] (Claim 1)

[0797] Information acquisition methods for obtaining information about unsold products,

[0798] A generation means that uses a generation artificial intelligence model to generate cooking procedures based on the acquired information,

[0799] A display means for visually presenting the generated cooking procedure,

[0800] An analytical means for performing emotion analysis in order to analyze the emotions of users,

[0801] A means of receiving feedback from users,

[0802] An improvement means for improving the generation means based on the aforementioned opinion and sentiment analysis,

[0803] A system that includes this.

[0804] (Claim 2)

[0805] The system according to claim 1, wherein the display means includes an electronic display device and a portable information terminal.

[0806] (Claim 3)

[0807] The system according to claim 1, wherein the information relating to the unsold goods includes the product name, classification, inventory quantity, and expiration date.

[0808] "Application example 2 of combining emotional engines"

[0809] (Claim 1)

[0810] Information acquisition methods for obtaining information related to unsold products,

[0811] A generating means for creating a creative cooking process based on the aforementioned information,

[0812] A display means for visually presenting the generated cooking process,

[0813] A means of analyzing the emotional state of a user,

[0814] A means of receiving feedback that records customer reactions and receives evaluations,

[0815] An adjustment means for adjusting and improving the generation means based on the customer's response,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, wherein the display means includes a display device and a portable device that provide visual information.

[0819] (Claim 3)

[0820] The system according to claim 1, wherein the information relating to the unsold goods includes item, type, storage quantity, and expiration date. [Explanation of Symbols]

[0821] 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 data acquisition method for obtaining data on unsold products, A generation means for generating cooking procedures based on the acquired data, A presentation means for presenting the generated cooking procedure, A means of receiving feedback from customers, An improvement means for improving the generation means based on the evaluation, A system that includes this.

2. The system according to claim 1, wherein the display means includes a power display device and an information terminal.

3. The system according to claim 1, wherein the unsold product data includes product name, category, inventory quantity, and expiration date.

Images