system

Abstract

We provide the system. [Solution] An input method for entering ingredient information, A generation means for generating cooking procedures based on the aforementioned ingredient information, A means of collecting price information from multiple available retailers, A recommendation system that analyzes collected price information and recommends the retailer with the lowest price, 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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Determining a menu and purchasing ingredients in cooking are time-consuming and laborious tasks for consumers, and it is not easy to purchase ingredients at an appropriate price from a plurality of stores. Therefore, a system that can cook efficiently and economically within limited time and budget is desired.

Means for Solving the Problems

[0005] The present invention provides a system that improves the efficiency and economy of cooking by including an input means for inputting information on ingredients possessed by a consumer, a generation means for automatically generating cooking procedures based on the input information, a collection means for collecting and analyzing price information of a plurality of stores in a region, and a recommendation means for recommending the cheapest store from the analysis results.

[0006] "Food ingredient information" refers to data that shows the specific types, quantities, and other related characteristics of food items that consumers possess.

[0007] "Input means" refers to the interface or device that allows users to provide ingredient information to the system.

[0008] A "generation method" is a function that automatically creates cooking procedures and recipes using AI and other technologies based on the input ingredient information.

[0009] "Collection methods" refer to the functions and protocols used to obtain information on food prices and inventory from local retailers.

[0010] "Recommendation methods" refer to functions that analyze collected price information and suggest the best place to buy to consumers.

[0011] A "system" is a collection of devices or software that integrates the input of ingredient information, generation of cooking procedures, collection of price information, and recommendation. [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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface that includes 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] The system according to the present invention suggests recipes based on the ingredient information owned by the consumer user, and also recommends the most economical ingredients that can be purchased from nearby stores.

[0034] First, the user uses a terminal to enter the current ingredient inventory. This information is entered using a list-based interface. The terminal is implemented to send the entered ingredient information to the server.

[0035] Next, the server analyzes the received ingredient information and uses a pre-trained AI model to generate cooking instructions that make the most of the input ingredients. This generated recipe aims to broaden the user's culinary horizons by enabling multiple cooking steps and the creation of new dishes. The server then sends this generated recipe to the terminal for display to the user.

[0036] Furthermore, the server collects up-to-date price information for necessary additional ingredients by crawling APIs and publicly available websites of local retailers. From this information, the server identifies the cheapest retailer and selects recommended ingredients and their retailers. The recommended results are displayed on the user's device, enabling them to create an efficient and economical purchasing plan. In this way, the system contributes to the efficient use and economical consumption of ingredients.

[0037] For example, if a user enters "chicken, carrots, and potatoes," the server will suggest "chicken stew" and recommend the cheapest store offering "onions" based on price information obtained via the internet. This implementation supports users in both discovering new recipes and reducing costs in their daily cooking.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The user enters information about the ingredients they own using the terminal's interface. The terminal organizes the entered information in a list format and displays it for the user to review.

[0041] Step 2:

[0042] The terminal converts the organized ingredient information into data packets, encrypts them using a security protocol, and then sends them to the server.

[0043] Step 3:

[0044] The server analyzes the received ingredient information and uses an AI model to generate cooking instructions using those ingredients. The generated cooking instructions may include multiple options, providing users with a variety of cooking methods.

[0045] Step 4:

[0046] The server sends the generated cooking instructions to the terminal, which then displays the instructions to the user. The user can review the displayed instructions and select or modify them as needed.

[0047] Step 5:

[0048] The server accesses the APIs or websites of local retailers to collect price information for any additional ingredients needed. The collected price information is stored in the server's database.

[0049] Step 6:

[0050] The server analyzes the collected price information to identify the retailer where the product can be purchased at the lowest price. The identified retailer's information, along with details of any additional ingredients, is listed.

[0051] Step 7:

[0052] The server sends information about the cheapest retailer it has identified to the terminal, which then displays it to the user. Based on the information presented, the user can then plan an efficient shopping trip.

[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] In home cooking, there are challenges in efficiently utilizing limited ingredients and purchasing necessary ingredients economically. These challenges need to be addressed to reduce food waste and lower household expenses.

[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 an input device for receiving ingredient inventory information, a generation device using a generation AI to generate cooking instructions based on the ingredient inventory information, and an acquisition device for obtaining price data from multiple supply sources in the region. This allows the user to obtain cooking instructions that make the most of the ingredients they own and to choose the most economical way to purchase the necessary ingredients.

[0058] "Ingredient inventory information" refers to information about the types and quantities of ingredients that the user currently possesses.

[0059] An "input device" is a device or interface used by users to input food inventory information.

[0060] "Generative AI" is an artificial intelligence system that uses a pre-trained model to generate optimal cooking instructions from given ingredient information.

[0061] A "generation device" is a device that uses a generation AI to generate cooking instructions based on the input information.

[0062] An "acquisition device" is a device that collects price data from multiple supply sources in a region.

[0063] A "selection device" is a device that analyzes acquired price data, identifies the source of the lowest price, and proposes it.

[0064] An "output device" is a device or interface for presenting the generated cooking instructions to the user.

[0065] This invention is a system that assists users in managing and purchasing ingredients for home cooking. The user inputs information about the ingredients they currently own using a terminal. The terminal then transmits this ingredient inventory information to a server. The input device used here is a digital device such as a PC or smartphone.

[0066] The server analyzes the received ingredient information and generates cooking instructions using a pre-trained generative AI model. This generative AI model is an artificial intelligence trained on a large-scale recipe dataset and proposes specific cooking steps using the ingredients entered by the user. An example of a prompt is, "Please tell me a recipe that can be made using chicken, carrots, and potatoes."

[0067] Furthermore, the server collects price data from multiple local supply sources via the internet. The collected price data is analyzed to identify the most economical supply source, and a selection device identifies the source with the lowest price. The identified information is transmitted from the server to the terminal, which then makes optimal purchase suggestions to the user.

[0068] For example, if a user inputs that they own "chicken, carrots, and potatoes," the server will generate a recipe for "chicken stew." It will also suggest a source that provides "onions" at the lowest price as an additional ingredient. In this way, users can try new dishes without wasting ingredients and shop cost-effectively.

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

[0070] Step 1:

[0071] The user uses a terminal to input the type and quantity of ingredients they possess through the interface. The input information is specific ingredient data, such as "chicken, carrots, potatoes." The terminal sends the entered ingredient information to the server in JSON format. HTTP POST requests are used in this process.

[0072] Step 2:

[0073] The server analyzes the received ingredient information. Specifically, it analyzes the JSON data and extracts the ingredient names and quantities. This data processing creates input prompts for the AI ​​model. Upon receiving these prompts, the generating AI model processes a recipe request in the format of "Please tell me a recipe that can be made using chicken, carrots, and potatoes," and generates the optimal cooking instructions.

[0074] Step 3:

[0075] The server sends the generated cooking instructions back to the terminal. The generated recipe is sent in a format that the terminal can receive (e.g., text format) and processed as an HTTP response. The terminal displays the received recipe to the user. The user can check the specific cooking instructions displayed on the screen and use them to help with cooking.

[0076] Step 4:

[0077] The server collects price data from multiple local suppliers (e.g., supermarkets and online stores). In this process, it uses APIs provided by the suppliers to obtain the latest price information for the required ingredients (e.g., "onions"). HTTP GET requests are used for this purpose.

[0078] Step 5:

[0079] The server analyzes the collected price data to identify the cheapest supply source. Based on the analyzed data, a selection algorithm is executed to determine the cheapest supply source to recommend to the user. The analysis results are prepared as recommendation information, including the name of the supply source and price information.

[0080] Step 6:

[0081] The server sends information about the lowest-priced source identified to the terminal. The terminal then displays efficient and economical purchasing information to the user. As a result, the user can plan their purchases based on the information presented.

[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] Modern consumers find it difficult to plan economical and efficient grocery purchases while effectively utilizing the ingredients they already own. Furthermore, they often lack diverse cooking suggestions, limiting the ways in which they use individual ingredients. Additionally, the lack of readily available and effective ways to access discount information at physical stores restricts the consumer's purchasing experience.

[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 input means for inputting ingredient information, a generation means for generating food preparation processes based on the ingredient information, a collection means for collecting price information from multiple available retail stores, a recommendation means for analyzing the collected price information and recommending the retail store with the lowest price, and an acquisition means for users to obtain discount information in real time at physical stores via a mobile information terminal. As a result, consumers can be offered dishes that make the most of the ingredients they have, and can plan to purchase any additional ingredients they need at the most economical price. Furthermore, they can obtain discount information instantly at physical stores, enabling efficient purchasing.

[0087] "Food ingredient information" refers to data about the specific types and quantities of food items that the user owns.

[0088] "Input means" refers to devices or interfaces that users use to input ingredient information into the system.

[0089] A "food preparation process" is a series of cooking methods and procedures generated based on the inputted ingredient information.

[0090] "Generation means" refers to devices or programs that utilize ingredient information to generate food preparation processes.

[0091] "Retail stores" refer to stores and commercial facilities that sell food and other daily necessities.

[0092] "Means of collection" refers to devices or systems used to collect information on prices and inventory from retail stores.

[0093] A "recommendation tool" is a processing device or program that analyzes collected price information and presents the most economical option.

[0094] A "personal digital assistant" is an electronic device that a user can carry with them, and includes smartphones, tablets, and other similar devices.

[0095] "Means of acquisition" refers to methods and systems that allow users to obtain real-time discount information from physical stores via their mobile devices.

[0096] To implement this system, the server and user terminals primarily cooperate in processing data. The server handles inputting ingredient information, generating food preparation processes, collecting and analyzing price information, and recommending optimal purchasing plans.

[0097] First, the user's device provides an interface for inputting information about the ingredients the user owns. This ingredient information is formatted in a data format such as JSON and sent to a cloud-based database (e.g., GOOGLE FI® rebase).

[0098] Information sent from the terminal is received on the server using Python and the Flask framework and stored in a database. The server then uses a generative AI model trained with TENSORFLOW® to generate food preparation processes based on the input ingredient information. This expands the range of dishes the user can cook.

[0099] Next, the server uses tools such as BeautifulSoup to collect price information from retail store websites and APIs. The collected information is analyzed within the server to identify the most economical store and the prices of additional ingredients there. The analyzed information is sent from the server to the user's terminal, and the optimal purchasing plan is presented.

[0100] For example, if a user enters "pork, cabbage, carrots" using their smartphone, the server will suggest a cooking method such as "stir-fried pork and cabbage" and communicate information about onions currently on sale. This function helps users make quick purchasing decisions in the store.

[0101] An example of a prompt for a generating AI model is: "Please enter a list of ingredients you have (e.g., pork, cabbage, carrots). The AI ​​model will use this information to suggest the most delicious cooking process and will also provide information on whether any additional ingredients you need are on sale." Using this prompt, users can easily input information and enjoy optimal suggestions from the AI.

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The user inputs ingredient information using a terminal. The application on the terminal formats the ingredient information selected or manually entered by the user into JSON format and sends this data to the server. The input is a list of ingredients owned by the user, such as "pork, cabbage, carrots," and the output is data formatted in JSON format.

[0105] Step 2:

[0106] The server receives JSON data sent from the terminal and stores it in a data database. Here, a cloud database such as Google® Firebase is used for data persistence. The input is JSON information about ingredients, and the output is saved to the database.

[0107] Step 3:

[0108] The server uses a generative AI model trained with TensorFlow to generate optimal food preparation processes based on ingredient information retrieved from a database. This generates new recipes that consider ingredient combinations, as well as general cooking procedures. The input is ingredient information in JSON format, and the output is text data of the food preparation process.

[0109] Step 4:

[0110] The server uses BeautifulSoup and its API to collect retailer price information from the internet. The input is a list of identified additional ingredients, and the output is price information for each store. The information obtained through crawling is temporarily stored on the server.

[0111] Step 5:

[0112] The server analyzes the collected price information and identifies the retailer with the lowest price from the obtained data. Statistical processing is used in the analysis, and the most economical option is calculated by filtering the data. The input is a list of price information, and the output is recommended retailer information.

[0113] Step 6:

[0114] The server sends the generated food preparation process and price analysis results to the terminal, making them accessible to the user. The input is food preparation process and price information, and the output is information formatted for viewing on the user's terminal. The user can then review recipes and the most economical purchase plan through the terminal to inform their purchasing decisions.

[0115] 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.

[0116] This invention provides a more personalized service tailored to the user's emotions by incorporating an emotion engine into a system that suggests recipes based on the user's existing ingredient information and recommends optimal purchase information from retailers. This system is implemented in the following form.

[0117] First, the user interacts with an interface that uses a terminal to input the ingredients they own. This information is encrypted by the terminal and sent to the server using a secure protocol.

[0118] The server analyzes the received ingredient information and uses an AI model to generate instructions for serving the dish. During this process, an emotion engine evaluates the user's current emotional state and selects dishes and customizes the instructions based on the evaluation. For example, if the emotion engine determines that the user is seeking relaxation, the server will suggest a simple but flavorful dish, such as soup or risotto.

[0119] Next, the server uses collection tools to obtain additional food price information from multiple retailers within the area. The emotion engine is also reflected in this process; for example, if it detects that the user is stressed, it can prioritize recommending the most accessible and convenient retailer.

[0120] For example, if a user is emotionally frustrated because the only options available are "chicken, carrots, and potatoes," the emotion engine will sense this and the server will suggest "chicken soup." At this point, the server will adjust the serving procedure to be as simple and easy to follow as possible.

[0121] This system aims to improve the overall user experience by addressing the user's psychological needs. It is designed so that meal planning and shopping become more fulfilling experiences that adapt to the user's emotional state.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The user enters a list of ingredients they own using the device's interface. The device organizes this ingredient information, encrypts it, and securely sends it to the server.

[0125] Step 2:

[0126] The server analyzes the received ingredient information. The server uses an AI model to generate possible cooking steps based on the input ingredients.

[0127] Step 3:

[0128] The server uses an emotion engine to analyze the user's emotional state. For example, if it determines that the user wants to relax, the server will prioritize suggesting dishes that have a relaxing effect.

[0129] Step 4:

[0130] The server sends the instructions for the generated dish to the terminal and displays them to the user. The terminal presents these instructions to the user in an easy-to-read format.

[0131] Step 5:

[0132] The server accesses APIs or websites of multiple retailers within the region to collect price information for any additional ingredients needed. The collected information is then stored in a database.

[0133] Step 6:

[0134] The server analyzes the collected price information. Based on the sentiment engine's judgment, it identifies and recommends the retailer that best suits the user's sentiment.

[0135] Step 7:

[0136] The server sends the identified optimal retailer information to the terminal. The terminal displays this information to the user to help with their purchase planning. The user makes purchases based on emotionally tailored recommendations.

[0137] (Example 2)

[0138] 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".

[0139] Modern consumers seek flexible and personalized suggestions that cater to their individual emotions and lifestyles when planning meals and sourcing ingredients. Traditional systems, which make suggestions based on a fixed logic without considering emotions, suffer from the problem of failing to adequately alleviate the stress and inconvenience experienced by users.

[0140] 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.

[0141] In this invention, the server includes an input device for inputting ingredient information, a generation algorithm for generating cooking procedures based on the ingredient information, an evaluation means for evaluating the user's emotional state and customizing the cooking procedures, a collection device for collecting price information from multiple sales facilities, and a recommendation system for recommending the most suitable sales facility according to the user's emotional state based on the collected price information. This enables personalized and optimal ingredient suggestions and procurement based on the user's emotional state.

[0142] An "input device" is a device used by a user to input information about the ingredients they own into the system.

[0143] A "generation algorithm" is a calculation method that automatically generates possible cooking steps based on the input information about the ingredients.

[0144] "Evaluation means" refers to a device or program that analyzes the user's emotional state and adjusts the cooking procedure based on that state.

[0145] A "collection device" is a device used to obtain price information for additional ingredients from multiple sales facilities.

[0146] A "recommendation system" is a program or device that suggests the most suitable sales facility based on the user's sentiment, using price information collected from sales facilities.

[0147] This invention relates to a system that provides personalized cooking suggestions based on the user's owned ingredient information, taking into account the user's emotional state. This system is mainly composed of a combination of components such as a terminal, a server, a generative AI model, and an emotion engine.

[0148] First, the user enters information about the ingredients they own using an input device on their terminal. Specifically, the input interface consists of fields for specifying the name and quantity of the ingredients. This information is securely converted using AES encryption and sent to the server via the HTTPS protocol.

[0149] The server operates a generation algorithm in conjunction with a database to analyze the received ingredient information. This algorithm generates usable recipes based on the combination of ingredients. Furthermore, the server uses an emotion engine to evaluate the user's emotional state. The emotion engine has the function of determining whether the user is feeling relaxed or stressed based on the user's input history and usage patterns.

[0150] For example, if a user enters "chicken, carrots, potatoes" and the emotion engine determines that the user is stressed, the server will customize the procedure to suggest a simple, relaxing dish such as "chicken soup." Another example of a prompt displayed on the terminal is when the user enters "I'm looking for a relaxing recipe," which then receives suggestions from the generative AI model.

[0151] Furthermore, the server collects additional ingredient price information from local retailers and identifies the optimal retailer based on the user's emotional state. In this way, users can obtain personalized shopping information and enjoy a more fulfilling experience in both meal planning and shopping.

[0152] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0153] Step 1:

[0154] The user uses a terminal to enter information about the ingredients they own. They enter a list of ingredients, such as "chicken, carrots, potatoes," using the terminal's input device. The entered information is encrypted using AES encryption. The encrypted data is sent to the server using the HTTPS protocol.

[0155] Step 2:

[0156] The server decrypts the received encrypted data and extracts ingredient information. The decrypted data is compared with the database, and a generation algorithm is activated. The generation algorithm searches for available recipes and lists the most suitable ones. This retrieves the steps for candidate dishes from the database.

[0157] Step 3:

[0158] The server uses an emotion engine to evaluate the user's emotional state. It analyzes input history and access patterns to determine whether the user is seeking relaxation or experiencing stress. The evaluation results are used to customize the cooking process.

[0159] Step 4:

[0160] Based on the results of the emotion evaluation, the server uses a generative AI model to customize the cooking procedure. For example, a user seeking relaxation might be suggested a simple, relaxing dish such as "chicken soup." The generative AI model aims to simplify the procedure and shorten the cooking time.

[0161] Step 5:

[0162] The server uses collection devices to gather price information from partner retailers within the region. It accesses each retailer via an API to retrieve current prices and inventory status. Based on the collected price information, it selects a retailer that matches the user's emotional state.

[0163] Step 6:

[0164] Based on the collected information, the server identifies recommended facilities and generates an optimal purchase plan. Based on the results of the emotion engine, it determines which facilities to recommend, prioritizing convenience such as ease of access. The generated purchase plan is then presented to the user.

[0165] Step 7:

[0166] The server sends the final cooking suggestions and shopping plan to the user's device. The user can then view the suggested cooking instructions and information on where to purchase the ingredients on their device. This enables the user to have a personalized cooking and shopping experience.

[0167] (Application Example 2)

[0168] 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".

[0169] Conventional cooking suggestion systems based on food information have the problem of not taking into account the user's emotional state, resulting in poor user satisfaction. Furthermore, when selecting ingredients to purchase, recommendations are based solely on the lowest price, failing to provide an optimal purchasing experience that matches the user's actual situation and needs. Therefore, there is a need for a system that customizes cooking suggestions and the purchasing experience according to the user's emotional state.

[0170] 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.

[0171] In this invention, the server includes an input means for inputting ingredient information, an emotion analysis means for analyzing emotional information, and a suggestion customization means for customizing cooking suggestions based on the emotional information. This enables personalized cooking and purchasing suggestions that correspond to the user's emotional state.

[0172] "Food ingredient information" refers to data on various foods and ingredients owned by the user.

[0173] An "input method" is an interface for users to register ingredient information on a terminal.

[0174] The "generation method" is a function that automatically creates cooking instructions based on the input ingredient information.

[0175] "Information gathering means" refers to the function of collecting information such as product prices and inventory status from multiple retailers.

[0176] "Recommendation methods" refer to a function that suggests the most suitable products and retailers to users based on the information collected.

[0177] "Emotional analysis tools" are functions that analyze a user's emotional state from their facial expressions and behavior.

[0178] The "suggestion customization method" is a function that adjusts cooking and purchasing suggestions to match the user's psychological state based on the results of emotion analysis.

[0179] "Communication methods" refer to the functions used to securely transmit ingredient information and other data to a server.

[0180] "Identification means" refers to a function for identifying necessary additional ingredients or materials based on the steps of the generated dish.

[0181] "Image acquisition means" refers to a function that uses a camera to acquire image data in order to analyze the user's emotions.

[0182] As an embodiment of this invention, a system is constructed in which a user, a terminal, and a server work together. First, the user uses a terminal to input information about the ingredients they own. This input can be done by voice input, scanning a QR code (registered trademark), or manual input. The terminal encrypts this ingredient information and transmits it to the server using a secure communication protocol.

[0183] The server generates cooking instructions using a generation AI model based on the received ingredient information. During this generation process, an emotion analysis means analyzes the user's current emotions, and a suggestion customization means adjusts the suggested dishes based on the results. The emotion analysis means uses image data acquired through the terminal's camera to determine the user's emotions from their facial expressions. For example, if the user wants to relax, it will suggest a dish that is easy to prepare and flavorful.

[0184] Furthermore, the server uses a retailer information gathering mechanism to collect price information on ingredients from multiple retailers in the area and makes optimal purchase suggestions based on the user's emotional state. Specifically, if the user is feeling stressed, it will prioritize recommending retailers that are easily accessible and convenient.

[0185] For example, if a user enters ingredients such as "tomatoes and mozzarella cheese" and the system analyzes that the user wants to relax, the server will suggest a simple recipe for "Caprese salad" and display an option for same-day delivery of cheese from a nearby store where it can be easily purchased.

[0186] Examples of input prompt statements for a generative AI model are as follows:

[0187] "The user is currently seeking relaxation. Available ingredients are tomatoes and mozzarella cheese. Please suggest a simple and flavorful recipe using these ingredients."

[0188] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0189] Step 1:

[0190] The user enters ingredient information into the terminal. The user registers the ingredients they own using voice input, QR code scanning, or manual input. The entered data is encrypted by the terminal. The encrypted data is then sent to the server using a secure communication protocol. The input is text data of ingredient information, and the output is sent as encrypted ingredient information.

[0191] Step 2:

[0192] The server decodes the received ingredient information and inputs it into the generating AI model. The AI ​​model then generates cooking instructions based on this information. During the data processing process, the AI ​​model refers to a pre-trained database to generate a recipe suitable for the input ingredients. The input is the decoded ingredient information, and the output is the generated cooking instructions.

[0193] Step 3:

[0194] The device's camera acquires images, and an emotion analysis system uses that data to evaluate the user's emotions. An image recognition algorithm is used to determine emotions from the user's facial expressions. The input is image data acquired by the camera, and the output is the analyzed emotion data.

[0195] Step 4:

[0196] The server uses a suggestion customization mechanism to provide cooking suggestions tailored to the user's emotions, based on the generated cooking procedure. The server analyzes the emotional data and customizes the recipe accordingly. The input is the cooking procedure and emotional data, and the output is a customized cooking suggestion.

[0197] Step 5:

[0198] The server, based on the user's emotional state, uses a store information gathering system to collect price information for ingredients from stores within the region. In addition to price, data such as accessibility and delivery time are also analyzed to recommend the most suitable store to the user. The input is store location and price information, and the output is a list of recommended stores.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] [Second Embodiment]

[0203] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0204] 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.

[0205] 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).

[0206] 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.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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".

[0215] The system according to the present invention suggests recipes based on the ingredient information owned by the consumer user, and also recommends the most economical ingredients that can be purchased from nearby stores.

[0216] First, the user uses a terminal to enter the current ingredient inventory. This information is entered using a list-based interface. The terminal is implemented to send the entered ingredient information to the server.

[0217] Next, the server analyzes the received ingredient information and uses a pre-trained AI model to generate cooking instructions that make the most of the input ingredients. This generated recipe aims to broaden the user's culinary horizons by enabling multiple cooking steps and the creation of new dishes. The server then sends this generated recipe to the terminal for display to the user.

[0218] Furthermore, the server collects up-to-date price information for necessary additional ingredients by crawling APIs and publicly available websites of local retailers. From this information, the server identifies the cheapest retailer and selects recommended ingredients and their retailers. The recommended results are displayed on the user's device, enabling them to create an efficient and economical purchasing plan. In this way, the system contributes to the efficient use and economical consumption of ingredients.

[0219] For example, if a user enters "chicken, carrots, and potatoes," the server will suggest "chicken stew" and recommend the cheapest store offering "onions" based on price information obtained via the internet. This implementation supports users in both discovering new recipes and reducing costs in their daily cooking.

[0220] The following describes the processing flow.

[0221] Step 1:

[0222] The user enters information about the ingredients they own using the terminal's interface. The terminal organizes the entered information in a list format and displays it for the user to review.

[0223] Step 2:

[0224] The terminal converts the organized ingredient information into data packets, encrypts them using a security protocol, and then sends them to the server.

[0225] Step 3:

[0226] The server analyzes the received ingredient information and uses an AI model to generate cooking instructions using those ingredients. The generated cooking instructions may include multiple options, providing users with a variety of cooking methods.

[0227] Step 4:

[0228] The server sends the generated cooking instructions to the terminal, which then displays the instructions to the user. The user can review the displayed instructions and select or modify them as needed.

[0229] Step 5:

[0230] The server accesses the APIs or websites of local retailers to collect price information for any additional ingredients needed. The collected price information is stored in the server's database.

[0231] Step 6:

[0232] The server analyzes the collected price information to identify the retailer where the product can be purchased at the lowest price. The identified retailer's information, along with details of any additional ingredients, is listed.

[0233] Step 7:

[0234] The server sends information about the cheapest retailer it has identified to the terminal, which then displays it to the user. Based on the information presented, the user can then plan an efficient shopping trip.

[0235] (Example 1)

[0236] 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."

[0237] In home cooking, there are challenges in efficiently utilizing limited ingredients and purchasing necessary ingredients economically. These challenges need to be addressed to reduce food waste and lower household expenses.

[0238] 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.

[0239] In this invention, the server includes an input device for receiving ingredient inventory information, a generation device using a generation AI to generate cooking instructions based on the ingredient inventory information, and an acquisition device for obtaining price data from multiple supply sources in the region. This allows the user to obtain cooking instructions that make the most of the ingredients they own and to choose the most economical way to purchase the necessary ingredients.

[0240] "Ingredient inventory information" refers to information about the types and quantities of ingredients that the user currently possesses.

[0241] An "input device" is a device or interface used by users to input food inventory information.

[0242] "Generative AI" is an artificial intelligence system that uses a pre-trained model to generate optimal cooking instructions from given ingredient information.

[0243] A "generation device" is a device that uses a generation AI to generate cooking instructions based on the input information.

[0244] An "acquisition device" is a device that collects price data from multiple supply sources in a region.

[0245] A "selection device" is a device that analyzes acquired price data, identifies the source of the lowest price, and proposes it.

[0246] An "output device" is a device or interface for presenting the generated cooking instructions to the user.

[0247] This invention is a system that assists users in managing and purchasing ingredients for home cooking. The user inputs information about the ingredients they currently own using a terminal. The terminal then transmits this ingredient inventory information to a server. The input device used here is a digital device such as a PC or smartphone.

[0248] The server analyzes the received ingredient information and generates cooking instructions using a pre-trained generative AI model. This generative AI model is an artificial intelligence trained on a large-scale recipe dataset and proposes specific cooking steps using the ingredients entered by the user. An example of a prompt is, "Please tell me a recipe that can be made using chicken, carrots, and potatoes."

[0249] Furthermore, the server collects price data from multiple local supply sources via the internet. The collected price data is analyzed to identify the most economical supply source, and a selection device identifies the source with the lowest price. The identified information is transmitted from the server to the terminal, which then makes optimal purchase suggestions to the user.

[0250] For example, if a user inputs that they own "chicken, carrots, and potatoes," the server will generate a recipe for "chicken stew." It will also suggest a source that provides "onions" at the lowest price as an additional ingredient. In this way, users can try new dishes without wasting ingredients and shop cost-effectively.

[0251] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0252] Step 1:

[0253] The user uses a terminal to input the type and quantity of ingredients they possess through the interface. The input information is specific ingredient data, such as "chicken, carrots, potatoes." The terminal sends the entered ingredient information to the server in JSON format. HTTP POST requests are used in this process.

[0254] Step 2:

[0255] The server analyzes the received ingredient information. Specifically, it analyzes the JSON data and extracts the ingredient names and quantities. This data processing creates input prompts for the AI ​​model. Upon receiving these prompts, the generating AI model processes a recipe request in the format of "Please tell me a recipe that can be made using chicken, carrots, and potatoes," and generates the optimal cooking instructions.

[0256] Step 3:

[0257] The server sends the generated cooking instructions back to the terminal. The generated recipe is sent in a format that the terminal can receive (e.g., text format) and processed as an HTTP response. The terminal displays the received recipe to the user. The user can check the specific cooking instructions displayed on the screen and use them to help with cooking.

[0258] Step 4:

[0259] The server collects price data from multiple local suppliers (e.g., supermarkets and online stores). In this process, it uses APIs provided by the suppliers to obtain the latest price information for the required ingredients (e.g., "onions"). HTTP GET requests are used for this purpose.

[0260] Step 5:

[0261] The server analyzes the collected price data to identify the cheapest supply source. Based on the analyzed data, a selection algorithm is executed to determine the cheapest supply source to recommend to the user. The analysis results are prepared as recommendation information, including the name of the supply source and price information.

[0262] Step 6:

[0263] The server sends information about the lowest-priced source identified to the terminal. The terminal then displays efficient and economical purchasing information to the user. As a result, the user can plan their purchases based on the information presented.

[0264] (Application Example 1)

[0265] 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."

[0266] Modern consumers find it difficult to plan economical and efficient grocery purchases while effectively utilizing the ingredients they already own. Furthermore, they often lack diverse cooking suggestions, limiting the ways in which they use individual ingredients. Additionally, the lack of readily available and effective ways to access discount information at physical stores restricts the consumer's purchasing experience.

[0267] 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.

[0268] In this invention, the server includes an input means for inputting ingredient information, a generation means for generating food preparation processes based on the ingredient information, a collection means for collecting price information from multiple available retail stores, a recommendation means for analyzing the collected price information and recommending the retail store with the lowest price, and an acquisition means for users to obtain discount information in real time at physical stores via a mobile information terminal. As a result, consumers can be offered dishes that make the most of the ingredients they have, and can plan to purchase any additional ingredients they need at the most economical price. Furthermore, they can obtain discount information instantly at physical stores, enabling efficient purchasing.

[0269] "Food ingredient information" refers to data about the specific types and quantities of food items that the user owns.

[0270] "Input means" refers to devices or interfaces that users use to input ingredient information into the system.

[0271] A "food preparation process" is a series of cooking methods and procedures generated based on the inputted ingredient information.

[0272] "Generation means" refers to devices or programs that utilize ingredient information to generate food preparation processes.

[0273] "Retail stores" refer to stores and commercial facilities that sell food and other daily necessities.

[0274] "Means of collection" refers to devices or systems used to collect information on prices and inventory from retail stores.

[0275] A "recommendation tool" is a processing device or program that analyzes collected price information and presents the most economical option.

[0276] A "personal digital assistant" is an electronic device that a user can carry with them, and includes smartphones, tablets, and other similar devices.

[0277] "Means of acquisition" refers to methods and systems that allow users to obtain real-time discount information from physical stores via their mobile devices.

[0278] To implement this system, the server and user terminals primarily cooperate in processing data. The server handles inputting ingredient information, generating food preparation processes, collecting and analyzing price information, and recommending optimal purchasing plans.

[0279] First, the user's device provides an interface for entering information about the ingredients the user owns. This ingredient information is formatted in a data format such as JSON and sent to a cloud-based database (e.g., Google Firebase).

[0280] Information sent from the terminal is received on the server using Python and the Flask framework and stored in a database. The server then uses a generative AI model trained with TensorFlow to generate food preparation steps based on the input ingredient information. This expands the range of dishes the user can cook.

[0281] Next, the server uses tools such as BeautifulSoup to collect price information from retail store websites and APIs. The collected information is analyzed within the server to identify the most economical store and the prices of additional ingredients there. The analyzed information is sent from the server to the user's terminal, and the optimal purchasing plan is presented.

[0282] For example, if a user enters "pork, cabbage, carrots" using their smartphone, the server will suggest a cooking method such as "stir-fried pork and cabbage" and communicate information about onions currently on sale. This function helps users make quick purchasing decisions in the store.

[0283] Examples of prompt texts for the generative AI model include: "Please input the list of ingredients the user has (e.g., pork, cabbage, carrot). Based on this information, the AI model will propose the most delicious food cooking process and further provide information on whether the additional ingredients needed are on sale." By using this prompt text, the user can easily input information and enjoy the optimal proposal by the AI.

[0284] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0285] Step 1:

[0286] The user inputs ingredient information using a terminal. The application on the terminal formats the ingredient information selected or manually input by the user in JSON format and sends this data to the server. The input is the list of ingredients the user has, such as "pork, cabbage, carrot", and the output is the data formatted in JSON.

[0287] Step 2:

[0288] The server receives the JSON data sent from the terminal and stores it in the database. Here, a cloud database such as Google Firebase is used to perform data persistence. The input is the JSON ingredient information, and the output is the storage in the database.

[0289] Step 3:

[0290] The server uses the generative AI model trained with TensorFlow to generate the optimal food cooking process based on the ingredient information obtained from the database. Here, new recipes or general cooking procedures considering the combination of ingredients are generated. The input is the ingredient information in JSON format, and the output is the data in text format of the food cooking process.

[0291] Step 4:

[0292] The server uses BeautifulSoup and its API to collect retailer price information from the internet. The input is a list of identified additional ingredients, and the output is price information for each store. The information obtained through crawling is temporarily stored on the server.

[0293] Step 5:

[0294] The server analyzes the collected price information and identifies the retailer with the lowest price from the obtained data. Statistical processing is used in the analysis, and the most economical option is calculated by filtering the data. The input is a list of price information, and the output is recommended retailer information.

[0295] Step 6:

[0296] The server sends the generated food preparation process and price analysis results to the terminal, making them accessible to the user. The input is food preparation process and price information, and the output is information formatted for viewing on the user's terminal. The user can then review recipes and the most economical purchase plan through the terminal to inform their purchasing decisions.

[0297] 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.

[0298] This invention provides a more personalized service tailored to the user's emotions by incorporating an emotion engine into a system that suggests recipes based on the user's existing ingredient information and recommends optimal purchase information from retailers. This system is implemented in the following form.

[0299] First, the user interacts with an interface that uses a terminal to input the ingredients they own. This information is encrypted by the terminal and sent to the server using a secure protocol.

[0300] The server analyzes the received food ingredient information and goes through the process of generating the cooking procedures of available dishes using an AI model. In this process, the emotion engine evaluates the user's current emotional state and selects dishes or customizes the procedures based on the evaluation results. For example, if the emotion engine determines that the user is seeking relaxation, the server recommends simple yet flavorful dishes such as soups or risottos.

[0301] Next, the server uses collection means to obtain additional food ingredient price information from multiple stores within the region. The emotion engine is also reflected in this process. For example, if it is sensed that the user is feeling stressed, the server can recommend the most accessible and convenient store as a priority.

[0302] As a specific example, when the user is emotionally anxious with only "chicken, carrot, and potato", the emotion engine senses this and the server proposes "chicken soup". At this time, the server adjusts the provided procedure to be as simple and easy to follow as possible.

[0303] This system aims to improve the overall user experience according to the user's psychological needs. Thus, meal planning and shopping are designed to be more fulfilling experiences adapted to the user's emotional state.

[0304] The following explains the process flow.

[0305] Step 1:

[0306] The user uses the interface of the terminal to input the list of food ingredients they own. The terminal organizes this food ingredient information, encrypts it, and securely transmits it to the server.

[0307] Step 2:

[0308] The server analyzes the received food ingredient information. The server utilizes an AI model to generate possible cooking procedures based on the input food ingredients.

[0309] Step 3:

[0310] The server uses an emotion engine to analyze the user's emotional state. For example, if it determines that the user wants to relax, the server will prioritize suggesting dishes that have a relaxing effect.

[0311] Step 4:

[0312] The server sends the instructions for the generated dish to the terminal and displays them to the user. The terminal presents these instructions to the user in an easy-to-read format.

[0313] Step 5:

[0314] The server accesses APIs or websites of multiple retailers within the region to collect price information for any additional ingredients needed. The collected information is then stored in a database.

[0315] Step 6:

[0316] The server analyzes the collected price information. Based on the sentiment engine's judgment, it identifies and recommends the retailer that best suits the user's sentiment.

[0317] Step 7:

[0318] The server sends the identified optimal retailer information to the terminal. The terminal displays this information to the user to help with their purchase planning. The user makes purchases based on emotionally tailored recommendations.

[0319] (Example 2)

[0320] 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".

[0321] Modern consumers seek flexible and personalized suggestions that cater to their individual emotions and lifestyles when planning meals and sourcing ingredients. Traditional systems, which make suggestions based on a fixed logic without considering emotions, suffer from the problem of failing to adequately alleviate the stress and inconvenience experienced by users.

[0322] 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.

[0323] In this invention, the server includes an input device for inputting ingredient information, a generation algorithm for generating cooking procedures based on the ingredient information, an evaluation means for evaluating the user's emotional state and customizing the cooking procedures, a collection device for collecting price information from multiple sales facilities, and a recommendation system for recommending the most suitable sales facility according to the user's emotional state based on the collected price information. This enables personalized and optimal ingredient suggestions and procurement based on the user's emotional state.

[0324] An "input device" is a device used by a user to input information about the ingredients they own into the system.

[0325] A "generation algorithm" is a calculation method that automatically generates possible cooking steps based on the input information about the ingredients.

[0326] "Evaluation means" refers to a device or program that analyzes the user's emotional state and adjusts the cooking procedure based on that state.

[0327] A "collection device" is a device used to obtain price information for additional ingredients from multiple sales facilities.

[0328] A "recommendation system" is a program or device that suggests the most suitable sales facility based on the user's sentiment, using price information collected from sales facilities.

[0329] This invention relates to a system that provides personalized cooking suggestions based on the user's owned ingredient information, taking into account the user's emotional state. This system is mainly composed of a combination of components such as a terminal, a server, a generative AI model, and an emotion engine.

[0330] First, the user enters information about the ingredients they own using an input device on their terminal. Specifically, the input interface consists of fields for specifying the name and quantity of the ingredients. This information is securely converted using AES encryption and sent to the server via the HTTPS protocol.

[0331] The server operates a generation algorithm in conjunction with a database to analyze the received ingredient information. This algorithm generates usable recipes based on the combination of ingredients. Furthermore, the server uses an emotion engine to evaluate the user's emotional state. The emotion engine has the function of determining whether the user is feeling relaxed or stressed based on the user's input history and usage patterns.

[0332] For example, if a user enters "chicken, carrots, potatoes" and the emotion engine determines that the user is stressed, the server will customize the procedure to suggest a simple, relaxing dish such as "chicken soup." Another example of a prompt displayed on the terminal is when the user enters "I'm looking for a relaxing recipe," which then receives suggestions from the generative AI model.

[0333] Furthermore, the server collects additional ingredient price information from local retailers and identifies the optimal retailer based on the user's emotional state. In this way, users can obtain personalized shopping information and enjoy a more fulfilling experience in both meal planning and shopping.

[0334] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0335] Step 1:

[0336] The user uses a terminal to enter information about the ingredients they own. They enter a list of ingredients, such as "chicken, carrots, potatoes," using the terminal's input device. The entered information is encrypted using AES encryption. The encrypted data is sent to the server using the HTTPS protocol.

[0337] Step 2:

[0338] The server decrypts the received encrypted data and extracts ingredient information. The decrypted data is compared with the database, and a generation algorithm is activated. The generation algorithm searches for available recipes and lists the most suitable ones. This retrieves the steps for candidate dishes from the database.

[0339] Step 3:

[0340] The server uses an emotion engine to evaluate the user's emotional state. It analyzes input history and access patterns to determine whether the user is seeking relaxation or experiencing stress. The evaluation results are used to customize the cooking process.

[0341] Step 4:

[0342] Based on the results of the emotion evaluation, the server uses a generative AI model to customize the cooking procedure. For example, a user seeking relaxation might be suggested a simple, relaxing dish such as "chicken soup." The generative AI model aims to simplify the procedure and shorten the cooking time.

[0343] Step 5:

[0344] The server uses collection devices to gather price information from partner retailers within the region. It accesses each retailer via an API to retrieve current prices and inventory status. Based on the collected price information, it selects a retailer that matches the user's emotional state.

[0345] Step 6:

[0346] Based on the collected information, the server identifies recommended facilities and generates an optimal purchase plan. Based on the results of the emotion engine, it determines which facilities to recommend, prioritizing convenience such as ease of access. The generated purchase plan is then presented to the user.

[0347] Step 7:

[0348] The server sends the final cooking suggestions and shopping plan to the user's device. The user can then view the suggested cooking instructions and information on where to purchase the ingredients on their device. This enables the user to have a personalized cooking and shopping experience.

[0349] (Application Example 2)

[0350] 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."

[0351] Conventional cooking suggestion systems based on food information have the problem of not taking into account the user's emotional state, resulting in poor user satisfaction. Furthermore, when selecting ingredients to purchase, recommendations are based solely on the lowest price, failing to provide an optimal purchasing experience that matches the user's actual situation and needs. Therefore, there is a need for a system that customizes cooking suggestions and the purchasing experience according to the user's emotional state.

[0352] 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.

[0353] In this invention, the server includes an input means for inputting ingredient information, an emotion analysis means for analyzing emotional information, and a suggestion customization means for customizing cooking suggestions based on the emotional information. This enables personalized cooking and purchasing suggestions that correspond to the user's emotional state.

[0354] "Food ingredient information" refers to data on various foods and ingredients owned by the user.

[0355] An "input method" is an interface for users to register ingredient information on a terminal.

[0356] The "generation method" is a function that automatically creates cooking instructions based on the input ingredient information.

[0357] "Information gathering means" refers to the function of collecting information such as product prices and inventory status from multiple retailers.

[0358] "Recommendation methods" refer to a function that suggests the most suitable products and retailers to users based on the information collected.

[0359] "Emotional analysis tools" are functions that analyze a user's emotional state from their facial expressions and behavior.

[0360] The "suggestion customization method" is a function that adjusts cooking and purchasing suggestions to match the user's psychological state based on the results of emotion analysis.

[0361] "Communication methods" refer to the functions used to securely transmit ingredient information and other data to a server.

[0362] "Identification means" refers to a function for identifying necessary additional ingredients or materials based on the steps of the generated dish.

[0363] "Image acquisition means" refers to a function that uses a camera to acquire image data in order to analyze the user's emotions.

[0364] As an embodiment of this invention, a system is constructed in which a user, a terminal, and a server work together. First, the user uses a terminal to input information about the ingredients they own. This input can be done by voice input, QR code scanning, or manual input. The terminal encrypts this ingredient information and transmits it to the server using a secure communication protocol.

[0365] The server generates cooking instructions using a generation AI model based on the received ingredient information. During this generation process, an emotion analysis means analyzes the user's current emotions, and a suggestion customization means adjusts the suggested dishes based on the results. The emotion analysis means uses image data acquired through the terminal's camera to determine the user's emotions from their facial expressions. For example, if the user wants to relax, it will suggest a dish that is easy to prepare and flavorful.

[0366] Furthermore, the server uses a retailer information gathering mechanism to collect price information on ingredients from multiple retailers in the area and makes optimal purchase suggestions based on the user's emotional state. Specifically, if the user is feeling stressed, it will prioritize recommending retailers that are easily accessible and convenient.

[0367] For example, if a user enters ingredients such as "tomatoes and mozzarella cheese" and the system analyzes that the user wants to relax, the server will suggest a simple recipe for "Caprese salad" and display an option for same-day delivery of cheese from a nearby store where it can be easily purchased.

[0368] Examples of input prompt statements for a generative AI model are as follows:

[0369] "The user is currently seeking relaxation. Available ingredients are tomatoes and mozzarella cheese. Please suggest a simple and flavorful recipe using these ingredients."

[0370] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0371] Step 1:

[0372] The user enters ingredient information into the terminal. The user registers the ingredients they own using voice input, QR code scanning, or manual input. The entered data is encrypted by the terminal. The encrypted data is then sent to the server using a secure communication protocol. The input is text data of ingredient information, and the output is sent as encrypted ingredient information.

[0373] Step 2:

[0374] The server decodes the received ingredient information and inputs it into the generating AI model. The AI ​​model then generates cooking instructions based on this information. During the data processing process, the AI ​​model refers to a pre-trained database to generate a recipe suitable for the input ingredients. The input is the decoded ingredient information, and the output is the generated cooking instructions.

[0375] Step 3:

[0376] The device's camera acquires images, and an emotion analysis system uses that data to evaluate the user's emotions. An image recognition algorithm is used to determine emotions from the user's facial expressions. The input is image data acquired by the camera, and the output is the analyzed emotion data.

[0377] Step 4:

[0378] The server uses a suggestion customization mechanism to provide cooking suggestions tailored to the user's emotions, based on the generated cooking procedure. The server analyzes the emotional data and customizes the recipe accordingly. The input is the cooking procedure and emotional data, and the output is a customized cooking suggestion.

[0379] Step 5:

[0380] The server, based on the user's emotional state, uses a store information gathering system to collect price information for ingredients from stores within the region. In addition to price, data such as accessibility and delivery time are also analyzed to recommend the most suitable store to the user. The input is store location and price information, and the output is a list of recommended stores.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] [Third Embodiment]

[0385] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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".

[0397] The system according to the present invention suggests recipes based on the ingredient information owned by the consumer user, and also recommends the most economical ingredients that can be purchased from nearby stores.

[0398] First, the user uses a terminal to enter the current ingredient inventory. This information is entered using a list-based interface. The terminal is implemented to send the entered ingredient information to the server.

[0399] Next, the server analyzes the received ingredient information and uses a pre-trained AI model to generate cooking instructions that make the most of the input ingredients. This generated recipe aims to broaden the user's culinary horizons by enabling multiple cooking steps and the creation of new dishes. The server then sends this generated recipe to the terminal for display to the user.

[0400] Furthermore, the server collects up-to-date price information for necessary additional ingredients by crawling APIs and publicly available websites of local retailers. From this information, the server identifies the cheapest retailer and selects recommended ingredients and their retailers. The recommended results are displayed on the user's device, enabling them to create an efficient and economical purchasing plan. In this way, the system contributes to the efficient use and economical consumption of ingredients.

[0401] For example, if a user enters "chicken, carrots, and potatoes," the server will suggest "chicken stew" and recommend the cheapest store offering "onions" based on price information obtained via the internet. This implementation supports users in both discovering new recipes and reducing costs in their daily cooking.

[0402] The following describes the processing flow.

[0403] Step 1:

[0404] The user enters information about the ingredients they own using the terminal's interface. The terminal organizes the entered information in a list format and displays it for the user to review.

[0405] Step 2:

[0406] The terminal converts the organized ingredient information into data packets, encrypts them using a security protocol, and then sends them to the server.

[0407] Step 3:

[0408] The server analyzes the received ingredient information and uses an AI model to generate cooking instructions using those ingredients. The generated cooking instructions may include multiple options, providing users with a variety of cooking methods.

[0409] Step 4:

[0410] The server sends the generated cooking instructions to the terminal, which then displays the instructions to the user. The user can review the displayed instructions and select or modify them as needed.

[0411] Step 5:

[0412] The server accesses the APIs or websites of local retailers to collect price information for any additional ingredients needed. The collected price information is stored in the server's database.

[0413] Step 6:

[0414] The server analyzes the collected price information to identify the retailer where the product can be purchased at the lowest price. The identified retailer's information, along with details of any additional ingredients, is listed.

[0415] Step 7:

[0416] The server sends information about the cheapest retailer it has identified to the terminal, which then displays it to the user. Based on the information presented, the user can then plan an efficient shopping trip.

[0417] (Example 1)

[0418] 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."

[0419] In home cooking, there are challenges in efficiently utilizing limited ingredients and purchasing necessary ingredients economically. These challenges need to be addressed to reduce food waste and lower household expenses.

[0420] 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.

[0421] In this invention, the server includes an input device for receiving ingredient inventory information, a generation device using a generation AI to generate cooking instructions based on the ingredient inventory information, and an acquisition device for obtaining price data from multiple supply sources in the region. This allows the user to obtain cooking instructions that make the most of the ingredients they own and to choose the most economical way to purchase the necessary ingredients.

[0422] "Ingredient inventory information" refers to information about the types and quantities of ingredients that the user currently possesses.

[0423] An "input device" is a device or interface used by users to input food inventory information.

[0424] "Generative AI" is an artificial intelligence system that uses a pre-trained model to generate optimal cooking instructions from given ingredient information.

[0425] A "generation device" is a device that uses a generation AI to generate cooking instructions based on the input information.

[0426] An "acquisition device" is a device that collects price data from multiple supply sources in a region.

[0427] A "selection device" is a device that analyzes acquired price data, identifies the source of the lowest price, and proposes it.

[0428] An "output device" is a device or interface for presenting the generated cooking instructions to the user.

[0429] This invention is a system that assists users in managing and purchasing ingredients for home cooking. The user inputs information about the ingredients they currently own using a terminal. The terminal then transmits this ingredient inventory information to a server. The input device used here is a digital device such as a PC or smartphone.

[0430] The server analyzes the received ingredient information and generates cooking instructions using a pre-trained generative AI model. This generative AI model is an artificial intelligence trained on a large-scale recipe dataset and proposes specific cooking steps using the ingredients entered by the user. An example of a prompt is, "Please tell me a recipe that can be made using chicken, carrots, and potatoes."

[0431] Furthermore, the server collects price data from multiple local supply sources via the internet. The collected price data is analyzed to identify the most economical supply source, and a selection device identifies the source with the lowest price. The identified information is transmitted from the server to the terminal, which then makes optimal purchase suggestions to the user.

[0432] For example, if a user inputs that they own "chicken, carrots, and potatoes," the server will generate a recipe for "chicken stew." It will also suggest a source that provides "onions" at the lowest price as an additional ingredient. In this way, users can try new dishes without wasting ingredients and shop cost-effectively.

[0433] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0434] Step 1:

[0435] The user uses a terminal to input the type and quantity of ingredients they possess through the interface. The input information is specific ingredient data, such as "chicken, carrots, potatoes." The terminal sends the entered ingredient information to the server in JSON format. HTTP POST requests are used in this process.

[0436] Step 2:

[0437] The server analyzes the received ingredient information. Specifically, it analyzes the JSON data and extracts the ingredient names and quantities. This data processing creates input prompts for the AI ​​model. Upon receiving these prompts, the generating AI model processes a recipe request in the format of "Please tell me a recipe that can be made using chicken, carrots, and potatoes," and generates the optimal cooking instructions.

[0438] Step 3:

[0439] The server sends the generated cooking instructions back to the terminal. The generated recipe is sent in a format that the terminal can receive (e.g., text format) and processed as an HTTP response. The terminal displays the received recipe to the user. The user can check the specific cooking instructions displayed on the screen and use them to help with cooking.

[0440] Step 4:

[0441] The server collects price data from multiple local suppliers (e.g., supermarkets and online stores). In this process, it uses APIs provided by the suppliers to obtain the latest price information for the required ingredients (e.g., "onions"). HTTP GET requests are used for this purpose.

[0442] Step 5:

[0443] The server analyzes the collected price data to identify the cheapest supply source. Based on the analyzed data, a selection algorithm is executed to determine the cheapest supply source to recommend to the user. The analysis results are prepared as recommendation information, including the name of the supply source and price information.

[0444] Step 6:

[0445] The server sends information about the lowest-priced source identified to the terminal. The terminal then displays efficient and economical purchasing information to the user. As a result, the user can plan their purchases based on the information presented.

[0446] (Application Example 1)

[0447] 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."

[0448] Modern consumers find it difficult to plan economical and efficient grocery purchases while effectively utilizing the ingredients they already own. Furthermore, they often lack diverse cooking suggestions, limiting the ways in which they use individual ingredients. Additionally, the lack of readily available and effective ways to access discount information at physical stores restricts the consumer's purchasing experience.

[0449] 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.

[0450] In this invention, the server includes an input means for inputting ingredient information, a generation means for generating food preparation processes based on the ingredient information, a collection means for collecting price information from multiple available retail stores, a recommendation means for analyzing the collected price information and recommending the retail store with the lowest price, and an acquisition means for users to obtain discount information in real time at physical stores via a mobile information terminal. As a result, consumers can be offered dishes that make the most of the ingredients they have, and can plan to purchase any additional ingredients they need at the most economical price. Furthermore, they can obtain discount information instantly at physical stores, enabling efficient purchasing.

[0451] "Food ingredient information" refers to data about the specific types and quantities of food items that the user owns.

[0452] "Input means" refers to devices or interfaces that users use to input ingredient information into the system.

[0453] A "food preparation process" is a series of cooking methods and procedures generated based on the inputted ingredient information.

[0454] "Generation means" refers to devices or programs that utilize ingredient information to generate food preparation processes.

[0455] "Retail stores" refer to stores and commercial facilities that sell food and other daily necessities.

[0456] "Means of collection" refers to devices or systems used to collect information on prices and inventory from retail stores.

[0457] A "recommendation tool" is a processing device or program that analyzes collected price information and presents the most economical option.

[0458] A "personal digital assistant" is an electronic device that a user can carry with them, and includes smartphones, tablets, and other similar devices.

[0459] "Means of acquisition" refers to methods and systems that allow users to obtain real-time discount information from physical stores via their mobile devices.

[0460] To implement this system, the server and user terminals primarily cooperate in processing data. The server handles inputting ingredient information, generating food preparation processes, collecting and analyzing price information, and recommending optimal purchasing plans.

[0461] First, the user's device provides an interface for entering information about the ingredients the user owns. This ingredient information is formatted in a data format such as JSON and sent to a cloud-based database (e.g., Google Firebase).

[0462] Information sent from the terminal is received on the server using Python and the Flask framework and stored in a database. The server then uses a generative AI model trained with TensorFlow to generate food preparation steps based on the input ingredient information. This expands the range of dishes the user can cook.

[0463] Next, the server uses tools such as BeautifulSoup to collect price information from retail store websites and APIs. The collected information is analyzed within the server to identify the most economical store and the prices of additional ingredients there. The analyzed information is sent from the server to the user's terminal, and the optimal purchasing plan is presented.

[0464] For example, if a user enters "pork, cabbage, carrots" using their smartphone, the server will suggest a cooking method such as "stir-fried pork and cabbage" and communicate information about onions currently on sale. This function helps users make quick purchasing decisions in the store.

[0465] An example of a prompt for a generating AI model is: "Please enter a list of ingredients you have (e.g., pork, cabbage, carrots). The AI ​​model will use this information to suggest the most delicious cooking process and will also provide information on whether any additional ingredients you need are on sale." Using this prompt, users can easily input information and enjoy optimal suggestions from the AI.

[0466] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0467] Step 1:

[0468] The user inputs ingredient information using a terminal. The application on the terminal formats the ingredient information selected or manually entered by the user into JSON format and sends this data to the server. The input is a list of ingredients owned by the user, such as "pork, cabbage, carrots," and the output is data formatted in JSON format.

[0469] Step 2:

[0470] The server receives JSON data sent from the terminal and stores it in a data database. Here, a cloud database such as Google Firebase is used for data persistence. The input is JSON information about ingredients, and the output is saved to the database.

[0471] Step 3:

[0472] The server uses a generative AI model trained with TensorFlow to generate optimal food preparation processes based on ingredient information retrieved from a database. This generates new recipes that consider ingredient combinations, as well as general cooking procedures. The input is ingredient information in JSON format, and the output is text data of the food preparation process.

[0473] Step 4:

[0474] The server uses BeautifulSoup and its API to collect retailer price information from the internet. The input is a list of identified additional ingredients, and the output is price information for each store. The information obtained through crawling is temporarily stored on the server.

[0475] Step 5:

[0476] The server analyzes the collected price information and identifies the retailer with the lowest price from the obtained data. Statistical processing is used in the analysis, and the most economical option is calculated by filtering the data. The input is a list of price information, and the output is recommended retailer information.

[0477] Step 6:

[0478] The server sends the generated food preparation process and price analysis results to the terminal, making them accessible to the user. The input is food preparation process and price information, and the output is information formatted for viewing on the user's terminal. The user can then review recipes and the most economical purchase plan through the terminal to inform their purchasing decisions.

[0479] 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.

[0480] This invention provides a more personalized service tailored to the user's emotions by incorporating an emotion engine into a system that suggests recipes based on the user's existing ingredient information and recommends optimal purchase information from retailers. This system is implemented in the following form.

[0481] First, the user interacts with an interface that uses a terminal to input the ingredients they own. This information is encrypted by the terminal and sent to the server using a secure protocol.

[0482] The server analyzes the received ingredient information and uses an AI model to generate instructions for serving the dish. During this process, an emotion engine evaluates the user's current emotional state and selects dishes and customizes the instructions based on the evaluation. For example, if the emotion engine determines that the user is seeking relaxation, the server will suggest a simple but flavorful dish, such as soup or risotto.

[0483] Next, the server uses collection tools to obtain additional food price information from multiple retailers within the area. The emotion engine is also reflected in this process; for example, if it detects that the user is stressed, it can prioritize recommending the most accessible and convenient retailer.

[0484] For example, if a user is emotionally frustrated because the only options available are "chicken, carrots, and potatoes," the emotion engine will sense this and the server will suggest "chicken soup." At this point, the server will adjust the serving procedure to be as simple and easy to follow as possible.

[0485] This system aims to improve the overall user experience by addressing the user's psychological needs. It is designed so that meal planning and shopping become more fulfilling experiences that adapt to the user's emotional state.

[0486] The following describes the processing flow.

[0487] Step 1:

[0488] The user enters a list of ingredients they own using the device's interface. The device organizes this ingredient information, encrypts it, and securely sends it to the server.

[0489] Step 2:

[0490] The server analyzes the received ingredient information. The server uses an AI model to generate possible cooking steps based on the input ingredients.

[0491] Step 3:

[0492] The server uses an emotion engine to analyze the user's emotional state. For example, if it determines that the user wants to relax, the server will prioritize suggesting dishes that have a relaxing effect.

[0493] Step 4:

[0494] The server sends the instructions for the generated dish to the terminal and displays them to the user. The terminal presents these instructions to the user in an easy-to-read format.

[0495] Step 5:

[0496] The server accesses APIs or websites of multiple retailers within the region to collect price information for any additional ingredients needed. The collected information is then stored in a database.

[0497] Step 6:

[0498] The server analyzes the collected price information. Based on the sentiment engine's judgment, it identifies and recommends the retailer that best suits the user's sentiment.

[0499] Step 7:

[0500] The server sends the identified optimal retailer information to the terminal. The terminal displays this information to the user to help with their purchase planning. The user makes purchases based on emotionally tailored recommendations.

[0501] (Example 2)

[0502] 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."

[0503] Modern consumers seek flexible and personalized suggestions that cater to their individual emotions and lifestyles when planning meals and sourcing ingredients. Traditional systems, which make suggestions based on a fixed logic without considering emotions, suffer from the problem of failing to adequately alleviate the stress and inconvenience experienced by users.

[0504] 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.

[0505] In this invention, the server includes an input device for inputting ingredient information, a generation algorithm for generating cooking procedures based on the ingredient information, an evaluation means for evaluating the user's emotional state and customizing the cooking procedures, a collection device for collecting price information from multiple sales facilities, and a recommendation system for recommending the most suitable sales facility according to the user's emotional state based on the collected price information. This enables personalized and optimal ingredient suggestions and procurement based on the user's emotional state.

[0506] An "input device" is a device used by a user to input information about the ingredients they own into the system.

[0507] A "generation algorithm" is a calculation method that automatically generates possible cooking steps based on the input information about the ingredients.

[0508] "Evaluation means" refers to a device or program that analyzes the user's emotional state and adjusts the cooking procedure based on that state.

[0509] A "collection device" is a device used to obtain price information for additional ingredients from multiple sales facilities.

[0510] A "recommendation system" is a program or device that suggests the most suitable sales facility based on the user's sentiment, using price information collected from sales facilities.

[0511] This invention relates to a system that provides personalized cooking suggestions based on the user's owned ingredient information, taking into account the user's emotional state. This system is mainly composed of a combination of components such as a terminal, a server, a generative AI model, and an emotion engine.

[0512] First, the user enters information about the ingredients they own using an input device on their terminal. Specifically, the input interface consists of fields for specifying the name and quantity of the ingredients. This information is securely converted using AES encryption and sent to the server via the HTTPS protocol.

[0513] The server operates a generation algorithm in conjunction with a database to analyze the received ingredient information. This algorithm generates usable recipes based on the combination of ingredients. Furthermore, the server uses an emotion engine to evaluate the user's emotional state. The emotion engine has the function of determining whether the user is feeling relaxed or stressed based on the user's input history and usage patterns.

[0514] For example, if a user enters "chicken, carrots, potatoes" and the emotion engine determines that the user is stressed, the server will customize the procedure to suggest a simple, relaxing dish such as "chicken soup." Another example of a prompt displayed on the terminal is when the user enters "I'm looking for a relaxing recipe," which then receives suggestions from the generative AI model.

[0515] Furthermore, the server collects additional ingredient price information from local retailers and identifies the optimal retailer based on the user's emotional state. In this way, users can obtain personalized shopping information and enjoy a more fulfilling experience in both meal planning and shopping.

[0516] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0517] Step 1:

[0518] The user uses a terminal to enter information about the ingredients they own. They enter a list of ingredients, such as "chicken, carrots, potatoes," using the terminal's input device. The entered information is encrypted using AES encryption. The encrypted data is sent to the server using the HTTPS protocol.

[0519] Step 2:

[0520] The server decrypts the received encrypted data and extracts ingredient information. The decrypted data is compared with the database, and a generation algorithm is activated. The generation algorithm searches for available recipes and lists the most suitable ones. This retrieves the steps for candidate dishes from the database.

[0521] Step 3:

[0522] The server uses an emotion engine to evaluate the user's emotional state. It analyzes input history and access patterns to determine whether the user is seeking relaxation or experiencing stress. The evaluation results are used to customize the cooking process.

[0523] Step 4:

[0524] Based on the results of the emotion evaluation, the server uses a generative AI model to customize the cooking procedure. For example, a user seeking relaxation might be suggested a simple, relaxing dish such as "chicken soup." The generative AI model aims to simplify the procedure and shorten the cooking time.

[0525] Step 5:

[0526] The server uses collection devices to gather price information from partner retailers within the region. It accesses each retailer via an API to retrieve current prices and inventory status. Based on the collected price information, it selects a retailer that matches the user's emotional state.

[0527] Step 6:

[0528] Based on the collected information, the server identifies recommended facilities and generates an optimal purchase plan. Based on the results of the emotion engine, it determines which facilities to recommend, prioritizing convenience such as ease of access. The generated purchase plan is then presented to the user.

[0529] Step 7:

[0530] The server sends the final cooking suggestions and shopping plan to the user's device. The user can then view the suggested cooking instructions and information on where to purchase the ingredients on their device. This enables the user to have a personalized cooking and shopping experience.

[0531] (Application Example 2)

[0532] 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."

[0533] Conventional cooking suggestion systems based on food information have the problem of not taking into account the user's emotional state, resulting in poor user satisfaction. Furthermore, when selecting ingredients to purchase, recommendations are based solely on the lowest price, failing to provide an optimal purchasing experience that matches the user's actual situation and needs. Therefore, there is a need for a system that customizes cooking suggestions and the purchasing experience according to the user's emotional state.

[0534] 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.

[0535] In this invention, the server includes an input means for inputting ingredient information, an emotion analysis means for analyzing emotional information, and a suggestion customization means for customizing cooking suggestions based on the emotional information. This enables personalized cooking and purchasing suggestions that correspond to the user's emotional state.

[0536] "Food ingredient information" refers to data on various foods and ingredients owned by the user.

[0537] An "input method" is an interface for users to register ingredient information on a terminal.

[0538] The "generation method" is a function that automatically creates cooking instructions based on the input ingredient information.

[0539] "Information gathering means" refers to the function of collecting information such as product prices and inventory status from multiple retailers.

[0540] "Recommendation methods" refer to a function that suggests the most suitable products and retailers to users based on the information collected.

[0541] "Emotional analysis tools" are functions that analyze a user's emotional state from their facial expressions and behavior.

[0542] The "suggestion customization method" is a function that adjusts cooking and purchasing suggestions to match the user's psychological state based on the results of emotion analysis.

[0543] "Communication methods" refer to the functions used to securely transmit ingredient information and other data to a server.

[0544] "Identification means" refers to a function for identifying necessary additional ingredients or materials based on the steps of the generated dish.

[0545] "Image acquisition means" refers to a function that uses a camera to acquire image data in order to analyze the user's emotions.

[0546] As an embodiment of this invention, a system is constructed in which a user, a terminal, and a server work together. First, the user uses a terminal to input information about the ingredients they own. This input can be done by voice input, QR code scanning, or manual input. The terminal encrypts this ingredient information and transmits it to the server using a secure communication protocol.

[0547] The server generates cooking instructions using a generation AI model based on the received ingredient information. During this generation process, an emotion analysis means analyzes the user's current emotions, and a suggestion customization means adjusts the suggested dishes based on the results. The emotion analysis means uses image data acquired through the terminal's camera to determine the user's emotions from their facial expressions. For example, if the user wants to relax, it will suggest a dish that is easy to prepare and flavorful.

[0548] Furthermore, the server uses a retailer information gathering mechanism to collect price information on ingredients from multiple retailers in the area and makes optimal purchase suggestions based on the user's emotional state. Specifically, if the user is feeling stressed, it will prioritize recommending retailers that are easily accessible and convenient.

[0549] For example, if a user enters ingredients such as "tomatoes and mozzarella cheese" and the system analyzes that the user wants to relax, the server will suggest a simple recipe for "Caprese salad" and display an option for same-day delivery of cheese from a nearby store where it can be easily purchased.

[0550] Examples of input prompt statements for a generative AI model are as follows:

[0551] "The user is currently seeking relaxation. Available ingredients are tomatoes and mozzarella cheese. Please suggest a simple and flavorful recipe using these ingredients."

[0552] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0553] Step 1:

[0554] The user enters ingredient information into the terminal. The user registers the ingredients they own using voice input, QR code scanning, or manual input. The entered data is encrypted by the terminal. The encrypted data is then sent to the server using a secure communication protocol. The input is text data of ingredient information, and the output is sent as encrypted ingredient information.

[0555] Step 2:

[0556] The server decodes the received ingredient information and inputs it into the generating AI model. The AI ​​model then generates cooking instructions based on this information. During the data processing process, the AI ​​model refers to a pre-trained database to generate a recipe suitable for the input ingredients. The input is the decoded ingredient information, and the output is the generated cooking instructions.

[0557] Step 3:

[0558] The device's camera acquires images, and an emotion analysis system uses that data to evaluate the user's emotions. An image recognition algorithm is used to determine emotions from the user's facial expressions. The input is image data acquired by the camera, and the output is the analyzed emotion data.

[0559] Step 4:

[0560] The server uses a suggestion customization mechanism to provide cooking suggestions tailored to the user's emotions, based on the generated cooking procedure. The server analyzes the emotional data and customizes the recipe accordingly. The input is the cooking procedure and emotional data, and the output is a customized cooking suggestion.

[0561] Step 5:

[0562] The server, based on the user's emotional state, uses a store information gathering system to collect price information for ingredients from stores within the region. In addition to price, data such as accessibility and delivery time are also analyzed to recommend the most suitable store to the user. The input is store location and price information, and the output is a list of recommended stores.

[0563] 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.

[0564] 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.

[0565] 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.

[0566] [Fourth Embodiment]

[0567] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0568] 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.

[0569] 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).

[0570] 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.

[0571] 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.

[0572] 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).

[0573] 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.

[0574] 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.

[0575] 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.

[0576] 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.

[0577] 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.

[0578] 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.

[0579] 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".

[0580] The system according to the present invention suggests recipes based on the ingredient information owned by the consumer user, and also recommends the most economical ingredients that can be purchased from nearby stores.

[0581] First, the user uses a terminal to enter the current ingredient inventory. This information is entered using a list-based interface. The terminal is implemented to send the entered ingredient information to the server.

[0582] Next, the server analyzes the received ingredient information and uses a pre-trained AI model to generate cooking instructions that make the most of the input ingredients. This generated recipe aims to broaden the user's culinary horizons by enabling multiple cooking steps and the creation of new dishes. The server then sends this generated recipe to the terminal for display to the user.

[0583] Furthermore, the server collects up-to-date price information for necessary additional ingredients by crawling APIs and publicly available websites of local retailers. From this information, the server identifies the cheapest retailer and selects recommended ingredients and their retailers. The recommended results are displayed on the user's device, enabling them to create an efficient and economical purchasing plan. In this way, the system contributes to the efficient use and economical consumption of ingredients.

[0584] For example, if a user enters "chicken, carrots, and potatoes," the server will suggest "chicken stew" and recommend the cheapest store offering "onions" based on price information obtained via the internet. This implementation supports users in both discovering new recipes and reducing costs in their daily cooking.

[0585] The following describes the processing flow.

[0586] Step 1:

[0587] The user enters information about the ingredients they own using the terminal's interface. The terminal organizes the entered information in a list format and displays it for the user to review.

[0588] Step 2:

[0589] The terminal converts the organized ingredient information into data packets, encrypts them using a security protocol, and then sends them to the server.

[0590] Step 3:

[0591] The server analyzes the received ingredient information and uses an AI model to generate cooking instructions using those ingredients. The generated cooking instructions may include multiple options, providing users with a variety of cooking methods.

[0592] Step 4:

[0593] The server sends the generated cooking instructions to the terminal, which then displays the instructions to the user. The user can review the displayed instructions and select or modify them as needed.

[0594] Step 5:

[0595] The server accesses the APIs or websites of local retailers to collect price information for any additional ingredients needed. The collected price information is stored in the server's database.

[0596] Step 6:

[0597] The server analyzes the collected price information to identify the retailer where the product can be purchased at the lowest price. The identified retailer's information, along with details of any additional ingredients, is listed.

[0598] Step 7:

[0599] The server sends information about the cheapest retailer it has identified to the terminal, which then displays it to the user. Based on the information presented, the user can then plan an efficient shopping trip.

[0600] (Example 1)

[0601] 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".

[0602] In home cooking, there are challenges in efficiently utilizing limited ingredients and purchasing necessary ingredients economically. These challenges need to be addressed to reduce food waste and lower household expenses.

[0603] 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.

[0604] In this invention, the server includes an input device for receiving ingredient inventory information, a generation device using a generation AI to generate cooking instructions based on the ingredient inventory information, and an acquisition device for obtaining price data from multiple supply sources in the region. This allows the user to obtain cooking instructions that make the most of the ingredients they own and to choose the most economical way to purchase the necessary ingredients.

[0605] "Ingredient inventory information" refers to information about the types and quantities of ingredients that the user currently possesses.

[0606] An "input device" is a device or interface used by users to input food inventory information.

[0607] "Generative AI" is an artificial intelligence system that uses a pre-trained model to generate optimal cooking instructions from given ingredient information.

[0608] A "generation device" is a device that uses a generation AI to generate cooking instructions based on the input information.

[0609] An "acquisition device" is a device that collects price data from multiple supply sources in a region.

[0610] A "selection device" is a device that analyzes acquired price data, identifies the source of the lowest price, and proposes it.

[0611] An "output device" is a device or interface for presenting the generated cooking instructions to the user.

[0612] This invention is a system that assists users in managing and purchasing ingredients for home cooking. The user inputs information about the ingredients they currently own using a terminal. The terminal then transmits this ingredient inventory information to a server. The input device used here is a digital device such as a PC or smartphone.

[0613] The server analyzes the received ingredient information and generates cooking instructions using a pre-trained generative AI model. This generative AI model is an artificial intelligence trained on a large-scale recipe dataset and proposes specific cooking steps using the ingredients entered by the user. An example of a prompt is, "Please tell me a recipe that can be made using chicken, carrots, and potatoes."

[0614] Furthermore, the server collects price data from multiple local supply sources via the internet. The collected price data is analyzed to identify the most economical supply source, and a selection device identifies the source with the lowest price. The identified information is transmitted from the server to the terminal, which then makes optimal purchase suggestions to the user.

[0615] For example, if a user inputs that they own "chicken, carrots, and potatoes," the server will generate a recipe for "chicken stew." It will also suggest a source that provides "onions" at the lowest price as an additional ingredient. In this way, users can try new dishes without wasting ingredients and shop cost-effectively.

[0616] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0617] Step 1:

[0618] The user uses a terminal to input the type and quantity of ingredients they possess through the interface. The input information is specific ingredient data, such as "chicken, carrots, potatoes." The terminal sends the entered ingredient information to the server in JSON format. HTTP POST requests are used in this process.

[0619] Step 2:

[0620] The server analyzes the received ingredient information. Specifically, it analyzes the JSON data and extracts the ingredient names and quantities. This data processing creates input prompts for the AI ​​model. Upon receiving these prompts, the generating AI model processes a recipe request in the format of "Please tell me a recipe that can be made using chicken, carrots, and potatoes," and generates the optimal cooking instructions.

[0621] Step 3:

[0622] The server sends the generated cooking instructions back to the terminal. The generated recipe is sent in a format that the terminal can receive (e.g., text format) and processed as an HTTP response. The terminal displays the received recipe to the user. The user can check the specific cooking instructions displayed on the screen and use them to help with cooking.

[0623] Step 4:

[0624] The server collects price data from multiple local suppliers (e.g., supermarkets and online stores). In this process, it uses APIs provided by the suppliers to obtain the latest price information for the required ingredients (e.g., "onions"). HTTP GET requests are used for this purpose.

[0625] Step 5:

[0626] The server analyzes the collected price data to identify the cheapest supply source. Based on the analyzed data, a selection algorithm is executed to determine the cheapest supply source to recommend to the user. The analysis results are prepared as recommendation information, including the name of the supply source and price information.

[0627] Step 6:

[0628] The server sends information about the lowest-priced source identified to the terminal. The terminal then displays efficient and economical purchasing information to the user. As a result, the user can plan their purchases based on the information presented.

[0629] (Application Example 1)

[0630] 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".

[0631] Modern consumers find it difficult to plan economical and efficient grocery purchases while effectively utilizing the ingredients they already own. Furthermore, they often lack diverse cooking suggestions, limiting the ways in which they use individual ingredients. Additionally, the lack of readily available and effective ways to access discount information at physical stores restricts the consumer's purchasing experience.

[0632] 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.

[0633] In this invention, the server includes an input means for inputting ingredient information, a generation means for generating food preparation processes based on the ingredient information, a collection means for collecting price information from multiple available retail stores, a recommendation means for analyzing the collected price information and recommending the retail store with the lowest price, and an acquisition means for users to obtain discount information in real time at physical stores via a mobile information terminal. As a result, consumers can be offered dishes that make the most of the ingredients they have, and can plan to purchase any additional ingredients they need at the most economical price. Furthermore, they can obtain discount information instantly at physical stores, enabling efficient purchasing.

[0634] "Food ingredient information" refers to data about the specific types and quantities of food items that the user owns.

[0635] "Input means" refers to devices or interfaces that users use to input ingredient information into the system.

[0636] A "food preparation process" is a series of cooking methods and procedures generated based on the inputted ingredient information.

[0637] "Generation means" refers to devices or programs that utilize ingredient information to generate food preparation processes.

[0638] "Retail stores" refer to stores and commercial facilities that sell food and other daily necessities.

[0639] "Means of collection" refers to devices or systems used to collect information on prices and inventory from retail stores.

[0640] A "recommendation tool" is a processing device or program that analyzes collected price information and presents the most economical option.

[0641] A "personal digital assistant" is an electronic device that a user can carry with them, and includes smartphones, tablets, and other similar devices.

[0642] "Means of acquisition" refers to methods and systems that allow users to obtain real-time discount information from physical stores via their mobile devices.

[0643] To implement this system, the server and user terminals primarily cooperate in processing data. The server handles inputting ingredient information, generating food preparation processes, collecting and analyzing price information, and recommending optimal purchasing plans.

[0644] First, the user's device provides an interface for entering information about the ingredients the user owns. This ingredient information is formatted in a data format such as JSON and sent to a cloud-based database (e.g., Google Firebase).

[0645] Information sent from the terminal is received on the server using Python and the Flask framework and stored in a database. The server then uses a generative AI model trained with TensorFlow to generate food preparation steps based on the input ingredient information. This expands the range of dishes the user can cook.

[0646] Next, the server uses tools such as BeautifulSoup to collect price information from retail store websites and APIs. The collected information is analyzed within the server to identify the most economical store and the prices of additional ingredients there. The analyzed information is sent from the server to the user's terminal, and the optimal purchasing plan is presented.

[0647] For example, if a user enters "pork, cabbage, carrots" using their smartphone, the server will suggest a cooking method such as "stir-fried pork and cabbage" and communicate information about onions currently on sale. This function helps users make quick purchasing decisions in the store.

[0648] An example of a prompt for a generating AI model is: "Please enter a list of ingredients you have (e.g., pork, cabbage, carrots). The AI ​​model will use this information to suggest the most delicious cooking process and will also provide information on whether any additional ingredients you need are on sale." Using this prompt, users can easily input information and enjoy optimal suggestions from the AI.

[0649] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0650] Step 1:

[0651] The user inputs ingredient information using a terminal. The application on the terminal formats the ingredient information selected or manually entered by the user into JSON format and sends this data to the server. The input is a list of ingredients owned by the user, such as "pork, cabbage, carrots," and the output is data formatted in JSON format.

[0652] Step 2:

[0653] The server receives JSON data sent from the terminal and stores it in a data database. Here, a cloud database such as Google Firebase is used for data persistence. The input is JSON information about ingredients, and the output is saved to the database.

[0654] Step 3:

[0655] The server uses a generative AI model trained with TensorFlow to generate optimal food preparation processes based on ingredient information retrieved from a database. This generates new recipes that consider ingredient combinations, as well as general cooking procedures. The input is ingredient information in JSON format, and the output is text data of the food preparation process.

[0656] Step 4:

[0657] The server uses BeautifulSoup and its API to collect retailer price information from the internet. The input is a list of identified additional ingredients, and the output is price information for each store. The information obtained through crawling is temporarily stored on the server.

[0658] Step 5:

[0659] The server analyzes the collected price information and identifies the retailer with the lowest price from the obtained data. Statistical processing is used in the analysis, and the most economical option is calculated by filtering the data. The input is a list of price information, and the output is recommended retailer information.

[0660] Step 6:

[0661] The server sends the generated food preparation process and price analysis results to the terminal, making them accessible to the user. The input is food preparation process and price information, and the output is information formatted for viewing on the user's terminal. The user can then review recipes and the most economical purchase plan through the terminal to inform their purchasing decisions.

[0662] 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.

[0663] This invention provides a more personalized service tailored to the user's emotions by incorporating an emotion engine into a system that suggests recipes based on the user's existing ingredient information and recommends optimal purchase information from retailers. This system is implemented in the following form.

[0664] First, the user interacts with an interface that uses a terminal to input the ingredients they own. This information is encrypted by the terminal and sent to the server using a secure protocol.

[0665] The server analyzes the received ingredient information and uses an AI model to generate instructions for serving the dish. During this process, an emotion engine evaluates the user's current emotional state and selects dishes and customizes the instructions based on the evaluation. For example, if the emotion engine determines that the user is seeking relaxation, the server will suggest a simple but flavorful dish, such as soup or risotto.

[0666] Next, the server uses collection tools to obtain additional food price information from multiple retailers within the area. The emotion engine is also reflected in this process; for example, if it detects that the user is stressed, it can prioritize recommending the most accessible and convenient retailer.

[0667] For example, if a user is emotionally frustrated because the only options available are "chicken, carrots, and potatoes," the emotion engine will sense this and the server will suggest "chicken soup." At this point, the server will adjust the serving procedure to be as simple and easy to follow as possible.

[0668] This system aims to improve the overall user experience by addressing the user's psychological needs. It is designed so that meal planning and shopping become more fulfilling experiences that adapt to the user's emotional state.

[0669] The following describes the processing flow.

[0670] Step 1:

[0671] The user enters a list of ingredients they own using the device's interface. The device organizes this ingredient information, encrypts it, and securely sends it to the server.

[0672] Step 2:

[0673] The server analyzes the received ingredient information. The server uses an AI model to generate possible cooking steps based on the input ingredients.

[0674] Step 3:

[0675] The server uses an emotion engine to analyze the user's emotional state. For example, if it determines that the user wants to relax, the server will prioritize suggesting dishes that have a relaxing effect.

[0676] Step 4:

[0677] The server sends the instructions for the generated dish to the terminal and displays them to the user. The terminal presents these instructions to the user in an easy-to-read format.

[0678] Step 5:

[0679] The server accesses APIs or websites of multiple retailers within the region to collect price information for any additional ingredients needed. The collected information is then stored in a database.

[0680] Step 6:

[0681] The server analyzes the collected price information. Based on the sentiment engine's judgment, it identifies and recommends the retailer that best suits the user's sentiment.

[0682] Step 7:

[0683] The server sends the identified optimal retailer information to the terminal. The terminal displays this information to the user to help with their purchase planning. The user makes purchases based on emotionally tailored recommendations.

[0684] (Example 2)

[0685] 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".

[0686] Modern consumers seek flexible and personalized suggestions that cater to their individual emotions and lifestyles when planning meals and sourcing ingredients. Traditional systems, which make suggestions based on a fixed logic without considering emotions, suffer from the problem of failing to adequately alleviate the stress and inconvenience experienced by users.

[0687] 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.

[0688] In this invention, the server includes an input device for inputting ingredient information, a generation algorithm for generating cooking procedures based on the ingredient information, an evaluation means for evaluating the user's emotional state and customizing the cooking procedures, a collection device for collecting price information from multiple sales facilities, and a recommendation system for recommending the most suitable sales facility according to the user's emotional state based on the collected price information. This enables personalized and optimal ingredient suggestions and procurement based on the user's emotional state.

[0689] An "input device" is a device used by a user to input information about the ingredients they own into the system.

[0690] A "generation algorithm" is a calculation method that automatically generates possible cooking steps based on the input information about the ingredients.

[0691] "Evaluation means" refers to a device or program that analyzes the user's emotional state and adjusts the cooking procedure based on that state.

[0692] A "collection device" is a device used to obtain price information for additional ingredients from multiple sales facilities.

[0693] A "recommendation system" is a program or device that suggests the most suitable sales facility based on the user's sentiment, using price information collected from sales facilities.

[0694] This invention relates to a system that provides personalized cooking suggestions based on the user's owned ingredient information, taking into account the user's emotional state. This system is mainly composed of a combination of components such as a terminal, a server, a generative AI model, and an emotion engine.

[0695] First, the user enters information about the ingredients they own using an input device on their terminal. Specifically, the input interface consists of fields for specifying the name and quantity of the ingredients. This information is securely converted using AES encryption and sent to the server via the HTTPS protocol.

[0696] The server operates a generation algorithm in conjunction with a database to analyze the received ingredient information. This algorithm generates usable recipes based on the combination of ingredients. Furthermore, the server uses an emotion engine to evaluate the user's emotional state. The emotion engine has the function of determining whether the user is feeling relaxed or stressed based on the user's input history and usage patterns.

[0697] For example, if a user enters "chicken, carrots, potatoes" and the emotion engine determines that the user is stressed, the server will customize the procedure to suggest a simple, relaxing dish such as "chicken soup." Another example of a prompt displayed on the terminal is when the user enters "I'm looking for a relaxing recipe," which then receives suggestions from the generative AI model.

[0698] Furthermore, the server collects additional ingredient price information from local retailers and identifies the optimal retailer based on the user's emotional state. In this way, users can obtain personalized shopping information and enjoy a more fulfilling experience in both meal planning and shopping.

[0699] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0700] Step 1:

[0701] The user uses a terminal to enter information about the ingredients they own. They enter a list of ingredients, such as "chicken, carrots, potatoes," using the terminal's input device. The entered information is encrypted using AES encryption. The encrypted data is sent to the server using the HTTPS protocol.

[0702] Step 2:

[0703] The server decrypts the received encrypted data and extracts ingredient information. The decrypted data is compared with the database, and a generation algorithm is activated. The generation algorithm searches for available recipes and lists the most suitable ones. This retrieves the steps for candidate dishes from the database.

[0704] Step 3:

[0705] The server uses an emotion engine to evaluate the user's emotional state. It analyzes input history and access patterns to determine whether the user is seeking relaxation or experiencing stress. The evaluation results are used to customize the cooking process.

[0706] Step 4:

[0707] Based on the results of the emotion evaluation, the server uses a generative AI model to customize the cooking procedure. For example, a user seeking relaxation might be suggested a simple, relaxing dish such as "chicken soup." The generative AI model aims to simplify the procedure and shorten the cooking time.

[0708] Step 5:

[0709] The server uses collection devices to gather price information from partner retailers within the region. It accesses each retailer via an API to retrieve current prices and inventory status. Based on the collected price information, it selects a retailer that matches the user's emotional state.

[0710] Step 6:

[0711] Based on the collected information, the server identifies recommended facilities and generates an optimal purchase plan. Based on the results of the emotion engine, it determines which facilities to recommend, prioritizing convenience such as ease of access. The generated purchase plan is then presented to the user.

[0712] Step 7:

[0713] The server sends the final cooking suggestions and shopping plan to the user's device. The user can then view the suggested cooking instructions and information on where to purchase the ingredients on their device. This enables the user to have a personalized cooking and shopping experience.

[0714] (Application Example 2)

[0715] 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".

[0716] Conventional cooking suggestion systems based on food information have the problem of not taking into account the user's emotional state, resulting in poor user satisfaction. Furthermore, when selecting ingredients to purchase, recommendations are based solely on the lowest price, failing to provide an optimal purchasing experience that matches the user's actual situation and needs. Therefore, there is a need for a system that customizes cooking suggestions and the purchasing experience according to the user's emotional state.

[0717] 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.

[0718] In this invention, the server includes an input means for inputting ingredient information, an emotion analysis means for analyzing emotional information, and a suggestion customization means for customizing cooking suggestions based on the emotional information. This enables personalized cooking and purchasing suggestions that correspond to the user's emotional state.

[0719] "Food ingredient information" refers to data on various foods and ingredients owned by the user.

[0720] An "input method" is an interface for users to register ingredient information on a terminal.

[0721] The "generation method" is a function that automatically creates cooking instructions based on the input ingredient information.

[0722] "Information gathering means" refers to the function of collecting information such as product prices and inventory status from multiple retailers.

[0723] "Recommendation methods" refer to a function that suggests the most suitable products and retailers to users based on the information collected.

[0724] "Emotional analysis tools" are functions that analyze a user's emotional state from their facial expressions and behavior.

[0725] The "suggestion customization method" is a function that adjusts cooking and purchasing suggestions to match the user's psychological state based on the results of emotion analysis.

[0726] "Communication methods" refer to the functions used to securely transmit ingredient information and other data to a server.

[0727] "Identification means" refers to a function for identifying necessary additional ingredients or materials based on the steps of the generated dish.

[0728] "Image acquisition means" refers to a function that uses a camera to acquire image data in order to analyze the user's emotions.

[0729] As an embodiment of this invention, a system is constructed in which a user, a terminal, and a server work together. First, the user uses a terminal to input information about the ingredients they own. This input can be done by voice input, QR code scanning, or manual input. The terminal encrypts this ingredient information and transmits it to the server using a secure communication protocol.

[0730] The server generates cooking instructions using a generation AI model based on the received ingredient information. During this generation process, an emotion analysis means analyzes the user's current emotions, and a suggestion customization means adjusts the suggested dishes based on the results. The emotion analysis means uses image data acquired through the terminal's camera to determine the user's emotions from their facial expressions. For example, if the user wants to relax, it will suggest a dish that is easy to prepare and flavorful.

[0731] Furthermore, the server uses a retailer information gathering mechanism to collect price information on ingredients from multiple retailers in the area and makes optimal purchase suggestions based on the user's emotional state. Specifically, if the user is feeling stressed, it will prioritize recommending retailers that are easily accessible and convenient.

[0732] For example, if a user enters ingredients such as "tomatoes and mozzarella cheese" and the system analyzes that the user wants to relax, the server will suggest a simple recipe for "Caprese salad" and display an option for same-day delivery of cheese from a nearby store where it can be easily purchased.

[0733] Examples of input prompt statements for a generative AI model are as follows:

[0734] "The user is currently seeking relaxation. Available ingredients are tomatoes and mozzarella cheese. Please suggest a simple and flavorful recipe using these ingredients."

[0735] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0736] Step 1:

[0737] The user enters ingredient information into the terminal. The user registers the ingredients they own using voice input, QR code scanning, or manual input. The entered data is encrypted by the terminal. The encrypted data is then sent to the server using a secure communication protocol. The input is text data of ingredient information, and the output is sent as encrypted ingredient information.

[0738] Step 2:

[0739] The server decodes the received ingredient information and inputs it into the generating AI model. The AI ​​model then generates cooking instructions based on this information. During the data processing process, the AI ​​model refers to a pre-trained database to generate a recipe suitable for the input ingredients. The input is the decoded ingredient information, and the output is the generated cooking instructions.

[0740] Step 3:

[0741] The device's camera acquires images, and an emotion analysis system uses that data to evaluate the user's emotions. An image recognition algorithm is used to determine emotions from the user's facial expressions. The input is image data acquired by the camera, and the output is the analyzed emotion data.

[0742] Step 4:

[0743] The server uses a suggestion customization mechanism to provide cooking suggestions tailored to the user's emotions, based on the generated cooking procedure. The server analyzes the emotional data and customizes the recipe accordingly. The input is the cooking procedure and emotional data, and the output is a customized cooking suggestion.

[0744] Step 5:

[0745] The server, based on the user's emotional state, uses a store information gathering system to collect price information for ingredients from stores within the region. In addition to price, data such as accessibility and delivery time are also analyzed to recommend the most suitable store to the user. The input is store location and price information, and the output is a list of recommended stores.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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."

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] The following is further disclosed regarding the embodiments described above.

[0768] (Claim 1)

[0769] An input method for entering ingredient information,

[0770] A generation means for generating cooking procedures based on the aforementioned ingredient information,

[0771] A means of collecting price information from multiple available retailers,

[0772] A recommendation system that analyzes collected price information and recommends the retailer with the lowest price,

[0773] A system that includes this.

[0774] (Claim 2)

[0775] The system according to claim 1, characterized by comprising identification means for identifying necessary additional ingredients based on the procedure of the generated dish.

[0776] (Claim 3)

[0777] The system according to claim 1, characterized in that it includes a communication means for encrypting and transmitting ingredient information from the input means.

[0778] "Example 1"

[0779] (Claim 1)

[0780] An input device for receiving food inventory information,

[0781] A generation device using a generation AI that generates cooking instructions based on the aforementioned food ingredient inventory information,

[0782] An acquisition device that obtains price data from multiple supply sources in a region,

[0783] A selection device that analyzes the obtained price data and presents the source of supply with the lowest price,

[0784] An output device that outputs the generated cooking instructions,

[0785] A system that includes this.

[0786] (Claim 2)

[0787] The system according to claim 1, further comprising an identification device that identifies additional ingredients required in accordance with the generated cooking instructions.

[0788] (Claim 3)

[0789] The system according to claim 1, further comprising a transmission device that encrypts and transmits food inventory information from the input device.

[0790] "Application Example 1"

[0791] (Claim 1)

[0792] An input method for entering ingredient information,

[0793] A generation means for generating a food preparation process based on the aforementioned ingredient information,

[0794] A means of collecting price information from multiple available retail stores,

[0795] A recommendation system that analyzes collected price information and recommends the retail store with the lowest price,

[0796] A means for users to obtain discount information in real time within a physical store via a mobile device,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, comprising identification means for identifying necessary additional ingredients based on the generated food preparation process and presenting an optimal purchase plan based on discount information.

[0800] (Claim 3)

[0801] The system according to claim 1, further comprising a communication means for transmitting ingredient information from the input means using digital protection technology.

[0802] "Example 2 of combining an emotion engine"

[0803] (Claim 1)

[0804] An input device for entering ingredient information,

[0805] A generation algorithm for generating cooking procedures based on the aforementioned ingredient information,

[0806] An evaluation means for evaluating the user's emotional state and customizing the cooking procedure,

[0807] A collection device for collecting price information from multiple sales facilities,

[0808] Based on the price information collected, a recommendation system is provided to recommend the most suitable sales facility according to the user's sentiment.

[0809] A system that includes this.

[0810] (Claim 2)

[0811] The system according to claim 1, characterized in that it identifies necessary additional ingredients based on the generated cooking procedure and adjusts the cooking procedure based on the user's emotional state.

[0812] (Claim 3)

[0813] The system according to claim 1, characterized in that ingredient information from the input device is encrypted and transmitted, and received by the server using a secure protocol.

[0814] "Application example 2 when combining with an emotional engine"

[0815] (Claim 1)

[0816] An input method for entering ingredient information,

[0817] A generation means for generating cooking procedures based on the aforementioned ingredient information,

[0818] A means of collecting price information from multiple available retailers,

[0819] A recommendation system that analyzes collected price information and recommends the retailer with the lowest price,

[0820] A means of analyzing emotional information,

[0821] A suggestion customization means for customizing cooking suggestions based on the aforementioned emotional information,

[0822] A system that includes this.

[0823] (Claim 2)

[0824] The system according to claim 1, comprising identification means for identifying necessary additional ingredients based on the generated cooking procedure, and characterized in that it adjusts ingredient purchase suggestions according to emotional information obtained from an emotional analysis means.

[0825] (Claim 3)

[0826] The system according to claim 1, further comprising a communication means for encrypting and transmitting ingredient information from the input means, and an image acquisition means for emotion analysis. [Explanation of Symbols]

[0827] 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. An input method for entering ingredient information, A generation means for generating cooking procedures based on the aforementioned ingredient information, A means of collecting price information from multiple available retailers, A recommendation system that analyzes collected price information and recommends the retailer with the lowest price, A system that includes this.

2. The system according to claim 1, characterized by comprising identification means for identifying necessary additional ingredients based on the procedure for creating a dish.

3. The system according to claim 1, characterized in that it includes a communication means for encrypting and transmitting ingredient information from the input means.

Images