system

Abstract

Provide a system. A collection means; a generating AI means for analyzing the food inventory information collected by the collecting means; a means for providing a user with information about ingredients that are predicted to be discarded, obtained by the analysis; A means for creating a dish based on the ingredient information provided by the user; A means to track and report on food waste reduction efforts; A system including:

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Food waste is a serious problem in modern society. In particular, food waste is high in depopulated areas, and food waste has a negative impact on the sustainability of the region. Furthermore, from the perspective of career support for young people, the limited opportunities to learn cooking skills is an issue. In this situation, there is a need for a system that can reduce food waste while simultaneously providing career support to young people. [Means for solving the problem]

[0005] This invention proposes a system that collects food inventory information, analyzes it using a generation AI, and provides users with information on ingredients that are predicted to be wasted. Specifically, food inventory information is collected by a collection means, and the generation AI means analyzes the information to identify ingredients that are predicted to be wasted. This information is then provided to users, who then have the means to create dishes using those ingredients, thereby reducing food waste. The system also includes a means to track the effectiveness of food waste reduction and report the results, allowing the effectiveness of the entire system to be evaluated. This makes it possible to simultaneously reduce food waste and support the careers of young people.

[0006] "Collection Implement" refers to the device, network interface, or software used to collect food inventory information from various sources.

[0007] "Generative AI means" refers to a system that includes algorithms or programs that analyze food inventory information collected by the collection means and identify information about ingredients that are predicted to be discarded.

[0008] "Means for providing" refers to a device or system for notifying or displaying the ingredient information obtained by the generating AI means to the user in real time.

[0009] "Means for creating a dish" refers to a system that includes guides, tools, and kitchen equipment that allow users to create a dish based on the provided ingredient information.

[0010] "Means for tracking and reporting food waste reduction results" refers to systems and software that compile data on user-created dishes and evaluate and report on food waste reduction results. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2]1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0012] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0013] First, the terms used in the following description will be explained.

[0014] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0015] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0016] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0017] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0024] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0031] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0032] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, and a means for tracking the effects of food waste reduction and reporting the results. A specific embodiment of this system will be described.

[0033] Data collection

[0034] First, a server collects food inventory information from commercial and agricultural facilities located in depopulated areas. The collection method is to obtain data via API using a network interface. For example, the server obtains food inventory data using APIs such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory."

[0035] Analysis by generative AI

[0036] Next, the server analyzes the collected food inventory data using a generation AI method. Specifically, it identifies ingredients that are close to their expiration date or that are likely to be discarded if not consumed from the collected data. For example, the generation AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0037] Providing information on ingredients

[0038] Based on the analysis results, the server uses a means to provide the user with information about the identified ingredients. The information is provided to the user's device via real-time notifications and a dashboard. For example, a notification such as "List of ingredients to be consumed today: tomatoes, bread, olive oil" is displayed on the device.

[0039] Menu proposal and cooking

[0040] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. This allows the user to create dishes based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish according to that recipe.

[0041] Tracking and reporting food waste reduction

[0042] After a user serves a dish, they input the data of the dish into the device, and the data is sent to the server. The server uses the aggregated data to track the food waste reduction effect and report the results. For example, it generates a report of the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis.

[0043] As a concrete example, let's assume that this system is introduced in a depopulated area of ​​Hokkaido. Food inventory information is collected daily from supermarkets and farmers in the area and sent to a server. The server uses generation AI to create a list of ingredients (e.g., tomatoes, bread) that need to be consumed by tomorrow, and notifies the terminals of local cafe staff in real time. Based on this notification, the cafe staff prepares and serves dishes such as paninis using tomatoes and bread according to the suggested recipe. The provided data is sent from the terminals to the server and compiled, allowing the effectiveness of food waste reduction throughout the area to be regularly evaluated and reported.

[0044] In this way, the system of the present invention can effectively reduce food waste and simultaneously support young people's careers.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] The server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. Specifically, the server calls endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" and stores the obtained inventory data in its own database.

[0048] Step 2:

[0049] The server preprocesses the collected inventory data and converts it into an analyzable format, for example, converting all data into a unified format and imputing missing values.

[0050] Step 3:

[0051] The server inputs the preprocessed data into the generation AI, which analyzes ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3."

[0052] Step 4:

[0053] The server creates a list of ingredients that are predicted to be discarded as a result of the AI's analysis and sends the list to the user's (cafe or restaurant staff) device. Specifically, the server notifies the device of the ingredient information in JSON format.

[0054] Step 5:

[0055] The device notifies the user of the list of ingredients received from the server and displays it on the screen. For example, the device displays information such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[0056] Step 6:

[0057] The device uses a generation AI to suggest menus and recipes using ingredients that are predicted to be wasted. Specifically, the device requests recipe suggestions from the generation AI based on the "available_ingredients" data, and displays recipes such as "Panini with tomatoes and bread" to the user.

[0058] Step 7:

[0059] The user creates a dish based on the proposed recipe. The user inputs the specific number and contents of the dish they want to serve into the terminal, and the data is sent to the server.

[0060] Step 8:

[0061] The server receives and aggregates the food serving data sent by users and tracks the food waste reduction effect. The server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, Amount of food waste reduced: 50 kilograms."

[0062] Step 9:

[0063] The server periodically notifies the relevant parties of the reports it generates, and evaluates and reports on the effectiveness of the entire system. For example, the server automatically generates a weekly report and sends it to the relevant parties by email.

[0064] Example 1

[0065] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0066] The problem of food waste is a major issue that causes environmental burdens and economic losses. In particular, in depopulated areas, distribution and sales efficiency is low, making it easy for excess food inventory to occur. As a result, food that is approaching its expiration date is often discarded. Furthermore, there is a lack of a system for sharing food inventory information across the entire region and using that information to make effective cooking suggestions, so concrete measures to reduce waste are needed.

[0067] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0068] In this invention, the server includes a means for collecting food inventory information from commercial facilities and agricultural facilities, a generating AI means for analyzing the food inventory information collected by the collecting means, a means for the generating AI means to identify ingredients that are close to their expiration date or are expected to be discarded, a means for providing the user with the ingredient information obtained by the analysis, a means for suggesting dishes based on the ingredient information provided by the user, a means for the user to prepare the suggested dishes, a means for tracking data on the dishes prepared by the user, and a means for reporting the effects of food waste reduction. This enables a consistent system that covers everything from collecting food inventory information to analyzing it, promoting consumption, and tracking and reporting the effects.

[0069] A "commercial establishment" is a place operated for the sale of food and essential commodities.

[0070] An "agricultural facility" is a facility designed for the cultivation and harvesting of agricultural crops.

[0071] "Food inventory information" refers to data such as the type, quantity, and expiration date of food at commercial and agricultural facilities.

[0072] "Collection methods" refers to the methods and techniques used to collect food inventory information from commercial and agricultural establishments.

[0073] "Generative AI means" is an artificial intelligence technology that analyzes collected food inventory information and extracts important ingredient information based on specific conditions.

[0074] "Analysis" is the process of evaluating collected food inventory information and identifying ingredients that are nearing their expiration date or are expected to be discarded.

[0075] "Means of providing" refers to the methods and techniques for informing users of the analysis results.

[0076] "Means for suggesting dishes" refers to a method for suggesting appropriate recipes and menus based on the ingredient information provided by the user.

[0077] "Means for creating a dish" refers to the methods and techniques that a user uses to create a dish according to a suggested recipe.

[0078] "Tracking means" refers to the method of collecting data on the dishes created by users and analyzing it to confirm the effectiveness of food waste reduction.

[0079] "Reporting means" refers to the methods and technologies used to inform users and other interested parties of collected data and analysis results.

[0080] "Food waste" refers to the amount and type of food that is not consumed and is destined to be discarded.

[0081] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, and a means for tracking the effects of food waste reduction and reporting the results. A specific embodiment of this system will be described.

[0082] Data collection

[0083] First, a server collects food inventory information from commercial and agricultural facilities located in depopulated areas. The collection method is to obtain data via API using a network interface. For example, the server obtains food inventory data using APIs such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." This allows food inventory information from commercial and agricultural facilities to be aggregated on the server.

[0084] Analysis by generative AI

[0085] Next, the server analyzes the collected food inventory data using a generative AI method. Specifically, a generative AI model is used to identify ingredients that are close to their expiration date or that are likely to be discarded if not consumed from the collected data. For example, the generative AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0086] Providing information on ingredients

[0087] Based on the analysis results, the server uses a means to provide the user with information about the identified ingredients. The information is provided to the user's device via real-time notifications and a dashboard. By displaying notifications such as "List of ingredients that need to be consumed today: tomatoes, bread, olive oil" on the device, the user can understand which ingredients should be prioritized for consumption.

[0088] Menu proposal and cooking

[0089] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. This allows the user to create a dish based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish according to that recipe. An example of a specific prompt might be, "Please suggest a simple dish using two tomatoes and one loaf of bread."

[0090] Tracking and reporting food waste reduction

[0091] After a user serves a dish, they input the data of the dish into the device, and the data is sent to the server. The server uses the aggregated data to track the food waste reduction effect and report the results. For example, it generates a report of the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis, thereby visualizing the food waste reduction effect of the entire region.

[0092] As a concrete example, let's assume that this system is introduced in a depopulated area of ​​Hokkaido. Food inventory information is collected daily from supermarkets and farmers in the area and sent to a server. The server uses generation AI to create a list of ingredients (e.g., tomatoes, bread) that need to be consumed by tomorrow, and notifies the terminals of local cafe staff in real time. Based on this notification, the cafe staff prepares and serves dishes such as paninis using tomatoes and bread using suggested recipes. The provided data is sent from the terminals to the server, where it is compiled and the effectiveness of food waste reduction throughout the area is regularly evaluated and reported.

[0093] In this way, the system of the present invention can effectively reduce food waste and simultaneously support young people's careers.

[0094] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0095] Step 1:

[0096] The server collects food inventory information from commercial and agricultural facilities located in depopulated areas.

[0097] Input: Your commercial or agricultural facility's API endpoint (e.g., "local_supermarket_api / get_inventory")

[0098] Specific operation: The server issues an API request via the network interface to obtain food inventory information.

[0099] Output: The acquired food inventory information data (e.g., JSON format) is saved on the server.

[0100] Step 2:

[0101] The food inventory data collected by the server is analyzed using generative AI methods.

[0102] Input: Food inventory data collected in Step 1

[0103] Specific operation: The server inputs food inventory data into the generative AI model and filters the data using the condition "expires_in_days < 3".

[0104] Output: A list of ingredients that are nearing their expiration date or are predicted to be discarded is generated.

[0105] Step 3:

[0106] The server uses a means for providing the user with the identified ingredient information.

[0107] Input: List of ingredients parsed in step 2

[0108] Specific operation: The server creates a notification message in real time based on the analysis results and sends it to the user's device.

[0109] Output: A notification of "List of ingredients to be consumed today" is displayed on the user's device.

[0110] Step 4:

[0111] The device uses generative AI based on the ingredient information provided to suggest appropriate recipes and menus.

[0112] Input: Ingredient information displayed on the user's device

[0113] Specific operation: The device inputs ingredient information into the generation AI to generate appropriate recipes and menus. An example of a prompt is "Please suggest a simple dish using two tomatoes and one loaf of bread."

[0114] Output: The suggested recipes and menus are displayed to the user.

[0115] Step 5:

[0116] The user creates a dish based on the suggested recipe.

[0117] Input: Recipe information displayed on the device

[0118] Specific operation: The user follows the instructions displayed on the device to create a dish using ingredients.

[0119] Output: The created dish (e.g., a panini with tomatoes and bread)

[0120] Step 6:

[0121] After the user has prepared the food, the user inputs data of the prepared food into the terminal, and the data is transmitted to the server.

[0122] Input: Information about the dish served (name of dish, ingredients used, number served, etc.)

[0123] Specific operation: The user enters recipe information into the device, and the device sends the data to the server.

[0124] Output: The data of the dishes served is saved on the server.

[0125] Step 7:

[0126] The server uses the collected data to track the effectiveness of food waste reduction and report the results.

[0127] Input: Food data submitted in step 6

[0128] Specific operation: The server analyzes the number of dishes served and the amount of food waste reduced, generates a report, and notifies relevant parties on a weekly or monthly basis.

[0129] Output: Report on food waste reduction (e.g., "Number of dishes served this week: 100, amount of food waste reduced: 50kg")

[0130] (Application example 1)

[0131] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0132] In recent years, the increase in food delivery services has exacerbated the problem of food waste. In addition, food inventory management at restaurants and supermarkets has become increasingly complex. Managing ingredients with approaching expiration dates is particularly difficult, resulting in large amounts of food being wasted. Furthermore, manually managing inventory and creating menus is time-consuming, labor-intensive, and inefficient. Therefore, there is a need for a system that can efficiently manage food inventory and suggest appropriate menus while reducing food waste.

[0133] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0134] In this invention, the server includes a collection means, a generation AI means, a provision means, a recipe creation means, and an effect tracking means. This allows the server to provide ingredient information to the user's device via real-time notifications and a dashboard, and furthermore, it is possible to suggest appropriate recipes using the generation AI. This encourages the efficient use of ingredients that are close to their expiration date, thereby reducing food waste.

[0135] A "collection instrument" is a device or system for collecting food inventory information from commercial or agricultural establishments.

[0136] "Generative AI methods" are artificial intelligence algorithms used to analyze collected food inventory information and identify ingredients that are nearing their expiration date or are likely to be discarded.

[0137] The "provision means" is a device or system for notifying or presenting the user with the ingredient information identified based on the analysis results.

[0138] The "dish preparation means" is a device or system that proposes an appropriate recipe to the user based on the provided ingredient information and prepares the dish.

[0139] "Effect Tracking Means" refers to a device or system that aggregates cooking data provided by users and tracks and reports the food waste reduction effect.

[0140] A "network interface" is a communication means for sending and receiving data between multiple devices or systems to collect food inventory information.

[0141] "Terminal" refers to an information display and input device used by a user, such as a smartphone, smart glasses, or head-mounted display.

[0142] "Real-time notification" is a communication function for instantly transmitting analyzed ingredient information to the user's terminal.

[0143] A "dashboard" is an interface that displays visually organized data and notifications so that users can intuitively grasp information.

[0144] "Recipe suggestions" are cooking methods suggested by the generative AI based on collected and analyzed ingredient information.

[0145] The present invention is a food waste reduction system that consists of a collection means, a generation AI means, a provision means, a cooking means, and an effect tracking means. Details of each means and a specific embodiment of the system are explained below.

[0146] First, the server collects food inventory information from commercial and agricultural facilities. The collection method is to obtain data via API using a network interface. For example, food inventory data is collected using API endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." The hardware used for this is a server, and the collected data is then analyzed by generative AI.

[0147] Next, the server analyzes the collected food inventory data using a generation AI means. Specifically, it identifies ingredients that are close to their expiration date or that are likely to be discarded from the collected data. This analysis process is carried out using an AI framework such as TENSORFLOW (registered trademark). For example, the generation AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days. This generation AI means analyzes food inventory information efficiently and accurately.

[0148] Based on the analysis results, the server uses a means to provide the user with the identified food ingredient information. The means of providing this information is to provide the user's device with real-time notifications or a dashboard. For example, a notification such as "List of ingredients that need to be consumed today: tomatoes, bread, olive oil" is displayed on the device. This allows the user to immediately understand which ingredients should be prioritized for consumption.

[0149] Based on the provided ingredient information, the user's device uses generative AI to suggest appropriate recipes and menus. This allows the user to create a dish based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish accordingly. This method of creating dishes makes it possible to provide meals efficiently while reducing food waste.

[0150] After the food is served, the user enters the data of the food served into the device, and the data is sent to the server. The server uses the aggregated data to track and report on the food waste reduction effect. For example, it generates reports on the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis. A real-time database such as Firebase is used to efficiently collect and manage data.

[0151] As a concrete example, let's assume that this system has been introduced to a food delivery service. In this service, food inventory information is collected daily from restaurants and affiliated supermarkets and farmers on a server. The generative AI lists ingredients (e.g., tomatoes, bread) that are approaching their expiration date, and notifies the food delivery service's delivery person's device in real time. Based on this notification, the user prepares a dish using tomatoes and bread using the suggested recipe, and delivers the dish through the delivery service. The provided data is sent from the device to a server and compiled, allowing the food delivery service's overall effectiveness in reducing food waste to be regularly evaluated and analyzed.

[0152] Examples of input prompts for generative AI models include:

[0153] "Based on today's food inventory data, please suggest ingredients that need to be consumed and new recipes using those ingredients. Here is the inventory data: {Inventory data in JSON format}"

[0154] This allows users to consume food efficiently and contribute to reducing food waste.

[0155] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0156] Step 1:

[0157] The server uses a network interface to retrieve data via API to collect food inventory information from commercial and agricultural facilities. Specifically, it collects real-time inventory data through the API endpoints "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory."

[0158] Input: Inventory data from API endpoint.

[0159] Output: Food inventory information stored on the server.

[0160] Step 2:

[0161] The server analyzes the collected food inventory data using generative AI. Specifically, it uses AI frameworks such as TensorFlow to identify food items that are nearing their expiration date or are likely to be discarded. In this process, it filters the data by setting conditions such as "expires_in_days < 3."

[0162] Input: Collected food inventory data.

[0163] Output: A list of ingredients that are close to expiry.

[0164] Step 3:

[0165] The server provides information on ingredients identified based on the analysis results to the user's device through real-time notifications and a dashboard, for example, displaying a notification such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[0166] Input: A list of ingredients that are close to expiry.

[0167] Output: Notification to the user's device.

[0168] Step 4:

[0169] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. For example, the generative AI suggests a recipe for "panini with tomatoes and bread."

[0170] Input: A list of ingredients that are close to expiry.

[0171] Output: The proposed recipe.

[0172] Step 5:

[0173] The user creates a dish based on the generative AI's suggestions. For example, the user makes a panini with tomatoes and bread according to the recipe provided.

[0174] Input: A suggested recipe.

[0175] Output: The dish created by the user.

[0176] Step 6:

[0177] The user inputs the recipe data into the terminal and transmits the data to the server.

[0178] Input: Recipe data entered by the user.

[0179] Output: The recipe data sent to the server.

[0180] Step 7:

[0181] The server uses the collected data to track the effectiveness of food waste reduction and periodically reports the results to relevant parties. Specifically, it generates reports on the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis.

[0182] Input: Recipe data sent to the server.

[0183] Output: Report on food waste reduction effect.

[0184] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0185] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, a means for tracking the effect of food waste reduction and reporting the results, and an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described.

[0186] Data collection

[0187] First, the server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. The collection method uses a network interface to call endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." The server then stores the obtained inventory data in its own database.

[0188] Analysis by generative AI

[0189] The server then preprocesses the collected food inventory data and converts it into an analyzable format. The preprocessed data is then input into the generation AI to analyze ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0190] Emotion recognition by emotion engine

[0191] The device uses a camera and microphone to sense the user's facial expressions and tone of voice, which are then analyzed by an emotion engine. The emotion engine recognizes the user's current emotional state (e.g., stress, enjoyment, concentration, etc.) and transmits the results to the means of providing the information.

[0192] Ingredient information and menu suggestions

[0193] The server sends the list of ingredients with predicted waste obtained as a result of the generation AI's analysis to the user's (cafe or restaurant staff's) device. Specifically, the server notifies the device of the ingredient information in JSON format. Based on the emotion recognition results from the emotion engine, the means of providing the information displays the ingredient information in a format that best suits the user's emotions, and the generation AI means suggests appropriate recipes and menus based on the emotion engine's data.

[0194] Cooking and serving

[0195] The device displays menus and recipes suggested by the AI ​​based on the provided ingredient information. For example, if the user is feeling stressed, the AI ​​will suggest easy-to-make or relaxing dishes. The user then prepares and serves the dish based on the suggested recipe. After serving, the user enters the details of the dish and the number of servings into the device, and the data is sent to the server.

[0196] Tracking and reporting food waste reduction

[0197] The server receives and aggregates the food serving data sent by users and tracks the effectiveness of food waste reduction. Specifically, the server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, amount of food waste reduced: 50 kilograms," and notifies relevant parties on a regular basis.

[0198] Specific examples

[0199] If this system were to be implemented in a depopulated area of ​​Hokkaido, a server would collect inventory information daily from commercial and agricultural facilities. The AI ​​would then identify ingredients that are nearing their expiration date, and the emotion engine would recognize the emotions of the cafe staff. For example, if the emotion engine recognized that the user was feeling stressed, the device would suggest a menu item suitable for reducing stress, such as a simple panini made with tomatoes and bread, as suggested by the AI.

[0200] By operating this system, it is possible to effectively reduce food waste and suggest optimal dishes according to the user's emotional state, while also providing career support for young people.

[0201] The processing flow will be explained below.

[0202] Step 1:

[0203] The server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. Specifically, the server calls endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" and stores the obtained inventory data in its own database.

[0204] Step 2:

[0205] The server preprocesses the collected inventory data and converts it into an analyzable format, for example, converting all data into a unified format and imputing missing values.

[0206] Step 3:

[0207] The server inputs the preprocessed data into the generation AI, which analyzes ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3."

[0208] Step 4:

[0209] The server creates a list of ingredients that are predicted to be discarded as a result of the AI's analysis and sends the list to the user's (cafe or restaurant staff) device. Specifically, the server notifies the device of the ingredient information in JSON format.

[0210] Step 5:

[0211] The device notifies the user of the list of ingredients received from the server and displays it on the screen. For example, the device displays information such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[0212] Step 6:

[0213] The device uses a camera and microphone to detect the user's facial expressions and tone of voice, and analyzes the data with an emotion engine. The emotion engine recognizes the user's emotional state (e.g., stress, enjoyment, concentration, etc.) and sends the results to the means of providing the information.

[0214] Step 7:

[0215] The device uses generative AI to suggest appropriate menus and recipes based on the emotion recognition results from the emotion engine. For example, if the user is feeling stressed, the device will display a recipe such as "a simple panini with tomatoes and bread."

[0216] Step 8:

[0217] The user creates a dish based on the proposed recipe. The user inputs the specific number and contents of the dish they want to serve into the terminal, and the data is sent to the server.

[0218] Step 9:

[0219] The server aggregates the food serving data sent by users and tracks the food waste reduction effect. The server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, amount of food waste reduced: 50 kilograms," and notifies relevant parties periodically.

[0220] Example 2

[0221] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0222] Food waste is a major issue in modern society, especially in commercial and agricultural facilities, which place a significant burden on the environment. Furthermore, in the food service industry, staff emotional states often affect the quality of service, but there is a lack of methods to efficiently manage this and provide optimal menu options. Given this situation, a system is needed that can efficiently reduce food waste and provide recipe suggestions that take staff emotional states into account.

[0223] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a collection means, a generation AI means for analyzing food inventory information collected by the collection means, a means for providing the user with ingredient information predicted to be wasted obtained by the analysis, a means for creating a dish based on the ingredient information provided by the user, a means for tracking the effect of food waste reduction and reporting the results, and an emotion engine for recognizing the user's emotions. This enables effective use of food inventory, reduction of food waste, and optimal recipe suggestions taking into account the emotional state of staff.

[0224] "Collection means" refers to a means for obtaining food inventory information from commercial and agricultural facilities, and includes a network interface.

[0225] The "generative AI means" is a means that implements an algorithm that analyzes food inventory information obtained by the collection means and identifies ingredients that are close to their expiration date or that are likely to be discarded.

[0226] The "means for providing" refers to a means for informing the user of the discard-predicted ingredient information obtained through the analysis.

[0227] The "means for creating a dish" is a means for suggesting recipes and menus for a dish based on the ingredient information provided by the user, and for actually creating the dish.

[0228] The "means for tracking the effect of food waste reduction and reporting the results" is a means for aggregating data on cooking provided by users, measuring the effect of food waste reduction, and reporting the results.

[0229] An "emotion engine" is a means of sensing and analyzing a user's facial expressions and tone of voice to recognize their current emotional state.

[0230] The present invention is a system focused on reducing food waste and managing employee emotions. The system includes a collection means, a generation AI means, a serving means, a cooking means, a means for tracking the food waste reduction effect and reporting the results, and an emotion engine that recognizes the user's emotions.

[0231] Data collection

[0232] The server plays the main role. At a specified time each day, the server uses a network interface to access the databases of local commercial and agricultural facilities to obtain food inventory information. Specifically, it calls API endpoints (e.g., "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory"). The obtained inventory data is stored in the server's database.

[0233] Analysis by generative AI

[0234] The server then preprocesses the collected food inventory data and converts it into an analyzable format. Preprocessing includes data cleansing and formatting. The server then inputs the preprocessed data into the generation AI. Based on the collected data, the generation AI identifies ingredients that are close to their expiration date or are likely to be discarded. Conditions such as "expires_in_days < 3" are used for this analysis.

[0235] Emotion recognition by emotion engine

[0236] The device senses the user's facial expressions and tone of voice using a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state (e.g., stress, joy, concentration, etc.). The emotion engine's analysis results are sent to the device providing the service.

[0237] Ingredient information and menu suggestions

[0238] The server sends the list of ingredients predicted to be wasted, obtained as a result of the analysis by the generation AI, to the user's device. This information is sent in JSON format. The means of providing this information is to display the ingredient information in a way that best suits the user's emotions, based on the results of the emotion engine. Furthermore, the generation AI suggests appropriate recipes and menus based on the data from the emotion engine.

[0239] Specific examples

[0240] For example, consider the case where this system is introduced in a depopulated area of ​​Hokkaido. The server collects inventory information from commercial and agricultural facilities every day, and the generation AI identifies ingredients that are close to their expiration date. If the emotion engine recognizes the emotions of the cafe staff and determines that the user is feeling stressed, the device will suggest a menu item that will help reduce stress, such as a simple panini with tomatoes and bread, based on the generation AI's suggestions.

[0241] This system effectively reduces food waste and provides the optimal meal according to the user's emotional state.

[0242] Example prompt statement

[0243] "Collect this week's inventory data."

[0244] "Generate a list of ingredients with a shelf life of less than 3 days"

[0245] "Analyze the user's emotions and suggest the best menu."

[0246] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0247] Step 1:

[0248] The server accesses the database of local commercial and agricultural facilities at a specified time each day. It uses an API endpoint (e.g., "local_supermarket_api / get_inventory" or "local_farm_api / get_inventory") as input to retrieve food inventory information. As output, the retrieved inventory data is stored in the server's database. Specifically, the server sends an API request, parses the JSON data received as a response, and extracts and stores the necessary information.

[0249] Step 2:

[0250] The server preprocesses the food inventory data collected. The input is the inventory data saved in the previous step, and data cleansing (e.g., filling in missing values ​​and removing outliers) and formatting (e.g., standardizing the data format) are performed. The output is the preprocessed data. Specifically, the server reads the data from the database, converts it into a format such as a data frame, and performs the necessary cleansing and formatting.

[0251] Step 3:

[0252] The server inputs the preprocessed data into the generation AI. The input data is formatted food inventory data. The generation AI performs analysis to identify ingredients that are close to their expiration date or are likely to be discarded. The output is a list of ingredients that need to be consumed. Specifically, the server inputs the data into the generation AI model and performs filtering by applying conditions such as "expires_in_days < 3."

[0253] Step 4:

[0254] The device senses the user's facial expressions and tone of voice using a camera and microphone. The input is image and audio data acquired from the camera and microphone. The emotion engine analyzes this data and recognizes the user's emotional state. The output is the recognized emotional state (e.g., stress, enjoyment, concentration). Specifically, the device collects image and audio data, sends it to the emotion engine for analysis, and determines the emotional state.

[0255] Step 5:

[0256] The server sends the list of ingredients with a predicted waste potential obtained as a result of the generation AI's analysis to the user's device. The input is the list of ingredients with a predicted waste potential and the emotional state analysis results of the emotion engine. The means of providing this information is to display the ingredient information in an optimal form for the user based on the emotional state. The output is adjusted ingredient information and recipe suggestions. Specifically, the server generates appropriate messages and recipes based on the ingredient list and emotional state and sends them to the device.

[0257] Step 6:

[0258] The device displays the cooking menu and recipes suggested by the generation AI based on the ingredient information provided. The input is the ingredient information and recipe sent from the server. The output is the cooking menu and recipe displayed to the user. In concrete terms, the device displays the received information on the screen, and the user views it.

[0259] Step 7:

[0260] The user prepares and serves a dish based on the suggested recipe. The input is the displayed recipe information. The output is the prepared dish and serving data. In concrete terms, the user prepares the dish according to the recipe and inputs post-serving data (e.g., number of servings and remaining ingredients) into the terminal.

[0261] Step 8:

[0262] The terminal sends the food serving data entered by the user to the server. The input is the data after serving (e.g., number of servings and remaining ingredients). The output is the serving data stored on the server. Specifically, the terminal sends the entered data to the server, and the server stores it in a database.

[0263] Step 9:

[0264] The server aggregates the provided data and tracks the food waste reduction effect. The input is the provided data. The output is a report of the aggregated food waste reduction effect. Specifically, the server aggregates the provided data, calculates the reduction effect for each period (e.g., number of dishes served, amount of food waste reduced), and generates a report.

[0265] Step 10:

[0266] The server periodically notifies the relevant parties of the generated report. The input is the summary report. The output is the report sent to the relevant parties. Specifically, the server sends the generated report to the relevant parties via email or other means, and periodically updates it.

[0267] (Application example 2)

[0268] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0269] Conventional food inventory management and recipe recommendation systems do not take into account the user's emotional state, which can result in low user satisfaction. It is also difficult to efficiently utilize ingredients that are likely to be wasted. Furthermore, there is a lack of a mechanism for clearly tracking and reporting the effectiveness of food waste reduction. Therefore, the challenge is to achieve both appropriate recipe recommendations based on the user's emotional state and food waste reduction.

[0270] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0271] In this invention, the server includes a collection means, a generation AI means, an emotion engine that recognizes the user's emotional state, a means for proposing a dish menu, a means for preparing a dish, a means for generating and executing a delivery order, and a means for tracking the food waste reduction effect and reporting the results. This makes it possible to propose an appropriate dish menu based on the user's emotional state, efficiently use ingredients that are predicted to be wasted, and clearly track and report the food waste reduction effect.

[0272] "Collection means" refers to the means used to collect food inventory information from local commercial and agricultural facilities.

[0273] "Generative AI means" refers to means including artificial intelligence for analyzing collected food inventory information and identifying food ingredient information that is predicted to be discarded.

[0274] The "means for providing to the user" is a means for displaying to the user the ingredient information analyzed by the generating AI means.

[0275] An "emotion engine" is a means for detecting a user's facial expression, tone of voice, etc., and recognizing their emotional state.

[0276] The "means for suggesting a dish menu" is a means for suggesting an appropriate dish menu to the user based on the emotional state of the user recognized by the emotion engine.

[0277] The "means for creating a dish" refers to the means by which the user actually creates a dish based on the provided ingredient information and the proposed dish menu.

[0278] The "means for generating and executing a delivery order" refers to a means for generating a delivery order based on the proposed food menu and ordering food from a partner restaurant.

[0279] "Means for tracking the effects of food waste reduction and reporting the results" refers to a means for tracking the effects of food waste reduction based on the dishes created and reporting the results to relevant parties.

[0280] The present invention is a system that includes a collection means, a generation AI means, a provision means, an emotion engine, a menu suggestion means, a cooking means, a delivery order generation and execution means, and a means for tracking the effect of food waste reduction and reporting the results. Specific embodiments of this system are described below.

[0281] Data collection and analysis

[0282] First, the server uses the collection method to access the databases of local commercial and agricultural facilities and obtain food inventory information via API. Specifically, food inventory information is collected by calling endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" through the network interface. The collected inventory data is stored in the server's database.

[0283] The server then preprocesses the collected food inventory data and converts it into an analyzable format. This preprocessed data is then input into the generation AI to analyze ingredients that are close to their expiration date or likely to be discarded. The generation AI filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0284] Emotion Recognition and Menu Suggestion

[0285] The user's device uses an emotion engine to sense the user's facial expressions and tone of voice using a camera and microphone to recognize their emotional state. The recognized emotional state is sent to the server. The server then suggests appropriate cooking menus based on the user's emotional state recognized by the emotion engine and the results of the analysis described above. For example, if the server recognizes that the user is feeling stressed, it will suggest easy-to-make, relaxing dishes.

[0286] Cooking and delivery orders

[0287] When the user selects a suggested menu item, the server generates a delivery order based on the selected menu item. The delivery order is sent to a local partner restaurant, which delivers the food to the user. After the food is delivered, the user inputs the details of the food and the number of servings into the terminal, and the data is sent to the server.

[0288] Tracking and reporting food waste reduction

[0289] The server receives and aggregates the food serving data sent by users and tracks the effectiveness of food waste reduction. Specifically, it generates a report of the aggregated results in the form of "Number of dishes served this week: 500 plates, Food waste reduction: 50 kilograms" and notifies relevant parties on a regular basis.

[0290] Examples of concrete examples and prompts

[0291] If this system were to be implemented in a depopulated area of ​​Hokkaido, the server would collect inventory information daily from commercial and agricultural facilities. The generative AI would then identify ingredients that are nearing their expiration date, and the emotion engine would recognize the emotions of the cafe staff. For example, if the emotion engine recognized that the user was feeling stressed, the server would suggest a menu item suitable for reducing stress, such as a simple panini made with tomatoes and bread. Operating this system would effectively reduce food waste and enable optimal recipe suggestions based on the user's emotional state.

[0292] Example prompt for a generative AI model:

[0293] Ingredients: Tomato, Best before date: 2 days

[0294] User Emotion: Stress

[0295] Menu suggestion: Easy to make, relaxing meals

[0296] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0297] Step 1:

[0298] The server accesses the database of local commercial and agricultural facilities at the specified time and retrieves food inventory information via API, specifically calling endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" using the network interface.

[0299] Input: API endpoint URL

[0300] Output: Food inventory information in JSON format

[0301] Specific behavior: The server sends an API request, receives food inventory information as a response, and stores it in a database.

[0302] Step 2:

[0303] The server preprocesses the collected food inventory data and converts it into an analyzable format, extracts necessary fields from the collected data, and cleans the data.

[0304] Input: Stored food inventory information in JSON format

[0305] Output: Preprocessed food inventory data

[0306] Specific operations: Normalize data, correct outliers, and extract necessary data.

[0307] Step 3:

[0308] The server inputs the preprocessed data into the generation AI means, which analyzes ingredients that are close to their expiration date or are likely to be discarded. The generation AI filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that are likely to be discarded.

[0309] Input: Preprocessed food inventory data

[0310] Output: List of ingredients predicted to be wasted

[0311] What it does: It uses a generative AI model to filter ingredients that meet the criteria and extract the results in list form.

[0312] Step 4:

[0313] The device uses an emotion engine to recognize the user's emotional state by detecting their facial expressions and tone of voice using a camera and microphone, and the emotional state is transmitted from the device to the server.

[0314] Input: User's facial expression data, tone of voice data

[0315] Output: Emotional state data

[0316] What it does: It uses a camera and microphone to collect data, which is then analyzed by an emotion engine to identify emotional states such as stress, enjoyment, and concentration.

[0317] Step 5:

[0318] The server uses a generative AI to suggest appropriate meal plans based on the user's emotional state recognized by the emotion engine and the list of ingredients that are predicted to be wasted. For example, if the user is feeling stressed, the server will suggest simple dishes that will relax them.

[0319] Input: Emotional state data, food waste prediction list

[0320] Output: Suggested food menu

[0321] Specific operation: Using generative AI means, prompts are created to generate the optimal cooking menu based on the emotional state and ingredient information, and the results are generated.

[0322] Step 6:

[0323] The user selects a suggested dish menu on the terminal, and this selection information is sent to the server.

[0324] Input: Menu data for special dishes

[0325] Output: User menu selection information

[0326] Specific behavior: Displays the suggested food menu on the device screen and provides a UI interface to receive the user's selection.

[0327] Step 7:

[0328] The server generates a delivery order based on the food menu selected by the user and sends it to the partner restaurant.

[0329] Input: User menu selection information

[0330] Output: Delivery order information

[0331] Specific operation: Based on the selected menu information, a delivery order is generated and sent to the partner restaurant's ordering system.

[0332] Step 8:

[0333] The food is delivered to the user based on the delivery order. After that, the user inputs the details of the food and the number of servings into the terminal, and the data is sent to the server.

[0334] Input: User input data after food is served

[0335] Output: Food offering information data

[0336] Specific operation: Provides a UI interface for inputting the provided dish information on the device, and sends the collected data to the server.

[0337] Step 9:

[0338] The server receives and aggregates the food provision data sent, tracks the effectiveness of food waste reduction, and generates a report of the aggregated results and notifies relevant parties on a regular basis.

[0339] Input: Food offering information data

[0340] Output: Food waste reduction effect report

[0341] Specific operation: The provided information stored in the database is compiled, a report is generated in the form of "Number of dishes provided this week: 500 plates, amount of food waste reduced: 50 kilograms," and the relevant parties are notified.

[0342] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0343] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0344] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0345] [Second embodiment]

[0346] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0347] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0348] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0349] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0350] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0351] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0352] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0353] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0354] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0355] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0356] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0357] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0358] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, and a means for tracking the effects of food waste reduction and reporting the results. A specific embodiment of this system will be described.

[0359] Data collection

[0360] First, a server collects food inventory information from commercial and agricultural facilities located in depopulated areas. The collection method is to obtain data via API using a network interface. For example, the server obtains food inventory data using APIs such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory."

[0361] Analysis by generative AI

[0362] Next, the server analyzes the collected food inventory data using a generation AI method. Specifically, it identifies ingredients that are close to their expiration date or that are likely to be discarded if not consumed from the collected data. For example, the generation AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0363] Providing information on ingredients

[0364] Based on the analysis results, the server uses a means to provide the user with information about the identified ingredients. The information is provided to the user's device via real-time notifications and a dashboard. For example, a notification such as "List of ingredients to be consumed today: tomatoes, bread, olive oil" is displayed on the device.

[0365] Menu proposal and cooking

[0366] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. This allows the user to create dishes based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish according to that recipe.

[0367] Tracking and reporting food waste reduction

[0368] After a user serves a dish, they input the data of the dish into the device, and the data is sent to the server. The server uses the aggregated data to track the food waste reduction effect and report the results. For example, it generates a report of the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis.

[0369] As a concrete example, let's assume that this system is introduced in a depopulated area of ​​Hokkaido. Food inventory information is collected daily from supermarkets and farmers in the area and sent to a server. The server uses generation AI to create a list of ingredients (e.g., tomatoes, bread) that need to be consumed by tomorrow, and notifies the terminals of local cafe staff in real time. Based on this notification, the cafe staff prepares and serves dishes such as paninis using tomatoes and bread according to the suggested recipe. The provided data is sent from the terminals to the server and compiled, allowing the effectiveness of food waste reduction throughout the area to be regularly evaluated and reported.

[0370] In this way, the system of the present invention can effectively reduce food waste and simultaneously support young people's careers.

[0371] The processing flow will be explained below.

[0372] Step 1:

[0373] The server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. Specifically, the server calls endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" and stores the obtained inventory data in its own database.

[0374] Step 2:

[0375] The server preprocesses the collected inventory data and converts it into an analyzable format, for example, converting all data into a unified format and imputing missing values.

[0376] Step 3:

[0377] The server inputs the preprocessed data into the generation AI, which analyzes ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3."

[0378] Step 4:

[0379] The server creates a list of ingredients that are predicted to be discarded as a result of the AI's analysis and sends the list to the user's (cafe or restaurant staff) device. Specifically, the server notifies the device of the ingredient information in JSON format.

[0380] Step 5:

[0381] The device notifies the user of the list of ingredients received from the server and displays it on the screen. For example, the device displays information such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[0382] Step 6:

[0383] The device uses a generation AI to suggest menus and recipes using ingredients that are predicted to be wasted. Specifically, the device requests recipe suggestions from the generation AI based on the "available_ingredients" data, and displays recipes such as "Panini with tomatoes and bread" to the user.

[0384] Step 7:

[0385] The user creates a dish based on the proposed recipe. The user inputs the specific number and contents of the dish they want to serve into the terminal, and the data is sent to the server.

[0386] Step 8:

[0387] The server receives and aggregates the food serving data sent by users and tracks the food waste reduction effect. The server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, Amount of food waste reduced: 50 kilograms."

[0388] Step 9:

[0389] The server periodically notifies the relevant parties of the reports it generates, and evaluates and reports on the effectiveness of the entire system. For example, the server automatically generates a weekly report and sends it to the relevant parties by email.

[0390] Example 1

[0391] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0392] The problem of food waste is a major issue that causes environmental burdens and economic losses. In particular, in depopulated areas, distribution and sales efficiency is low, making it easy for excess food inventory to occur. As a result, food that is approaching its expiration date is often discarded. Furthermore, there is a lack of a system for sharing food inventory information across the entire region and using that information to make effective cooking suggestions, so concrete measures to reduce waste are needed.

[0393] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0394] In this invention, the server includes a means for collecting food inventory information from commercial facilities and agricultural facilities, a generating AI means for analyzing the food inventory information collected by the collecting means, a means for the generating AI means to identify ingredients that are close to their expiration date or are expected to be discarded, a means for providing the user with the ingredient information obtained by the analysis, a means for suggesting dishes based on the ingredient information provided by the user, a means for the user to prepare the suggested dishes, a means for tracking data on the dishes prepared by the user, and a means for reporting the effects of food waste reduction. This enables a consistent system that covers everything from collecting food inventory information to analyzing it, promoting consumption, and tracking and reporting the effects.

[0395] A "commercial establishment" is a place operated for the sale of food and essential commodities.

[0396] An "agricultural facility" is a facility designed for the cultivation and harvesting of agricultural crops.

[0397] "Food inventory information" refers to data such as the type, quantity, and expiration date of food at commercial and agricultural facilities.

[0398] "Collection methods" refers to the methods and techniques used to collect food inventory information from commercial and agricultural establishments.

[0399] "Generative AI means" is an artificial intelligence technology that analyzes collected food inventory information and extracts important ingredient information based on specific conditions.

[0400] "Analysis" is the process of evaluating collected food inventory information and identifying ingredients that are nearing their expiration date or are expected to be discarded.

[0401] "Means of providing" refers to the methods and techniques for informing users of the analysis results.

[0402] "Means for suggesting dishes" refers to a method for suggesting appropriate recipes and menus based on the ingredient information provided by the user.

[0403] "Means for creating a dish" refers to the methods and techniques that a user uses to create a dish according to a suggested recipe.

[0404] "Tracking means" refers to the method of collecting data on the dishes created by users and analyzing it to confirm the effectiveness of food waste reduction.

[0405] "Reporting means" refers to the methods and technologies used to inform users and other interested parties of collected data and analysis results.

[0406] "Food waste" refers to the amount and type of food that is not consumed and is destined to be discarded.

[0407] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, and a means for tracking the effects of food waste reduction and reporting the results. A specific embodiment of this system will be described.

[0408] Data collection

[0409] First, a server collects food inventory information from commercial and agricultural facilities located in depopulated areas. The collection method is to obtain data via API using a network interface. For example, the server obtains food inventory data using APIs such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." This allows food inventory information from commercial and agricultural facilities to be aggregated on the server.

[0410] Analysis by generative AI

[0411] Next, the server analyzes the collected food inventory data using a generative AI method. Specifically, a generative AI model is used to identify ingredients that are close to their expiration date or that are likely to be discarded if not consumed from the collected data. For example, the generative AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0412] Providing information on ingredients

[0413] Based on the analysis results, the server uses a means to provide the user with information about the identified ingredients. The information is provided to the user's device via real-time notifications and a dashboard. By displaying notifications such as "List of ingredients that need to be consumed today: tomatoes, bread, olive oil" on the device, the user can understand which ingredients should be prioritized for consumption.

[0414] Menu proposal and cooking

[0415] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. This allows the user to create a dish based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish according to that recipe. An example of a specific prompt might be, "Please suggest a simple dish using two tomatoes and one loaf of bread."

[0416] Tracking and reporting food waste reduction

[0417] After a user serves a dish, they input the data of the dish into the device, and the data is sent to the server. The server uses the aggregated data to track the food waste reduction effect and report the results. For example, it generates a report of the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis, thereby visualizing the food waste reduction effect of the entire region.

[0418] As a concrete example, let's assume that this system is introduced in a depopulated area of ​​Hokkaido. Food inventory information is collected daily from supermarkets and farmers in the area and sent to a server. The server uses generation AI to create a list of ingredients (e.g., tomatoes, bread) that need to be consumed by tomorrow, and notifies the terminals of local cafe staff in real time. Based on this notification, the cafe staff prepares and serves dishes such as paninis using tomatoes and bread using suggested recipes. The provided data is sent from the terminals to the server, where it is compiled and the effectiveness of food waste reduction throughout the area is regularly evaluated and reported.

[0419] In this way, the system of the present invention can effectively reduce food waste and simultaneously support young people's careers.

[0420] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0421] Step 1:

[0422] The server collects food inventory information from commercial and agricultural facilities located in depopulated areas.

[0423] Input: Your commercial or agricultural facility's API endpoint (e.g., "local_supermarket_api / get_inventory")

[0424] Specific operation: The server issues an API request via the network interface to obtain food inventory information.

[0425] Output: The acquired food inventory information data (e.g., JSON format) is saved on the server.

[0426] Step 2:

[0427] The food inventory data collected by the server is analyzed using generative AI methods.

[0428] Input: Food inventory data collected in Step 1

[0429] Specific operation: The server inputs food inventory data into the generative AI model and filters the data using the condition "expires_in_days < 3".

[0430] Output: A list of ingredients that are nearing their expiration date or are predicted to be discarded is generated.

[0431] Step 3:

[0432] The server uses a means for providing the user with the identified ingredient information.

[0433] Input: List of ingredients parsed in step 2

[0434] Specific operation: The server creates a notification message in real time based on the analysis results and sends it to the user's device.

[0435] Output: A notification of "List of ingredients to be consumed today" is displayed on the user's device.

[0436] Step 4:

[0437] The device uses generative AI based on the ingredient information provided to suggest appropriate recipes and menus.

[0438] Input: Ingredient information displayed on the user's device

[0439] Specific operation: The device inputs ingredient information into the generation AI to generate appropriate recipes and menus. An example of a prompt is "Please suggest a simple dish using two tomatoes and one loaf of bread."

[0440] Output: The suggested recipes and menus are displayed to the user.

[0441] Step 5:

[0442] The user creates a dish based on the suggested recipe.

[0443] Input: Recipe information displayed on the device

[0444] Specific operation: The user follows the instructions displayed on the device to create a dish using ingredients.

[0445] Output: The created dish (e.g., a panini with tomatoes and bread)

[0446] Step 6:

[0447] After the user has prepared the food, the user inputs data of the prepared food into the terminal, and the data is transmitted to the server.

[0448] Input: Information about the dish served (name of dish, ingredients used, number served, etc.)

[0449] Specific operation: The user enters recipe information into the device, and the device sends the data to the server.

[0450] Output: The data of the dishes served is saved on the server.

[0451] Step 7:

[0452] The server uses the collected data to track the effectiveness of food waste reduction and report the results.

[0453] Input: Food data submitted in step 6

[0454] Specific operation: The server analyzes the number of dishes served and the amount of food waste reduced, generates a report, and notifies relevant parties on a weekly or monthly basis.

[0455] Output: Report on food waste reduction (e.g., "Number of dishes served this week: 100, amount of food waste reduced: 50kg")

[0456] (Application example 1)

[0457] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0458] In recent years, the increase in food delivery services has exacerbated the problem of food waste. In addition, food inventory management at restaurants and supermarkets has become increasingly complex. Managing ingredients with approaching expiration dates is particularly difficult, resulting in large amounts of food being wasted. Furthermore, manually managing inventory and creating menus is time-consuming, labor-intensive, and inefficient. Therefore, there is a need for a system that can efficiently manage food inventory and suggest appropriate menus while reducing food waste.

[0459] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0460] In this invention, the server includes a collection means, a generation AI means, a provision means, a recipe creation means, and an effect tracking means. This allows the server to provide ingredient information to the user's device via real-time notifications and a dashboard, and furthermore, it is possible to suggest appropriate recipes using the generation AI. This encourages the efficient use of ingredients that are close to their expiration date, thereby reducing food waste.

[0461] A "collection instrument" is a device or system for collecting food inventory information from commercial or agricultural establishments.

[0462] "Generative AI methods" are artificial intelligence algorithms used to analyze collected food inventory information and identify ingredients that are nearing their expiration date or are likely to be discarded.

[0463] The "provision means" is a device or system for notifying or presenting the user with the ingredient information identified based on the analysis results.

[0464] The "dish preparation means" is a device or system that proposes an appropriate recipe to the user based on the provided ingredient information and prepares the dish.

[0465] "Effect Tracking Means" refers to a device or system that aggregates cooking data provided by users and tracks and reports the food waste reduction effect.

[0466] A "network interface" is a communication means for sending and receiving data between multiple devices or systems to collect food inventory information.

[0467] "Terminal" refers to an information display and input device used by a user, such as a smartphone, smart glasses, or head-mounted display.

[0468] "Real-time notification" is a communication function for instantly transmitting analyzed ingredient information to the user's terminal.

[0469] A "dashboard" is an interface that displays visually organized data and notifications so that users can intuitively grasp information.

[0470] "Recipe suggestions" are cooking methods suggested by the generative AI based on collected and analyzed ingredient information.

[0471] The present invention is a food waste reduction system that consists of a collection means, a generation AI means, a provision means, a cooking means, and an effect tracking means. Details of each means and a specific embodiment of the system are explained below.

[0472] First, the server collects food inventory information from commercial and agricultural facilities. The collection method is to obtain data via API using a network interface. For example, food inventory data is collected using API endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." The hardware used for this is a server, and the collected data is then analyzed by generative AI.

[0473] Next, the server analyzes the collected food inventory data using a generative AI means. Specifically, it identifies ingredients that are close to their expiration date or that are likely to be discarded from the collected data. This analysis process is carried out using an AI framework such as TensorFlow. For example, the generative AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days. This generative AI means analyzes food inventory information efficiently and accurately.

[0474] Based on the analysis results, the server uses a means to provide the user with the identified food ingredient information. The means of providing this information is to provide the user's device with real-time notifications or a dashboard. For example, a notification such as "List of ingredients that need to be consumed today: tomatoes, bread, olive oil" is displayed on the device. This allows the user to immediately understand which ingredients should be prioritized for consumption.

[0475] Based on the provided ingredient information, the user's device uses generative AI to suggest appropriate recipes and menus. This allows the user to create a dish based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish accordingly. This method of creating dishes makes it possible to provide meals efficiently while reducing food waste.

[0476] After the food is served, the user enters the data of the food served into the device, and the data is sent to the server. The server uses the aggregated data to track and report on the food waste reduction effect. For example, it generates reports on the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis. A real-time database such as Firebase is used to efficiently collect and manage data.

[0477] As a concrete example, let's assume that this system has been introduced to a food delivery service. In this service, food inventory information is collected daily from restaurants and affiliated supermarkets and farmers on a server. The generative AI lists ingredients (e.g., tomatoes, bread) that are approaching their expiration date, and notifies the food delivery service's delivery person's device in real time. Based on this notification, the user prepares a dish using tomatoes and bread using the suggested recipe, and delivers the dish through the delivery service. The provided data is sent from the device to a server and compiled, allowing the food delivery service's overall effectiveness in reducing food waste to be regularly evaluated and analyzed.

[0478] Examples of input prompts for generative AI models include:

[0479] "Based on today's food inventory data, please suggest ingredients that need to be consumed and new recipes using those ingredients. Here is the inventory data: {Inventory data in JSON format}"

[0480] This allows users to consume food efficiently and contribute to reducing food waste.

[0481] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0482] Step 1:

[0483] The server uses a network interface to retrieve data via API to collect food inventory information from commercial and agricultural facilities. Specifically, it collects real-time inventory data through the API endpoints "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory."

[0484] Input: Inventory data from API endpoint.

[0485] Output: Food inventory information stored on the server.

[0486] Step 2:

[0487] The server analyzes the collected food inventory data using generative AI. Specifically, it uses AI frameworks such as TensorFlow to identify food items that are nearing their expiration date or are likely to be discarded. In this process, it filters the data by setting conditions such as "expires_in_days < 3."

[0488] Input: Collected food inventory data.

[0489] Output: A list of ingredients that are close to expiry.

[0490] Step 3:

[0491] The server provides information on ingredients identified based on the analysis results to the user's device through real-time notifications and a dashboard, for example, displaying a notification such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[0492] Input: A list of ingredients that are close to expiry.

[0493] Output: Notification to the user's device.

[0494] Step 4:

[0495] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. For example, the generative AI suggests a recipe for "panini with tomatoes and bread."

[0496] Input: A list of ingredients that are close to expiry.

[0497] Output: The proposed recipe.

[0498] Step 5:

[0499] The user creates a dish based on the generative AI's suggestions. For example, the user makes a panini with tomatoes and bread according to the recipe provided.

[0500] Input: A suggested recipe.

[0501] Output: The dish created by the user.

[0502] Step 6:

[0503] The user inputs the recipe data into the terminal and transmits the data to the server.

[0504] Input: Recipe data entered by the user.

[0505] Output: The recipe data sent to the server.

[0506] Step 7:

[0507] The server uses the collected data to track the effectiveness of food waste reduction and periodically reports the results to relevant parties. Specifically, it generates reports on the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis.

[0508] Input: Recipe data sent to the server.

[0509] Output: Report on food waste reduction effect.

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

[0511] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, a means for tracking the effect of food waste reduction and reporting the results, and an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described.

[0512] Data collection

[0513] First, the server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. The collection method uses a network interface to call endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." The server then stores the obtained inventory data in its own database.

[0514] Analysis by generative AI

[0515] The server then preprocesses the collected food inventory data and converts it into an analyzable format. The preprocessed data is then input into the generation AI to analyze ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0516] Emotion recognition by emotion engine

[0517] The device uses a camera and microphone to sense the user's facial expressions and tone of voice, which are then analyzed by an emotion engine. The emotion engine recognizes the user's current emotional state (e.g., stress, enjoyment, concentration, etc.) and transmits the results to the means of providing the information.

[0518] Ingredient information and menu suggestions

[0519] The server sends the list of ingredients with predicted waste obtained as a result of the generation AI's analysis to the user's (cafe or restaurant staff's) device. Specifically, the server notifies the device of the ingredient information in JSON format. Based on the emotion recognition results from the emotion engine, the means of providing the information displays the ingredient information in a format that best suits the user's emotions, and the generation AI means suggests appropriate recipes and menus based on the emotion engine's data.

[0520] Cooking and serving

[0521] The device displays menus and recipes suggested by the AI ​​based on the provided ingredient information. For example, if the user is feeling stressed, the AI ​​will suggest easy-to-make or relaxing dishes. The user then prepares and serves the dish based on the suggested recipe. After serving, the user enters the details of the dish and the number of servings into the device, and the data is sent to the server.

[0522] Tracking and reporting food waste reduction

[0523] The server receives and aggregates the food serving data sent by users and tracks the effectiveness of food waste reduction. Specifically, the server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, amount of food waste reduced: 50 kilograms," and notifies relevant parties on a regular basis.

[0524] Specific examples

[0525] If this system were to be implemented in a depopulated area of ​​Hokkaido, a server would collect inventory information daily from commercial and agricultural facilities. The AI ​​would then identify ingredients that are nearing their expiration date, and the emotion engine would recognize the emotions of the cafe staff. For example, if the emotion engine recognized that the user was feeling stressed, the device would suggest a menu item suitable for reducing stress, such as a simple panini made with tomatoes and bread, as suggested by the AI.

[0526] By operating this system, it is possible to effectively reduce food waste and suggest optimal dishes according to the user's emotional state, while also providing career support for young people.

[0527] The processing flow will be explained below.

[0528] Step 1:

[0529] The server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. Specifically, the server calls endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" and stores the obtained inventory data in its own database.

[0530] Step 2:

[0531] The server preprocesses the collected inventory data and converts it into an analyzable format, for example, converting all data into a unified format and imputing missing values.

[0532] Step 3:

[0533] The server inputs the preprocessed data into the generation AI, which analyzes ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3."

[0534] Step 4:

[0535] The server creates a list of ingredients that are predicted to be discarded as a result of the AI's analysis and sends the list to the user's (cafe or restaurant staff) device. Specifically, the server notifies the device of the ingredient information in JSON format.

[0536] Step 5:

[0537] The device notifies the user of the list of ingredients received from the server and displays it on the screen. For example, the device displays information such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[0538] Step 6:

[0539] The device uses a camera and microphone to detect the user's facial expressions and tone of voice, and analyzes the data with an emotion engine. The emotion engine recognizes the user's emotional state (e.g., stress, enjoyment, concentration, etc.) and sends the results to the means of providing the information.

[0540] Step 7:

[0541] The device uses generative AI to suggest appropriate menus and recipes based on the emotion recognition results from the emotion engine. For example, if the user is feeling stressed, the device will display a recipe such as "a simple panini with tomatoes and bread."

[0542] Step 8:

[0543] The user creates a dish based on the proposed recipe. The user inputs the specific number and contents of the dish they want to serve into the terminal, and the data is sent to the server.

[0544] Step 9:

[0545] The server aggregates the food serving data sent by users and tracks the food waste reduction effect. The server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, amount of food waste reduced: 50 kilograms," and notifies relevant parties periodically.

[0546] Example 2

[0547] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0548] Food waste is a major issue in modern society, especially in commercial and agricultural facilities, which place a significant burden on the environment. Furthermore, in the food service industry, staff emotional states often affect the quality of service, but there is a lack of methods to efficiently manage this and provide optimal menu options. Given this situation, a system is needed that can efficiently reduce food waste and provide recipe suggestions that take staff emotional states into account.

[0549] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a collection means, a generation AI means for analyzing food inventory information collected by the collection means, a means for providing the user with ingredient information predicted to be wasted obtained by the analysis, a means for creating a dish based on the ingredient information provided by the user, a means for tracking the effect of food waste reduction and reporting the results, and an emotion engine for recognizing the user's emotions. This enables effective use of food inventory, reduction of food waste, and optimal recipe suggestions taking into account the emotional state of staff.

[0550] "Collection means" refers to a means for obtaining food inventory information from commercial and agricultural facilities, and includes a network interface.

[0551] The "generative AI means" is a means that implements an algorithm that analyzes food inventory information obtained by the collection means and identifies ingredients that are close to their expiration date or that are likely to be discarded.

[0552] The "means for providing" refers to a means for informing the user of the discard-predicted ingredient information obtained through the analysis.

[0553] The "means for creating a dish" is a means for suggesting recipes and menus for a dish based on the ingredient information provided by the user, and for actually creating the dish.

[0554] The "means for tracking the effect of food waste reduction and reporting the results" is a means for aggregating data on cooking provided by users, measuring the effect of food waste reduction, and reporting the results.

[0555] An "emotion engine" is a means of sensing and analyzing a user's facial expressions and tone of voice to recognize their current emotional state.

[0556] The present invention is a system focused on reducing food waste and managing employee emotions. The system includes a collection means, a generation AI means, a serving means, a cooking means, a means for tracking the food waste reduction effect and reporting the results, and an emotion engine that recognizes the user's emotions.

[0557] Data collection

[0558] The server plays the main role. At a specified time each day, the server uses a network interface to access the databases of local commercial and agricultural facilities to obtain food inventory information. Specifically, it calls API endpoints (e.g., "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory"). The obtained inventory data is stored in the server's database.

[0559] Analysis by generative AI

[0560] The server then preprocesses the collected food inventory data and converts it into an analyzable format. Preprocessing includes data cleansing and formatting. The server then inputs the preprocessed data into the generation AI. Based on the collected data, the generation AI identifies ingredients that are close to their expiration date or are likely to be discarded. Conditions such as "expires_in_days < 3" are used for this analysis.

[0561] Emotion recognition by emotion engine

[0562] The device senses the user's facial expressions and tone of voice using a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state (e.g., stress, joy, concentration, etc.). The emotion engine's analysis results are sent to the device providing the service.

[0563] Ingredient information and menu suggestions

[0564] The server sends the list of ingredients predicted to be wasted, obtained as a result of the analysis by the generation AI, to the user's device. This information is sent in JSON format. The means of providing this information is to display the ingredient information in a way that best suits the user's emotions, based on the results of the emotion engine. Furthermore, the generation AI suggests appropriate recipes and menus based on the data from the emotion engine.

[0565] Specific examples

[0566] For example, consider the case where this system is introduced in a depopulated area of ​​Hokkaido. The server collects inventory information from commercial and agricultural facilities every day, and the generation AI identifies ingredients that are close to their expiration date. If the emotion engine recognizes the emotions of the cafe staff and determines that the user is feeling stressed, the device will suggest a menu item that will help reduce stress, such as a simple panini with tomatoes and bread, based on the generation AI's suggestions.

[0567] This system effectively reduces food waste and provides the optimal meal according to the user's emotional state.

[0568] Example prompt statement

[0569] "Collect this week's inventory data."

[0570] "Generate a list of ingredients with a shelf life of less than 3 days"

[0571] "Analyze the user's emotions and suggest the best menu."

[0572] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0573] Step 1:

[0574] The server accesses the database of local commercial and agricultural facilities at a specified time each day. It uses an API endpoint (e.g., "local_supermarket_api / get_inventory" or "local_farm_api / get_inventory") as input to retrieve food inventory information. As output, the retrieved inventory data is stored in the server's database. Specifically, the server sends an API request, parses the JSON data received as a response, and extracts and stores the necessary information.

[0575] Step 2:

[0576] The server preprocesses the food inventory data collected. The input is the inventory data saved in the previous step, and data cleansing (e.g., filling in missing values ​​and removing outliers) and formatting (e.g., standardizing the data format) are performed. The output is the preprocessed data. Specifically, the server reads the data from the database, converts it into a format such as a data frame, and performs the necessary cleansing and formatting.

[0577] Step 3:

[0578] The server inputs the preprocessed data into the generation AI. The input data is formatted food inventory data. The generation AI performs analysis to identify ingredients that are close to their expiration date or are likely to be discarded. The output is a list of ingredients that need to be consumed. Specifically, the server inputs the data into the generation AI model and performs filtering by applying conditions such as "expires_in_days < 3."

[0579] Step 4:

[0580] The device senses the user's facial expressions and tone of voice using a camera and microphone. The input is image and audio data acquired from the camera and microphone. The emotion engine analyzes this data and recognizes the user's emotional state. The output is the recognized emotional state (e.g., stress, enjoyment, concentration). Specifically, the device collects image and audio data, sends it to the emotion engine for analysis, and determines the emotional state.

[0581] Step 5:

[0582] The server sends the list of ingredients with a predicted waste potential obtained as a result of the generation AI's analysis to the user's device. The input is the list of ingredients with a predicted waste potential and the emotional state analysis results of the emotion engine. The means of providing this information is to display the ingredient information in an optimal form for the user based on the emotional state. The output is adjusted ingredient information and recipe suggestions. Specifically, the server generates appropriate messages and recipes based on the ingredient list and emotional state and sends them to the device.

[0583] Step 6:

[0584] The device displays the cooking menu and recipes suggested by the generation AI based on the ingredient information provided. The input is the ingredient information and recipe sent from the server. The output is the cooking menu and recipe displayed to the user. In concrete terms, the device displays the received information on the screen, and the user views it.

[0585] Step 7:

[0586] The user prepares and serves a dish based on the suggested recipe. The input is the displayed recipe information. The output is the prepared dish and serving data. In concrete terms, the user prepares the dish according to the recipe and inputs post-serving data (e.g., number of servings and remaining ingredients) into the terminal.

[0587] Step 8:

[0588] The terminal sends the food serving data entered by the user to the server. The input is the data after serving (e.g., number of servings and remaining ingredients). The output is the serving data stored on the server. Specifically, the terminal sends the entered data to the server, and the server stores it in a database.

[0589] Step 9:

[0590] The server aggregates the provided data and tracks the food waste reduction effect. The input is the provided data. The output is a report of the aggregated food waste reduction effect. Specifically, the server aggregates the provided data, calculates the reduction effect for each period (e.g., number of dishes served, amount of food waste reduced), and generates a report.

[0591] Step 10:

[0592] The server periodically notifies the relevant parties of the generated report. The input is the summary report. The output is the report sent to the relevant parties. Specifically, the server sends the generated report to the relevant parties via email or other means, and periodically updates it.

[0593] (Application example 2)

[0594] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0595] Conventional food inventory management and recipe recommendation systems do not take into account the user's emotional state, which can result in low user satisfaction. It is also difficult to efficiently utilize ingredients that are likely to be wasted. Furthermore, there is a lack of a mechanism for clearly tracking and reporting the effectiveness of food waste reduction. Therefore, the challenge is to achieve both appropriate recipe recommendations based on the user's emotional state and food waste reduction.

[0596] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0597] In this invention, the server includes a collection means, a generation AI means, an emotion engine that recognizes the user's emotional state, a means for proposing a dish menu, a means for preparing a dish, a means for generating and executing a delivery order, and a means for tracking the food waste reduction effect and reporting the results. This makes it possible to propose an appropriate dish menu based on the user's emotional state, efficiently use ingredients that are predicted to be wasted, and clearly track and report the food waste reduction effect.

[0598] "Collection means" refers to the means used to collect food inventory information from local commercial and agricultural facilities.

[0599] "Generative AI means" refers to means including artificial intelligence for analyzing collected food inventory information and identifying food ingredient information that is predicted to be discarded.

[0600] The "means for providing to the user" is a means for displaying to the user the ingredient information analyzed by the generating AI means.

[0601] An "emotion engine" is a means for detecting a user's facial expression, tone of voice, etc., and recognizing their emotional state.

[0602] The "means for suggesting a dish menu" is a means for suggesting an appropriate dish menu to the user based on the emotional state of the user recognized by the emotion engine.

[0603] The "means for creating a dish" refers to the means by which the user actually creates a dish based on the provided ingredient information and the proposed dish menu.

[0604] The "means for generating and executing a delivery order" refers to a means for generating a delivery order based on the proposed food menu and ordering food from a partner restaurant.

[0605] "Means for tracking the effects of food waste reduction and reporting the results" refers to a means for tracking the effects of food waste reduction based on the dishes created and reporting the results to relevant parties.

[0606] The present invention is a system that includes a collection means, a generation AI means, a provision means, an emotion engine, a menu suggestion means, a cooking means, a delivery order generation and execution means, and a means for tracking the effect of food waste reduction and reporting the results. Specific embodiments of this system are described below.

[0607] Data collection and analysis

[0608] First, the server uses the collection method to access the databases of local commercial and agricultural facilities and obtain food inventory information via API. Specifically, food inventory information is collected by calling endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" through the network interface. The collected inventory data is stored in the server's database.

[0609] The server then preprocesses the collected food inventory data and converts it into an analyzable format. This preprocessed data is then input into the generation AI to analyze ingredients that are close to their expiration date or likely to be discarded. The generation AI filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0610] Emotion Recognition and Menu Suggestion

[0611] The user's device uses an emotion engine to sense the user's facial expressions and tone of voice using a camera and microphone to recognize their emotional state. The recognized emotional state is sent to the server. The server then suggests appropriate cooking menus based on the user's emotional state recognized by the emotion engine and the results of the analysis described above. For example, if the server recognizes that the user is feeling stressed, it will suggest easy-to-make, relaxing dishes.

[0612] Cooking and delivery orders

[0613] When the user selects a suggested menu item, the server generates a delivery order based on the selected menu item. The delivery order is sent to a local partner restaurant, which delivers the food to the user. After the food is delivered, the user inputs the details of the food and the number of servings into the terminal, and the data is sent to the server.

[0614] Tracking and reporting food waste reduction

[0615] The server receives and aggregates the food serving data sent by users and tracks the effectiveness of food waste reduction. Specifically, it generates a report of the aggregated results in the form of "Number of dishes served this week: 500 plates, Food waste reduction: 50 kilograms" and notifies relevant parties on a regular basis.

[0616] Examples of specific examples and prompts

[0617] If this system were to be implemented in a depopulated area of ​​Hokkaido, the server would collect inventory information daily from commercial and agricultural facilities. The generative AI would then identify ingredients that are nearing their expiration date, and the emotion engine would recognize the emotions of the cafe staff. For example, if the emotion engine recognized that the user was feeling stressed, the server would suggest a menu item suitable for reducing stress, such as a simple panini made with tomatoes and bread. Operating this system would effectively reduce food waste and enable optimal recipe suggestions based on the user's emotional state.

[0618] Example prompt for a generative AI model:

[0619] Ingredients: Tomato, Best before date: 2 days

[0620] User Emotion: Stress

[0621] Menu suggestion: Easy to make, relaxing meals

[0622] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0623] Step 1:

[0624] The server accesses the database of local commercial and agricultural facilities at the specified time and retrieves food inventory information via API, specifically calling endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" using the network interface.

[0625] Input: API endpoint URL

[0626] Output: Food inventory information in JSON format

[0627] Specific behavior: The server sends an API request, receives food inventory information as a response, and stores it in a database.

[0628] Step 2:

[0629] The server preprocesses the collected food inventory data and converts it into an analyzable format, extracts necessary fields from the collected data, and cleans the data.

[0630] Input: Stored food inventory information in JSON format

[0631] Output: Preprocessed food inventory data

[0632] Specific operations: Normalize data, correct outliers, and extract necessary data.

[0633] Step 3:

[0634] The server inputs the preprocessed data into the generation AI means, which analyzes ingredients that are close to their expiration date or are likely to be discarded. The generation AI filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that are likely to be discarded.

[0635] Input: Preprocessed food inventory data

[0636] Output: List of ingredients predicted to be wasted

[0637] What it does: It uses a generative AI model to filter ingredients that meet the criteria and extract the results in list form.

[0638] Step 4:

[0639] The device uses an emotion engine to recognize the user's emotional state by detecting their facial expressions and tone of voice using a camera and microphone, and the emotional state is transmitted from the device to the server.

[0640] Input: User's facial expression data, tone of voice data

[0641] Output: Emotional state data

[0642] What it does: It uses a camera and microphone to collect data, which is then analyzed by an emotion engine to identify emotional states such as stress, enjoyment, and concentration.

[0643] Step 5:

[0644] The server uses a generative AI to suggest appropriate meal plans based on the user's emotional state recognized by the emotion engine and the list of ingredients that are predicted to be wasted. For example, if the user is feeling stressed, the server will suggest simple dishes that will relax them.

[0645] Input: Emotional state data, food waste prediction list

[0646] Output: Suggested food menu

[0647] Specific operation: Using generative AI means, prompts are created to generate the optimal cooking menu based on the emotional state and ingredient information, and the results are generated.

[0648] Step 6:

[0649] The user selects a suggested dish menu on the terminal, and this selection information is sent to the server.

[0650] Input: Menu data for special dishes

[0651] Output: User menu selection information

[0652] Specific behavior: Displays the suggested food menu on the device screen and provides a UI interface to receive the user's selection.

[0653] Step 7:

[0654] The server generates a delivery order based on the food menu selected by the user and sends it to the partner restaurant.

[0655] Input: User menu selection information

[0656] Output: Delivery order information

[0657] Specific operation: Based on the selected menu information, a delivery order is generated and sent to the partner restaurant's ordering system.

[0658] Step 8:

[0659] The food is delivered to the user based on the delivery order. After that, the user inputs the details of the food and the number of servings into the terminal, and the data is sent to the server.

[0660] Input: User input data after food is served

[0661] Output: Food offering information data

[0662] Specific operation: Provides a UI interface for inputting the provided dish information on the device, and sends the collected data to the server.

[0663] Step 9:

[0664] The server receives and aggregates the food provision data sent, tracks the effectiveness of food waste reduction, and generates a report of the aggregated results and notifies relevant parties on a regular basis.

[0665] Input: Food offering information data

[0666] Output: Food waste reduction effect report

[0667] Specific operation: The provided information stored in the database is compiled, a report is generated in the form of "Number of dishes provided this week: 500 plates, amount of food waste reduced: 50 kilograms," and the relevant parties are notified.

[0668] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0669] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0670] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0671] [Third embodiment]

[0672] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0673] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0674] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0675] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0676] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0677] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0678] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0679] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0680] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0681] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0682] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0683] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0684] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, and a means for tracking the effects of food waste reduction and reporting the results. A specific embodiment of this system will be described.

[0685] Data collection

[0686] First, a server collects food inventory information from commercial and agricultural facilities located in depopulated areas. The collection method is to obtain data via API using a network interface. For example, the server obtains food inventory data using APIs such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory."

[0687] Analysis by generative AI

[0688] Next, the server analyzes the collected food inventory data using a generation AI method. Specifically, it identifies ingredients that are close to their expiration date or that are likely to be discarded if not consumed from the collected data. For example, the generation AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0689] Providing information on ingredients

[0690] Based on the analysis results, the server uses a means to provide the user with information about the identified ingredients. The information is provided to the user's device via real-time notifications and a dashboard. For example, a notification such as "List of ingredients to be consumed today: tomatoes, bread, olive oil" is displayed on the device.

[0691] Menu proposal and cooking

[0692] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. This allows the user to create dishes based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish according to that recipe.

[0693] Tracking and reporting food waste reduction

[0694] After a user serves a dish, they input the data of the dish into the device, and the data is sent to the server. The server uses the aggregated data to track the food waste reduction effect and report the results. For example, it generates a report of the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis.

[0695] As a concrete example, let's assume that this system is introduced in a depopulated area of ​​Hokkaido. Food inventory information is collected daily from supermarkets and farmers in the area and sent to a server. The server uses generation AI to create a list of ingredients (e.g., tomatoes, bread) that need to be consumed by tomorrow, and notifies the terminals of local cafe staff in real time. Based on this notification, the cafe staff prepares and serves dishes such as paninis using tomatoes and bread according to the suggested recipe. The provided data is sent from the terminals to the server and compiled, allowing the effectiveness of food waste reduction throughout the area to be regularly evaluated and reported.

[0696] In this way, the system of the present invention can effectively reduce food waste and simultaneously support young people's careers.

[0697] The processing flow will be explained below.

[0698] Step 1:

[0699] The server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. Specifically, the server calls endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" and stores the obtained inventory data in its own database.

[0700] Step 2:

[0701] The server preprocesses the collected inventory data and converts it into an analyzable format, for example, converting all data into a unified format and imputing missing values.

[0702] Step 3:

[0703] The server inputs the preprocessed data into the generation AI, which analyzes ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3."

[0704] Step 4:

[0705] The server creates a list of ingredients that are predicted to be discarded as a result of the AI's analysis and sends the list to the user's (cafe or restaurant staff) device. Specifically, the server notifies the device of the ingredient information in JSON format.

[0706] Step 5:

[0707] The device notifies the user of the list of ingredients received from the server and displays it on the screen. For example, the device displays information such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[0708] Step 6:

[0709] The device uses a generation AI to suggest menus and recipes using ingredients that are predicted to be wasted. Specifically, the device requests recipe suggestions from the generation AI based on the "available_ingredients" data, and displays recipes such as "Panini with tomatoes and bread" to the user.

[0710] Step 7:

[0711] The user creates a dish based on the proposed recipe. The user inputs the specific number and contents of the dish they want to serve into the terminal, and the data is sent to the server.

[0712] Step 8:

[0713] The server receives and aggregates the food serving data sent by users and tracks the food waste reduction effect. The server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, Amount of food waste reduced: 50 kilograms."

[0714] Step 9:

[0715] The server periodically notifies the relevant parties of the reports it generates, and evaluates and reports on the effectiveness of the entire system. For example, the server automatically generates a weekly report and sends it to the relevant parties by email.

[0716] Example 1

[0717] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0718] The problem of food waste is a major issue that causes environmental burdens and economic losses. In particular, in depopulated areas, distribution and sales efficiency is low, making it easy for excess food inventory to occur. As a result, food that is approaching its expiration date is often discarded. Furthermore, there is a lack of a system for sharing food inventory information across the entire region and using that information to make effective cooking suggestions, so concrete measures to reduce waste are needed.

[0719] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0720] In this invention, the server includes a means for collecting food inventory information from commercial facilities and agricultural facilities, a generating AI means for analyzing the food inventory information collected by the collecting means, a means for the generating AI means to identify ingredients that are close to their expiration date or are expected to be discarded, a means for providing the user with the ingredient information obtained by the analysis, a means for suggesting dishes based on the ingredient information provided by the user, a means for the user to prepare the suggested dishes, a means for tracking data on the dishes prepared by the user, and a means for reporting the effects of food waste reduction. This enables a consistent system that covers everything from collecting food inventory information to analyzing it, promoting consumption, and tracking and reporting the effects.

[0721] A "commercial establishment" is a place operated for the sale of food and essential commodities.

[0722] An "agricultural facility" is a facility designed for the cultivation and harvesting of agricultural crops.

[0723] "Food inventory information" refers to data such as the type, quantity, and expiration date of food at commercial and agricultural facilities.

[0724] "Collection methods" refers to the methods and techniques used to collect food inventory information from commercial and agricultural establishments.

[0725] "Generative AI means" is an artificial intelligence technology that analyzes collected food inventory information and extracts important ingredient information based on specific conditions.

[0726] "Analysis" is the process of evaluating collected food inventory information and identifying ingredients that are nearing their expiration date or are expected to be discarded.

[0727] "Means of providing" refers to the methods and techniques for informing users of the analysis results.

[0728] "Means for suggesting dishes" refers to a method for suggesting appropriate recipes and menus based on the ingredient information provided by the user.

[0729] "Means for creating a dish" refers to the methods and techniques that a user uses to create a dish according to a suggested recipe.

[0730] "Tracking means" refers to the method of collecting data on the dishes created by users and analyzing it to confirm the effectiveness of food waste reduction.

[0731] "Reporting means" refers to the methods and technologies used to inform users and other interested parties of collected data and analysis results.

[0732] "Food waste" refers to the amount and type of food that is not consumed and is destined to be discarded.

[0733] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, and a means for tracking the effects of food waste reduction and reporting the results. A specific embodiment of this system will be described.

[0734] Data collection

[0735] First, a server collects food inventory information from commercial and agricultural facilities located in depopulated areas. The collection method is to obtain data via API using a network interface. For example, the server obtains food inventory data using APIs such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." This allows food inventory information from commercial and agricultural facilities to be aggregated on the server.

[0736] Analysis by generative AI

[0737] Next, the server analyzes the collected food inventory data using a generative AI method. Specifically, a generative AI model is used to identify ingredients that are close to their expiration date or that are likely to be discarded if not consumed from the collected data. For example, the generative AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0738] Providing information on ingredients

[0739] Based on the analysis results, the server uses a means to provide the user with information about the identified ingredients. The information is provided to the user's device via real-time notifications and a dashboard. By displaying notifications such as "List of ingredients that need to be consumed today: tomatoes, bread, olive oil" on the device, the user can understand which ingredients should be prioritized for consumption.

[0740] Menu proposal and cooking

[0741] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. This allows the user to create a dish based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish according to that recipe. An example of a specific prompt might be, "Please suggest a simple dish using two tomatoes and one loaf of bread."

[0742] Tracking and reporting food waste reduction

[0743] After a user serves a dish, they input the data of the dish into the device, and the data is sent to the server. The server uses the aggregated data to track the food waste reduction effect and report the results. For example, it generates a report of the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis, thereby visualizing the food waste reduction effect of the entire region.

[0744] As a concrete example, let's assume that this system is introduced in a depopulated area of ​​Hokkaido. Food inventory information is collected daily from supermarkets and farmers in the area and sent to a server. The server uses generation AI to create a list of ingredients (e.g., tomatoes, bread) that need to be consumed by tomorrow, and notifies the terminals of local cafe staff in real time. Based on this notification, the cafe staff prepares and serves dishes such as paninis using tomatoes and bread using suggested recipes. The provided data is sent from the terminals to the server, where it is compiled and the effectiveness of food waste reduction throughout the area is regularly evaluated and reported.

[0745] In this way, the system of the present invention can effectively reduce food waste and simultaneously support young people's careers.

[0746] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0747] Step 1:

[0748] The server collects food inventory information from commercial and agricultural facilities located in depopulated areas.

[0749] Input: Your commercial or agricultural facility's API endpoint (e.g., "local_supermarket_api / get_inventory")

[0750] Specific operation: The server issues an API request via the network interface to obtain food inventory information.

[0751] Output: The acquired food inventory information data (e.g., JSON format) is saved on the server.

[0752] Step 2:

[0753] The food inventory data collected by the server is analyzed using generative AI methods.

[0754] Input: Food inventory data collected in Step 1

[0755] Specific operation: The server inputs food inventory data into the generative AI model and filters the data using the condition "expires_in_days < 3".

[0756] Output: A list of ingredients that are nearing their expiration date or are predicted to be discarded is generated.

[0757] Step 3:

[0758] The server uses a means for providing the user with the identified ingredient information.

[0759] Input: List of ingredients parsed in step 2

[0760] Specific operation: The server creates a notification message in real time based on the analysis results and sends it to the user's device.

[0761] Output: A notification of "List of ingredients to be consumed today" is displayed on the user's device.

[0762] Step 4:

[0763] The device uses generative AI based on the ingredient information provided to suggest appropriate recipes and menus.

[0764] Input: Ingredient information displayed on the user's device

[0765] Specific operation: The device inputs ingredient information into the generation AI to generate appropriate recipes and menus. An example of a prompt is "Please suggest a simple dish using two tomatoes and one loaf of bread."

[0766] Output: The suggested recipes and menus are displayed to the user.

[0767] Step 5:

[0768] The user creates a dish based on the suggested recipe.

[0769] Input: Recipe information displayed on the device

[0770] Specific operation: The user follows the instructions displayed on the device to create a dish using ingredients.

[0771] Output: The created dish (e.g., a panini with tomatoes and bread)

[0772] Step 6:

[0773] After the user has prepared the food, the user inputs data of the prepared food into the terminal, and the data is transmitted to the server.

[0774] Input: Information about the dish served (name of dish, ingredients used, number served, etc.)

[0775] Specific operation: The user enters recipe information into the device, and the device sends the data to the server.

[0776] Output: The data of the dishes served is saved on the server.

[0777] Step 7:

[0778] The server uses the collected data to track the effectiveness of food waste reduction and report the results.

[0779] Input: Food data submitted in step 6

[0780] Specific operation: The server analyzes the number of dishes served and the amount of food waste reduced, generates a report, and notifies relevant parties on a weekly or monthly basis.

[0781] Output: Report on food waste reduction (e.g., "Number of dishes served this week: 100, amount of food waste reduced: 50kg")

[0782] (Application example 1)

[0783] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0784] In recent years, the increase in food delivery services has exacerbated the problem of food waste. In addition, food inventory management at restaurants and supermarkets has become increasingly complex. Managing ingredients with approaching expiration dates is particularly difficult, resulting in large amounts of food being wasted. Furthermore, manually managing inventory and creating menus is time-consuming, labor-intensive, and inefficient. Therefore, there is a need for a system that can efficiently manage food inventory and suggest appropriate menus while reducing food waste.

[0785] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0786] In this invention, the server includes a collection means, a generation AI means, a provision means, a recipe creation means, and an effect tracking means. This allows the server to provide ingredient information to the user's device via real-time notifications and a dashboard, and furthermore, it is possible to suggest appropriate recipes using the generation AI. This encourages the efficient use of ingredients that are close to their expiration date, thereby reducing food waste.

[0787] A "collection instrument" is a device or system for collecting food inventory information from commercial or agricultural establishments.

[0788] "Generative AI methods" are artificial intelligence algorithms used to analyze collected food inventory information and identify ingredients that are nearing their expiration date or are likely to be discarded.

[0789] The "provision means" is a device or system for notifying or presenting the user with the ingredient information identified based on the analysis results.

[0790] The "dish preparation means" is a device or system that proposes an appropriate recipe to the user based on the provided ingredient information and prepares the dish.

[0791] "Effect Tracking Means" refers to a device or system that aggregates cooking data provided by users and tracks and reports the food waste reduction effect.

[0792] A "network interface" is a communication means for sending and receiving data between multiple devices or systems to collect food inventory information.

[0793] "Terminal" refers to an information display and input device used by a user, such as a smartphone, smart glasses, or head-mounted display.

[0794] "Real-time notification" is a communication function for instantly transmitting analyzed ingredient information to the user's terminal.

[0795] A "dashboard" is an interface that displays visually organized data and notifications so that users can intuitively grasp information.

[0796] "Recipe suggestions" are cooking methods suggested by the generative AI based on collected and analyzed ingredient information.

[0797] The present invention is a food waste reduction system that consists of a collection means, a generation AI means, a provision means, a cooking means, and an effect tracking means. Details of each means and a specific embodiment of the system are explained below.

[0798] First, the server collects food inventory information from commercial and agricultural facilities. The collection method is to obtain data via API using a network interface. For example, food inventory data is collected using API endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." The hardware used for this is a server, and the collected data is then analyzed by generative AI.

[0799] Next, the server analyzes the collected food inventory data using a generative AI means. Specifically, it identifies ingredients that are close to their expiration date or that are likely to be discarded from the collected data. This analysis process is carried out using an AI framework such as TensorFlow. For example, the generative AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days. This generative AI means analyzes food inventory information efficiently and accurately.

[0800] Based on the analysis results, the server uses a means to provide the user with the identified food ingredient information. The means of providing this information is to provide the user's device with real-time notifications or a dashboard. For example, a notification such as "List of ingredients that need to be consumed today: tomatoes, bread, olive oil" is displayed on the device. This allows the user to immediately understand which ingredients should be prioritized for consumption.

[0801] Based on the provided ingredient information, the user's device uses generative AI to suggest appropriate recipes and menus. This allows the user to create a dish based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish accordingly. This method of creating dishes makes it possible to provide meals efficiently while reducing food waste.

[0802] After the food is served, the user enters the data of the food served into the device, and the data is sent to the server. The server uses the aggregated data to track and report on the food waste reduction effect. For example, it generates reports on the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis. A real-time database such as Firebase is used to efficiently collect and manage data.

[0803] As a concrete example, let's assume that this system has been introduced to a food delivery service. In this service, food inventory information is collected daily from restaurants and affiliated supermarkets and farmers on a server. The generative AI lists ingredients (e.g., tomatoes, bread) that are approaching their expiration date, and notifies the food delivery service's delivery person's device in real time. Based on this notification, the user prepares a dish using tomatoes and bread using the suggested recipe, and delivers the dish through the delivery service. The provided data is sent from the device to a server and compiled, allowing the food delivery service's overall effectiveness in reducing food waste to be regularly evaluated and analyzed.

[0804] Examples of input prompts for generative AI models include:

[0805] "Based on today's food inventory data, please suggest ingredients that need to be consumed and new recipes using those ingredients. Here is the inventory data: {Inventory data in JSON format}"

[0806] This allows users to consume food efficiently and contribute to reducing food waste.

[0807] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0808] Step 1:

[0809] The server uses a network interface to retrieve data via API to collect food inventory information from commercial and agricultural facilities. Specifically, it collects real-time inventory data through the API endpoints "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory."

[0810] Input: Inventory data from API endpoint.

[0811] Output: Food inventory information stored on the server.

[0812] Step 2:

[0813] The server analyzes the collected food inventory data using generative AI. Specifically, it uses AI frameworks such as TensorFlow to identify food items that are nearing their expiration date or are likely to be discarded. In this process, it filters the data by setting conditions such as "expires_in_days < 3."

[0814] Input: Collected food inventory data.

[0815] Output: A list of ingredients that are close to expiry.

[0816] Step 3:

[0817] The server provides information on ingredients identified based on the analysis results to the user's device through real-time notifications and a dashboard, for example, displaying a notification such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[0818] Input: A list of ingredients that are close to expiry.

[0819] Output: Notification to the user's device.

[0820] Step 4:

[0821] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. For example, the generative AI suggests a recipe for "panini with tomatoes and bread."

[0822] Input: A list of ingredients that are close to expiry.

[0823] Output: The proposed recipe.

[0824] Step 5:

[0825] The user creates a dish based on the generative AI's suggestions. For example, the user makes a panini with tomatoes and bread according to the recipe provided.

[0826] Input: A suggested recipe.

[0827] Output: The dish created by the user.

[0828] Step 6:

[0829] The user inputs the recipe data into the terminal and transmits the data to the server.

[0830] Input: Recipe data entered by the user.

[0831] Output: The recipe data sent to the server.

[0832] Step 7:

[0833] The server uses the collected data to track the effectiveness of food waste reduction and periodically reports the results to relevant parties. Specifically, it generates reports on the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis.

[0834] Input: Recipe data sent to the server.

[0835] Output: Report on food waste reduction effect.

[0836] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0837] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, a means for tracking the effect of food waste reduction and reporting the results, and an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described.

[0838] Data collection

[0839] First, the server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. The collection method uses a network interface to call endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." The server then stores the obtained inventory data in its own database.

[0840] Analysis by generative AI

[0841] The server then preprocesses the collected food inventory data and converts it into an analyzable format. The preprocessed data is then input into the generation AI to analyze ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0842] Emotion recognition by emotion engine

[0843] The device uses a camera and microphone to sense the user's facial expressions and tone of voice, which are then analyzed by an emotion engine. The emotion engine recognizes the user's current emotional state (e.g., stress, enjoyment, concentration, etc.) and transmits the results to the means of providing the information.

[0844] Ingredient information and menu suggestions

[0845] The server sends the list of ingredients with predicted waste obtained as a result of the generation AI's analysis to the user's (cafe or restaurant staff's) device. Specifically, the server notifies the device of the ingredient information in JSON format. Based on the emotion recognition results from the emotion engine, the means of providing the information displays the ingredient information in a format that best suits the user's emotions, and the generation AI means suggests appropriate recipes and menus based on the emotion engine's data.

[0846] Cooking and serving

[0847] The device displays menus and recipes suggested by the AI ​​based on the provided ingredient information. For example, if the user is feeling stressed, the AI ​​will suggest easy-to-make or relaxing dishes. The user then prepares and serves the dish based on the suggested recipe. After serving, the user enters the details of the dish and the number of servings into the device, and the data is sent to the server.

[0848] Tracking and reporting food waste reduction

[0849] The server receives and aggregates the food serving data sent by users and tracks the effectiveness of food waste reduction. Specifically, the server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, amount of food waste reduced: 50 kilograms," and notifies relevant parties on a regular basis.

[0850] Specific examples

[0851] If this system were to be implemented in a depopulated area of ​​Hokkaido, a server would collect inventory information daily from commercial and agricultural facilities. The AI ​​would then identify ingredients that are nearing their expiration date, and the emotion engine would recognize the emotions of the cafe staff. For example, if the emotion engine recognized that the user was feeling stressed, the device would suggest a menu item suitable for reducing stress, such as a simple panini made with tomatoes and bread, as suggested by the AI.

[0852] By operating this system, it is possible to effectively reduce food waste and suggest optimal dishes according to the user's emotional state, while also providing career support for young people.

[0853] The processing flow will be explained below.

[0854] Step 1:

[0855] The server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. Specifically, the server calls endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" and stores the obtained inventory data in its own database.

[0856] Step 2:

[0857] The server preprocesses the collected inventory data and converts it into an analyzable format, for example, converting all data into a unified format and imputing missing values.

[0858] Step 3:

[0859] The server inputs the preprocessed data into the generation AI, which analyzes ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3."

[0860] Step 4:

[0861] The server creates a list of ingredients that are predicted to be discarded as a result of the AI's analysis and sends the list to the user's (cafe or restaurant staff) device. Specifically, the server notifies the device of the ingredient information in JSON format.

[0862] Step 5:

[0863] The device notifies the user of the list of ingredients received from the server and displays it on the screen. For example, the device displays information such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[0864] Step 6:

[0865] The device uses a camera and microphone to detect the user's facial expressions and tone of voice, and analyzes the data with an emotion engine. The emotion engine recognizes the user's emotional state (e.g., stress, enjoyment, concentration, etc.) and sends the results to the means of providing the information.

[0866] Step 7:

[0867] The device uses generative AI to suggest appropriate menus and recipes based on the emotion recognition results from the emotion engine. For example, if the user is feeling stressed, the device will display a recipe such as "a simple panini with tomatoes and bread."

[0868] Step 8:

[0869] The user creates a dish based on the proposed recipe. The user inputs the specific number and contents of the dish they want to serve into the terminal, and the data is sent to the server.

[0870] Step 9:

[0871] The server aggregates the food serving data sent by users and tracks the food waste reduction effect. The server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, amount of food waste reduced: 50 kilograms," and notifies relevant parties periodically.

[0872] Example 2

[0873] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0874] Food waste is a major issue in modern society, especially in commercial and agricultural facilities, which place a significant burden on the environment. Furthermore, in the food service industry, staff emotional states often affect the quality of service, but there is a lack of methods to efficiently manage this and provide optimal menu options. Given this situation, a system is needed that can efficiently reduce food waste and provide recipe suggestions that take staff emotional states into account.

[0875] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a collection means, a generation AI means for analyzing food inventory information collected by the collection means, a means for providing the user with ingredient information predicted to be wasted obtained by the analysis, a means for creating a dish based on the ingredient information provided by the user, a means for tracking the effect of food waste reduction and reporting the results, and an emotion engine for recognizing the user's emotions. This enables effective use of food inventory, reduction of food waste, and optimal recipe suggestions taking into account the emotional state of staff.

[0876] "Collection means" refers to a means for obtaining food inventory information from commercial and agricultural facilities, and includes a network interface.

[0877] The "generative AI means" is a means that implements an algorithm that analyzes food inventory information obtained by the collection means and identifies ingredients that are close to their expiration date or that are likely to be discarded.

[0878] The "means for providing" refers to a means for informing the user of the discard-predicted ingredient information obtained through the analysis.

[0879] The "means for creating a dish" is a means for suggesting recipes and menus for a dish based on the ingredient information provided by the user, and for actually creating the dish.

[0880] The "means for tracking the effect of food waste reduction and reporting the results" is a means for aggregating data on cooking provided by users, measuring the effect of food waste reduction, and reporting the results.

[0881] An "emotion engine" is a means of sensing and analyzing a user's facial expressions and tone of voice to recognize their current emotional state.

[0882] The present invention is a system focused on reducing food waste and managing employee emotions. The system includes a collection means, a generation AI means, a serving means, a cooking means, a means for tracking the food waste reduction effect and reporting the results, and an emotion engine that recognizes the user's emotions.

[0883] Data collection

[0884] The server plays the main role. At a specified time each day, the server uses a network interface to access the databases of local commercial and agricultural facilities to obtain food inventory information. Specifically, it calls API endpoints (e.g., "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory"). The obtained inventory data is stored in the server's database.

[0885] Analysis by generative AI

[0886] The server then preprocesses the collected food inventory data and converts it into an analyzable format. Preprocessing includes data cleansing and formatting. The server then inputs the preprocessed data into the generation AI. Based on the collected data, the generation AI identifies ingredients that are close to their expiration date or are likely to be discarded. Conditions such as "expires_in_days < 3" are used for this analysis.

[0887] Emotion recognition by emotion engine

[0888] The device senses the user's facial expressions and tone of voice using a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state (e.g., stress, joy, concentration, etc.). The emotion engine's analysis results are sent to the device providing the service.

[0889] Ingredient information and menu suggestions

[0890] The server sends the list of ingredients predicted to be wasted, obtained as a result of the analysis by the generation AI, to the user's device. This information is sent in JSON format. The means of providing this information is to display the ingredient information in a way that best suits the user's emotions, based on the results of the emotion engine. Furthermore, the generation AI suggests appropriate recipes and menus based on the data from the emotion engine.

[0891] Specific examples

[0892] For example, consider the case where this system is introduced in a depopulated area of ​​Hokkaido. The server collects inventory information from commercial and agricultural facilities every day, and the generation AI identifies ingredients that are close to their expiration date. If the emotion engine recognizes the emotions of the cafe staff and determines that the user is feeling stressed, the device will suggest a menu item that will help reduce stress, such as a simple panini with tomatoes and bread, based on the generation AI's suggestions.

[0893] This system effectively reduces food waste and provides the optimal meal according to the user's emotional state.

[0894] Example prompt statement

[0895] "Collect this week's inventory data."

[0896] "Generate a list of ingredients with a shelf life of less than 3 days"

[0897] "Analyze the user's emotions and suggest the best menu."

[0898] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0899] Step 1:

[0900] The server accesses the database of local commercial and agricultural facilities at a specified time each day. It uses an API endpoint (e.g., "local_supermarket_api / get_inventory" or "local_farm_api / get_inventory") as input to retrieve food inventory information. As output, the retrieved inventory data is stored in the server's database. Specifically, the server sends an API request, parses the JSON data received as a response, and extracts and stores the necessary information.

[0901] Step 2:

[0902] The server preprocesses the food inventory data collected. The input is the inventory data saved in the previous step, and data cleansing (e.g., filling in missing values ​​and removing outliers) and formatting (e.g., standardizing the data format) are performed. The output is the preprocessed data. Specifically, the server reads the data from the database, converts it into a format such as a data frame, and performs the necessary cleansing and formatting.

[0903] Step 3:

[0904] The server inputs the preprocessed data into the generation AI. The input data is formatted food inventory data. The generation AI performs analysis to identify ingredients that are close to their expiration date or are likely to be discarded. The output is a list of ingredients that need to be consumed. Specifically, the server inputs the data into the generation AI model and performs filtering by applying conditions such as "expires_in_days < 3."

[0905] Step 4:

[0906] The device senses the user's facial expressions and tone of voice using a camera and microphone. The input is image and audio data acquired from the camera and microphone. The emotion engine analyzes this data and recognizes the user's emotional state. The output is the recognized emotional state (e.g., stress, enjoyment, concentration). Specifically, the device collects image and audio data, sends it to the emotion engine for analysis, and determines the emotional state.

[0907] Step 5:

[0908] The server sends the list of ingredients with a predicted waste potential obtained as a result of the generation AI's analysis to the user's device. The input is the list of ingredients with a predicted waste potential and the emotional state analysis results of the emotion engine. The means of providing this information is to display the ingredient information in an optimal form for the user based on the emotional state. The output is adjusted ingredient information and recipe suggestions. Specifically, the server generates appropriate messages and recipes based on the ingredient list and emotional state and sends them to the device.

[0909] Step 6:

[0910] The device displays the cooking menu and recipes suggested by the generation AI based on the ingredient information provided. The input is the ingredient information and recipe sent from the server. The output is the cooking menu and recipe displayed to the user. In concrete terms, the device displays the received information on the screen, and the user views it.

[0911] Step 7:

[0912] The user prepares and serves a dish based on the suggested recipe. The input is the displayed recipe information. The output is the prepared dish and serving data. In concrete terms, the user prepares the dish according to the recipe and inputs post-serving data (e.g., number of servings and remaining ingredients) into the terminal.

[0913] Step 8:

[0914] The terminal sends the food serving data entered by the user to the server. The input is the data after serving (e.g., number of servings and remaining ingredients). The output is the serving data stored on the server. Specifically, the terminal sends the entered data to the server, and the server stores it in a database.

[0915] Step 9:

[0916] The server aggregates the provided data and tracks the food waste reduction effect. The input is the provided data. The output is a report of the aggregated food waste reduction effect. Specifically, the server aggregates the provided data, calculates the reduction effect for each period (e.g., number of dishes served, amount of food waste reduced), and generates a report.

[0917] Step 10:

[0918] The server periodically notifies the relevant parties of the generated report. The input is the summary report. The output is the report sent to the relevant parties. Specifically, the server sends the generated report to the relevant parties via email or other means, and periodically updates it.

[0919] (Application example 2)

[0920] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0921] Conventional food inventory management and recipe recommendation systems do not take into account the user's emotional state, which can result in low user satisfaction. It is also difficult to efficiently utilize ingredients that are likely to be wasted. Furthermore, there is a lack of a mechanism for clearly tracking and reporting the effectiveness of food waste reduction. Therefore, the challenge is to achieve both appropriate recipe recommendations based on the user's emotional state and food waste reduction.

[0922] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0923] In this invention, the server includes a collection means, a generation AI means, an emotion engine that recognizes the user's emotional state, a means for proposing a dish menu, a means for preparing a dish, a means for generating and executing a delivery order, and a means for tracking the food waste reduction effect and reporting the results. This makes it possible to propose an appropriate dish menu based on the user's emotional state, efficiently use ingredients that are predicted to be wasted, and clearly track and report the food waste reduction effect.

[0924] "Collection means" refers to the means used to collect food inventory information from local commercial and agricultural facilities.

[0925] "Generative AI means" refers to means including artificial intelligence for analyzing collected food inventory information and identifying food ingredient information that is predicted to be discarded.

[0926] The "means for providing to the user" is a means for displaying to the user the ingredient information analyzed by the generating AI means.

[0927] An "emotion engine" is a means for detecting a user's facial expression, tone of voice, etc., and recognizing their emotional state.

[0928] The "means for suggesting a dish menu" is a means for suggesting an appropriate dish menu to the user based on the emotional state of the user recognized by the emotion engine.

[0929] The "means for creating a dish" refers to the means by which the user actually creates a dish based on the provided ingredient information and the proposed dish menu.

[0930] The "means for generating and executing a delivery order" refers to a means for generating a delivery order based on the proposed food menu and ordering food from a partner restaurant.

[0931] "Means for tracking the effects of food waste reduction and reporting the results" refers to a means for tracking the effects of food waste reduction based on the dishes created and reporting the results to relevant parties.

[0932] The present invention is a system that includes a collection means, a generation AI means, a provision means, an emotion engine, a menu suggestion means, a cooking means, a delivery order generation and execution means, and a means for tracking the effect of food waste reduction and reporting the results. Specific embodiments of this system are described below.

[0933] Data collection and analysis

[0934] First, the server uses the collection method to access the databases of local commercial and agricultural facilities and obtain food inventory information via API. Specifically, food inventory information is collected by calling endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" through the network interface. The collected inventory data is stored in the server's database.

[0935] The server then preprocesses the collected food inventory data and converts it into an analyzable format. This preprocessed data is then input into the generation AI to analyze ingredients that are close to their expiration date or likely to be discarded. The generation AI filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[0936] Emotion Recognition and Menu Suggestion

[0937] The user's device uses an emotion engine to sense the user's facial expressions and tone of voice using a camera and microphone to recognize their emotional state. The recognized emotional state is sent to the server. The server then suggests appropriate cooking menus based on the user's emotional state recognized by the emotion engine and the results of the analysis described above. For example, if the server recognizes that the user is feeling stressed, it will suggest easy-to-make, relaxing dishes.

[0938] Cooking and delivery orders

[0939] When the user selects a suggested menu item, the server generates a delivery order based on the selected menu item. The delivery order is sent to a local partner restaurant, which delivers the food to the user. After the food is delivered, the user inputs the details of the food and the number of servings into the terminal, and the data is sent to the server.

[0940] Tracking and reporting food waste reduction

[0941] The server receives and aggregates the food serving data sent by users and tracks the effectiveness of food waste reduction. Specifically, it generates a report of the aggregated results in the form of "Number of dishes served this week: 500 plates, Food waste reduction: 50 kilograms" and notifies relevant parties on a regular basis.

[0942] Examples of specific examples and prompts

[0943] If this system were to be implemented in a depopulated area of ​​Hokkaido, the server would collect inventory information daily from commercial and agricultural facilities. The generative AI would then identify ingredients that are nearing their expiration date, and the emotion engine would recognize the emotions of the cafe staff. For example, if the emotion engine recognized that the user was feeling stressed, the server would suggest a menu item suitable for reducing stress, such as a simple panini made with tomatoes and bread. Operating this system would effectively reduce food waste and enable optimal recipe suggestions based on the user's emotional state.

[0944] Example prompt for a generative AI model:

[0945] Ingredients: Tomato, Best before date: 2 days

[0946] User Emotion: Stress

[0947] Menu suggestion: Easy to make, relaxing meals

[0948] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0949] Step 1:

[0950] The server accesses the database of local commercial and agricultural facilities at the specified time and retrieves food inventory information via API, specifically calling endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" using the network interface.

[0951] Input: API endpoint URL

[0952] Output: Food inventory information in JSON format

[0953] Specific behavior: The server sends an API request, receives food inventory information as a response, and stores it in a database.

[0954] Step 2:

[0955] The server preprocesses the collected food inventory data and converts it into an analyzable format, extracts necessary fields from the collected data, and cleans the data.

[0956] Input: Stored food inventory information in JSON format

[0957] Output: Preprocessed food inventory data

[0958] Specific operations: Normalize data, correct outliers, and extract necessary data.

[0959] Step 3:

[0960] The server inputs the preprocessed data into the generation AI means, which analyzes ingredients that are close to their expiration date or are likely to be discarded. The generation AI filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that are likely to be discarded.

[0961] Input: Preprocessed food inventory data

[0962] Output: List of ingredients predicted to be wasted

[0963] What it does: It uses a generative AI model to filter ingredients that meet the criteria and extract the results in list form.

[0964] Step 4:

[0965] The device uses an emotion engine to recognize the user's emotional state by detecting their facial expressions and tone of voice using a camera and microphone, and the emotional state is transmitted from the device to the server.

[0966] Input: User's facial expression data, tone of voice data

[0967] Output: Emotional state data

[0968] What it does: It uses a camera and microphone to collect data, which is then analyzed by an emotion engine to identify emotional states such as stress, enjoyment, and concentration.

[0969] Step 5:

[0970] The server uses a generative AI to suggest appropriate meal plans based on the user's emotional state recognized by the emotion engine and the list of ingredients that are predicted to be wasted. For example, if the user is feeling stressed, the server will suggest simple dishes that will relax them.

[0971] Input: Emotional state data, food waste prediction list

[0972] Output: Suggested food menu

[0973] Specific operation: Using generative AI means, prompts are created to generate the optimal cooking menu based on the emotional state and ingredient information, and the results are generated.

[0974] Step 6:

[0975] The user selects a suggested dish menu on the terminal, and this selection information is sent to the server.

[0976] Input: Menu data for special dishes

[0977] Output: User menu selection information

[0978] Specific behavior: Displays the suggested food menu on the device screen and provides a UI interface to receive the user's selection.

[0979] Step 7:

[0980] The server generates a delivery order based on the food menu selected by the user and sends it to the partner restaurant.

[0981] Input: User menu selection information

[0982] Output: Delivery order information

[0983] Specific operation: Based on the selected menu information, a delivery order is generated and sent to the partner restaurant's ordering system.

[0984] Step 8:

[0985] The food is delivered to the user based on the delivery order. After that, the user inputs the details of the food and the number of servings into the terminal, and the data is sent to the server.

[0986] Input: User input data after food is served

[0987] Output: Food offering information data

[0988] Specific operation: Provides a UI interface for inputting the provided dish information on the device, and sends the collected data to the server.

[0989] Step 9:

[0990] The server receives and aggregates the food provision data sent, tracks the effectiveness of food waste reduction, and generates a report of the aggregated results and notifies relevant parties on a regular basis.

[0991] Input: Food offering information data

[0992] Output: Food waste reduction effect report

[0993] Specific operation: The provided information stored in the database is compiled, a report is generated in the form of "Number of dishes provided this week: 500 plates, amount of food waste reduced: 50 kilograms," and the relevant parties are notified.

[0994] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0995] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0996] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0997] [Fourth embodiment]

[0998] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0999] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1000] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1001] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1002] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1003] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1004] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1005] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1006] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1007] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1008] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1009] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1010] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1011] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, and a means for tracking the effects of food waste reduction and reporting the results. A specific embodiment of this system will be described.

[1012] Data collection

[1013] First, a server collects food inventory information from commercial and agricultural facilities located in depopulated areas. The collection method is to obtain data via API using a network interface. For example, the server obtains food inventory data using APIs such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory."

[1014] Analysis by generative AI

[1015] Next, the server analyzes the collected food inventory data using a generation AI method. Specifically, it identifies ingredients that are close to their expiration date or that are likely to be discarded if not consumed from the collected data. For example, the generation AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[1016] Providing information on ingredients

[1017] Based on the analysis results, the server uses a means to provide the user with information about the identified ingredients. The information is provided to the user's device via real-time notifications and a dashboard. For example, a notification such as "List of ingredients to be consumed today: tomatoes, bread, olive oil" is displayed on the device.

[1018] Menu proposal and cooking

[1019] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. This allows the user to create dishes based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish according to that recipe.

[1020] Tracking and reporting food waste reduction

[1021] After a user serves a dish, they input the data of the dish into the device, and the data is sent to the server. The server uses the aggregated data to track the food waste reduction effect and report the results. For example, it generates a report of the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis.

[1022] As a concrete example, let's assume that this system is introduced in a depopulated area of ​​Hokkaido. Food inventory information is collected daily from supermarkets and farmers in the area and sent to a server. The server uses generation AI to create a list of ingredients (e.g., tomatoes, bread) that need to be consumed by tomorrow, and notifies the terminals of local cafe staff in real time. Based on this notification, the cafe staff prepares and serves dishes such as paninis using tomatoes and bread according to the suggested recipe. The provided data is sent from the terminals to the server and compiled, allowing the effectiveness of food waste reduction throughout the area to be regularly evaluated and reported.

[1023] In this way, the system of the present invention can effectively reduce food waste and simultaneously support young people's careers.

[1024] The processing flow will be explained below.

[1025] Step 1:

[1026] The server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. Specifically, the server calls endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" and stores the obtained inventory data in its own database.

[1027] Step 2:

[1028] The server preprocesses the collected inventory data and converts it into an analyzable format, for example, converting all data into a unified format and imputing missing values.

[1029] Step 3:

[1030] The server inputs the preprocessed data into the generation AI, which analyzes ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3."

[1031] Step 4:

[1032] The server creates a list of ingredients that are predicted to be discarded as a result of the AI's analysis and sends the list to the user's (cafe or restaurant staff) device. Specifically, the server notifies the device of the ingredient information in JSON format.

[1033] Step 5:

[1034] The device notifies the user of the list of ingredients received from the server and displays it on the screen. For example, the device displays information such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[1035] Step 6:

[1036] The device uses a generation AI to suggest menus and recipes using ingredients that are predicted to be wasted. Specifically, the device requests recipe suggestions from the generation AI based on the "available_ingredients" data, and displays recipes such as "Panini with tomatoes and bread" to the user.

[1037] Step 7:

[1038] The user creates a dish based on the proposed recipe. The user inputs the specific number and contents of the dish they want to serve into the terminal, and the data is sent to the server.

[1039] Step 8:

[1040] The server receives and aggregates the food serving data sent by users and tracks the food waste reduction effect. The server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, Amount of food waste reduced: 50 kilograms."

[1041] Step 9:

[1042] The server periodically notifies the relevant parties of the reports it generates, and evaluates and reports on the effectiveness of the entire system. For example, the server automatically generates a weekly report and sends it to the relevant parties by email.

[1043] Example 1

[1044] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1045] The problem of food waste is a major issue that causes environmental burdens and economic losses. In particular, in depopulated areas, distribution and sales efficiency is low, making it easy for excess food inventory to occur. As a result, food that is approaching its expiration date is often discarded. Furthermore, there is a lack of a system for sharing food inventory information across the entire region and using that information to make effective cooking suggestions, so concrete measures to reduce waste are needed.

[1046] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1047] In this invention, the server includes a means for collecting food inventory information from commercial facilities and agricultural facilities, a generating AI means for analyzing the food inventory information collected by the collecting means, a means for the generating AI means to identify ingredients that are close to their expiration date or are expected to be discarded, a means for providing the user with the ingredient information obtained by the analysis, a means for suggesting dishes based on the ingredient information provided by the user, a means for the user to prepare the suggested dishes, a means for tracking data on the dishes prepared by the user, and a means for reporting the effects of food waste reduction. This enables a consistent system that covers everything from collecting food inventory information to analyzing it, promoting consumption, and tracking and reporting the effects.

[1048] A "commercial establishment" is a place operated for the sale of food and essential commodities.

[1049] An "agricultural facility" is a facility designed for the cultivation and harvesting of agricultural crops.

[1050] "Food inventory information" refers to data such as the type, quantity, and expiration date of food at commercial and agricultural facilities.

[1051] "Collection methods" refers to the methods and techniques used to collect food inventory information from commercial and agricultural establishments.

[1052] "Generative AI means" is an artificial intelligence technology that analyzes collected food inventory information and extracts important ingredient information based on specific conditions.

[1053] "Analysis" is the process of evaluating collected food inventory information and identifying ingredients that are nearing their expiration date or are expected to be discarded.

[1054] "Means of providing" refers to the methods and techniques for informing users of the analysis results.

[1055] "Means for suggesting dishes" refers to a method for suggesting appropriate recipes and menus based on the ingredient information provided by the user.

[1056] "Means for creating a dish" refers to the methods and techniques that a user uses to create a dish according to a suggested recipe.

[1057] "Tracking means" refers to the method of collecting data on the dishes created by users and analyzing it to confirm the effectiveness of food waste reduction.

[1058] "Reporting means" refers to the methods and technologies used to inform users and other interested parties of collected data and analysis results.

[1059] "Food waste" refers to the amount and type of food that is not consumed and is destined to be discarded.

[1060] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, and a means for tracking the effects of food waste reduction and reporting the results. A specific embodiment of this system will be described.

[1061] Data collection

[1062] First, a server collects food inventory information from commercial and agricultural facilities located in depopulated areas. The collection method is to obtain data via API using a network interface. For example, the server obtains food inventory data using APIs such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." This allows food inventory information from commercial and agricultural facilities to be aggregated on the server.

[1063] Analysis by generative AI

[1064] Next, the server analyzes the collected food inventory data using a generative AI method. Specifically, a generative AI model is used to identify ingredients that are close to their expiration date or that are likely to be discarded if not consumed from the collected data. For example, the generative AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[1065] Providing information on ingredients

[1066] Based on the analysis results, the server uses a means to provide the user with information about the identified ingredients. The information is provided to the user's device via real-time notifications and a dashboard. By displaying notifications such as "List of ingredients that need to be consumed today: tomatoes, bread, olive oil" on the device, the user can understand which ingredients should be prioritized for consumption.

[1067] Menu proposal and cooking

[1068] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. This allows the user to create a dish based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish according to that recipe. An example of a specific prompt might be, "Please suggest a simple dish using two tomatoes and one loaf of bread."

[1069] Tracking and reporting food waste reduction

[1070] After a user serves a dish, they input the data of the dish into the device, and the data is sent to the server. The server uses the aggregated data to track the food waste reduction effect and report the results. For example, it generates a report of the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis, thereby visualizing the food waste reduction effect of the entire region.

[1071] As a concrete example, let's assume that this system is introduced in a depopulated area of ​​Hokkaido. Food inventory information is collected daily from supermarkets and farmers in the area and sent to a server. The server uses generation AI to create a list of ingredients (e.g., tomatoes, bread) that need to be consumed by tomorrow, and notifies the terminals of local cafe staff in real time. Based on this notification, the cafe staff prepares and serves dishes such as paninis using tomatoes and bread using suggested recipes. The provided data is sent from the terminals to the server, where it is compiled and the effectiveness of food waste reduction throughout the area is regularly evaluated and reported.

[1072] In this way, the system of the present invention can effectively reduce food waste and simultaneously support young people's careers.

[1073] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1074] Step 1:

[1075] The server collects food inventory information from commercial and agricultural facilities located in depopulated areas.

[1076] Input: Your commercial or agricultural facility's API endpoint (e.g., "local_supermarket_api / get_inventory")

[1077] Specific operation: The server issues an API request via the network interface to obtain food inventory information.

[1078] Output: The acquired food inventory information data (e.g., JSON format) is saved on the server.

[1079] Step 2:

[1080] The food inventory data collected by the server is analyzed using generative AI methods.

[1081] Input: Food inventory data collected in Step 1

[1082] Specific operation: The server inputs food inventory data into the generative AI model and filters the data using the condition "expires_in_days < 3".

[1083] Output: A list of ingredients that are nearing their expiration date or are predicted to be discarded is generated.

[1084] Step 3:

[1085] The server uses a means for providing the user with the identified ingredient information.

[1086] Input: List of ingredients parsed in step 2

[1087] Specific operation: The server creates a notification message in real time based on the analysis results and sends it to the user's device.

[1088] Output: A notification of "List of ingredients to be consumed today" is displayed on the user's device.

[1089] Step 4:

[1090] The device uses generative AI based on the ingredient information provided to suggest appropriate recipes and menus.

[1091] Input: Ingredient information displayed on the user's device

[1092] Specific operation: The device inputs ingredient information into the generation AI to generate appropriate recipes and menus. An example of a prompt is "Please suggest a simple dish using two tomatoes and one loaf of bread."

[1093] Output: The suggested recipes and menus are displayed to the user.

[1094] Step 5:

[1095] The user creates a dish based on the suggested recipe.

[1096] Input: Recipe information displayed on the device

[1097] Specific operation: The user follows the instructions displayed on the device to create a dish using ingredients.

[1098] Output: The created dish (e.g., a panini with tomatoes and bread)

[1099] Step 6:

[1100] After the user has prepared the food, the user inputs data of the prepared food into the terminal, and the data is transmitted to the server.

[1101] Input: Information about the dish served (name of dish, ingredients used, number served, etc.)

[1102] Specific operation: The user enters recipe information into the device, and the device sends the data to the server.

[1103] Output: The data of the dishes served is saved on the server.

[1104] Step 7:

[1105] The server uses the collected data to track the effectiveness of food waste reduction and report the results.

[1106] Input: Food data submitted in step 6

[1107] Specific operation: The server analyzes the number of dishes served and the amount of food waste reduced, generates a report, and notifies relevant parties on a weekly or monthly basis.

[1108] Output: Report on food waste reduction (e.g., "Number of dishes served this week: 100, amount of food waste reduced: 50kg")

[1109] (Application example 1)

[1110] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1111] In recent years, the increase in food delivery services has exacerbated the problem of food waste. In addition, food inventory management at restaurants and supermarkets has become increasingly complex. Managing ingredients with approaching expiration dates is particularly difficult, resulting in large amounts of food being wasted. Furthermore, manually managing inventory and creating menus is time-consuming, labor-intensive, and inefficient. Therefore, there is a need for a system that can efficiently manage food inventory and suggest appropriate menus while reducing food waste.

[1112] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1113] In this invention, the server includes a collection means, a generation AI means, a provision means, a recipe creation means, and an effect tracking means. This allows the server to provide ingredient information to the user's device via real-time notifications and a dashboard, and furthermore, it is possible to suggest appropriate recipes using the generation AI. This encourages the efficient use of ingredients that are close to their expiration date, thereby reducing food waste.

[1114] A "collection instrument" is a device or system for collecting food inventory information from commercial or agricultural establishments.

[1115] "Generative AI methods" are artificial intelligence algorithms used to analyze collected food inventory information and identify ingredients that are nearing their expiration date or are likely to be discarded.

[1116] The "provision means" is a device or system for notifying or presenting the user with the ingredient information identified based on the analysis results.

[1117] The "dish preparation means" is a device or system that proposes an appropriate recipe to the user based on the provided ingredient information and prepares the dish.

[1118] "Effect Tracking Means" refers to a device or system that aggregates cooking data provided by users and tracks and reports the food waste reduction effect.

[1119] A "network interface" is a communication means for sending and receiving data between multiple devices or systems to collect food inventory information.

[1120] "Terminal" refers to an information display and input device used by a user, such as a smartphone, smart glasses, or head-mounted display.

[1121] "Real-time notification" is a communication function for instantly transmitting analyzed ingredient information to the user's terminal.

[1122] A "dashboard" is an interface that displays visually organized data and notifications so that users can intuitively grasp information.

[1123] "Recipe suggestions" are cooking methods suggested by the generative AI based on collected and analyzed ingredient information.

[1124] The present invention is a food waste reduction system that consists of a collection means, a generation AI means, a provision means, a cooking means, and an effect tracking means. Details of each means and a specific embodiment of the system are explained below.

[1125] First, the server collects food inventory information from commercial and agricultural facilities. The collection method is to obtain data via API using a network interface. For example, food inventory data is collected using API endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." The hardware used for this is a server, and the collected data is then analyzed by generative AI.

[1126] Next, the server analyzes the collected food inventory data using a generative AI means. Specifically, it identifies ingredients that are close to their expiration date or that are likely to be discarded from the collected data. This analysis process is carried out using an AI framework such as TensorFlow. For example, the generative AI filters the data using the condition "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days. This generative AI means analyzes food inventory information efficiently and accurately.

[1127] Based on the analysis results, the server uses a means to provide the user with the identified food ingredient information. The means of providing this information is to provide the user's device with real-time notifications or a dashboard. For example, a notification such as "List of ingredients that need to be consumed today: tomatoes, bread, olive oil" is displayed on the device. This allows the user to immediately understand which ingredients should be prioritized for consumption.

[1128] Based on the provided ingredient information, the user's device uses generative AI to suggest appropriate recipes and menus. This allows the user to create a dish based on the suggested menu. For example, the device suggests a recipe for "panini with tomatoes and bread," and the user creates the dish accordingly. This method of creating dishes makes it possible to provide meals efficiently while reducing food waste.

[1129] After the food is served, the user enters the data of the food served into the device, and the data is sent to the server. The server uses the aggregated data to track and report on the food waste reduction effect. For example, it generates reports on the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis. A real-time database such as Firebase is used to efficiently collect and manage data.

[1130] As a concrete example, let's assume that this system has been introduced to a food delivery service. In this service, food inventory information is collected daily from restaurants and affiliated supermarkets and farmers on a server. The generative AI lists ingredients (e.g., tomatoes, bread) that are approaching their expiration date, and notifies the food delivery service's delivery person's device in real time. Based on this notification, the user prepares a dish using tomatoes and bread using the suggested recipe, and delivers the dish through the delivery service. The provided data is sent from the device to a server and compiled, allowing the food delivery service's overall effectiveness in reducing food waste to be regularly evaluated and analyzed.

[1131] Examples of input prompts for generative AI models include:

[1132] "Based on today's food inventory data, please suggest ingredients that need to be consumed and new recipes using those ingredients. Here is the inventory data: {Inventory data in JSON format}"

[1133] This allows users to consume food efficiently and contribute to reducing food waste.

[1134] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1135] Step 1:

[1136] The server uses a network interface to retrieve data via API to collect food inventory information from commercial and agricultural facilities. Specifically, it collects real-time inventory data through the API endpoints "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory."

[1137] Input: Inventory data from API endpoint.

[1138] Output: Food inventory information stored on the server.

[1139] Step 2:

[1140] The server analyzes the collected food inventory data using generative AI. Specifically, it uses AI frameworks such as TensorFlow to identify food items that are nearing their expiration date or are likely to be discarded. In this process, it filters the data by setting conditions such as "expires_in_days < 3."

[1141] Input: Collected food inventory data.

[1142] Output: A list of ingredients that are close to expiry.

[1143] Step 3:

[1144] The server provides information on ingredients identified based on the analysis results to the user's device through real-time notifications and a dashboard, for example, displaying a notification such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[1145] Input: A list of ingredients that are close to expiry.

[1146] Output: Notification to the user's device.

[1147] Step 4:

[1148] The device uses generative AI to suggest appropriate recipes and menus based on the provided ingredient information. For example, the generative AI suggests a recipe for "panini with tomatoes and bread."

[1149] Input: A list of ingredients that are close to expiry.

[1150] Output: The proposed recipe.

[1151] Step 5:

[1152] The user creates a dish based on the generative AI's suggestions. For example, the user makes a panini with tomatoes and bread according to the recipe provided.

[1153] Input: A suggested recipe.

[1154] Output: The dish created by the user.

[1155] Step 6:

[1156] The user inputs the recipe data into the terminal and transmits the data to the server.

[1157] Input: Recipe data entered by the user.

[1158] Output: The recipe data sent to the server.

[1159] Step 7:

[1160] The server uses the collected data to track the effectiveness of food waste reduction and periodically reports the results to relevant parties. Specifically, it generates reports on the number of dishes served and the amount of food waste reduced, and notifies relevant parties on a weekly or monthly basis.

[1161] Input: Recipe data sent to the server.

[1162] Output: Report on food waste reduction effect.

[1163] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1164] The present invention is a system that includes a collection means, a generation AI means, a provision means, a means for creating dishes, a means for tracking the effect of food waste reduction and reporting the results, and an emotion engine that recognizes the user's emotions. A specific embodiment of this system will be described.

[1165] Data collection

[1166] First, the server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. The collection method uses a network interface to call endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory." The server then stores the obtained inventory data in its own database.

[1167] Analysis by generative AI

[1168] The server then preprocesses the collected food inventory data and converts it into an analyzable format. The preprocessed data is then input into the generation AI to analyze ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[1169] Emotion recognition by emotion engine

[1170] The device uses a camera and microphone to sense the user's facial expressions and tone of voice, which are then analyzed by an emotion engine. The emotion engine recognizes the user's current emotional state (e.g., stress, enjoyment, concentration, etc.) and transmits the results to the means of providing the information.

[1171] Ingredient information and menu suggestions

[1172] The server sends the list of ingredients with predicted waste obtained as a result of the generation AI's analysis to the user's (cafe or restaurant staff's) device. Specifically, the server notifies the device of the ingredient information in JSON format. Based on the emotion recognition results from the emotion engine, the means of providing the information displays the ingredient information in a format that best suits the user's emotions, and the generation AI means suggests appropriate recipes and menus based on the emotion engine's data.

[1173] Cooking and serving

[1174] The device displays menus and recipes suggested by the AI ​​based on the provided ingredient information. For example, if the user is feeling stressed, the AI ​​will suggest easy-to-make or relaxing dishes. The user then prepares and serves the dish based on the suggested recipe. After serving, the user enters the details of the dish and the number of servings into the device, and the data is sent to the server.

[1175] Tracking and reporting food waste reduction

[1176] The server receives and aggregates the food serving data sent by users and tracks the effectiveness of food waste reduction. Specifically, the server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, amount of food waste reduced: 50 kilograms," and notifies relevant parties on a regular basis.

[1177] Specific examples

[1178] If this system were to be implemented in a depopulated area of ​​Hokkaido, a server would collect inventory information daily from commercial and agricultural facilities. The AI ​​would then identify ingredients that are nearing their expiration date, and the emotion engine would recognize the emotions of the cafe staff. For example, if the emotion engine recognized that the user was feeling stressed, the device would suggest a menu item suitable for reducing stress, such as a simple panini made with tomatoes and bread, as suggested by the AI.

[1179] By operating this system, it is possible to effectively reduce food waste and suggest optimal dishes according to the user's emotional state, while also providing career support for young people.

[1180] The processing flow will be explained below.

[1181] Step 1:

[1182] The server accesses the database of local commercial and agricultural facilities at a specified time each day to obtain food inventory information via API. Specifically, the server calls endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" and stores the obtained inventory data in its own database.

[1183] Step 2:

[1184] The server preprocesses the collected inventory data and converts it into an analyzable format, for example, converting all data into a unified format and imputing missing values.

[1185] Step 3:

[1186] The server inputs the preprocessed data into the generation AI, which analyzes ingredients that are close to their expiration date or likely to be discarded. The generation AI then filters ingredients based on conditions such as "expires_in_days < 3."

[1187] Step 4:

[1188] The server creates a list of ingredients that are predicted to be discarded as a result of the AI's analysis and sends the list to the user's (cafe or restaurant staff) device. Specifically, the server notifies the device of the ingredient information in JSON format.

[1189] Step 5:

[1190] The device notifies the user of the list of ingredients received from the server and displays it on the screen. For example, the device displays information such as "List of ingredients to be consumed today: tomatoes, bread, olive oil."

[1191] Step 6:

[1192] The device uses a camera and microphone to detect the user's facial expressions and tone of voice, and analyzes the data with an emotion engine. The emotion engine recognizes the user's emotional state (e.g., stress, enjoyment, concentration, etc.) and sends the results to the means of providing the information.

[1193] Step 7:

[1194] The device uses generative AI to suggest appropriate menus and recipes based on the emotion recognition results from the emotion engine. For example, if the user is feeling stressed, the device will display a recipe such as "a simple panini with tomatoes and bread."

[1195] Step 8:

[1196] The user creates a dish based on the proposed recipe. The user inputs the specific number and contents of the dish they want to serve into the terminal, and the data is sent to the server.

[1197] Step 9:

[1198] The server aggregates the food serving data sent by users and tracks the food waste reduction effect. The server generates a report of the aggregated results in the form of, for example, "Number of dishes served this week: 500 plates, amount of food waste reduced: 50 kilograms," and notifies relevant parties periodically.

[1199] Example 2

[1200] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1201] Food waste is a major issue in modern society, especially in commercial and agricultural facilities, which place a significant burden on the environment. Furthermore, in the food service industry, staff emotional states often affect the quality of service, but there is a lack of methods to efficiently manage this and provide optimal menu options. Given this situation, a system is needed that can efficiently reduce food waste and provide recipe suggestions that take staff emotional states into account.

[1202] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a collection means, a generation AI means for analyzing food inventory information collected by the collection means, a means for providing the user with ingredient information predicted to be wasted obtained by the analysis, a means for creating a dish based on the ingredient information provided by the user, a means for tracking the effect of food waste reduction and reporting the results, and an emotion engine for recognizing the user's emotions. This enables effective use of food inventory, reduction of food waste, and optimal recipe suggestions taking into account the emotional state of staff.

[1203] "Collection means" refers to a means for obtaining food inventory information from commercial and agricultural facilities, and includes a network interface.

[1204] The "generative AI means" is a means that implements an algorithm that analyzes food inventory information obtained by the collection means and identifies ingredients that are close to their expiration date or that are likely to be discarded.

[1205] The "means for providing" refers to a means for informing the user of the discard-predicted ingredient information obtained through the analysis.

[1206] The "means for creating a dish" is a means for suggesting recipes and menus for a dish based on the ingredient information provided by the user, and for actually creating the dish.

[1207] The "means for tracking the effect of food waste reduction and reporting the results" is a means for aggregating data on cooking provided by users, measuring the effect of food waste reduction, and reporting the results.

[1208] An "emotion engine" is a means of sensing and analyzing a user's facial expressions and tone of voice to recognize their current emotional state.

[1209] The present invention is a system focused on reducing food waste and managing employee emotions. The system includes a collection means, a generation AI means, a serving means, a cooking means, a means for tracking the food waste reduction effect and reporting the results, and an emotion engine that recognizes the user's emotions.

[1210] Data collection

[1211] The server plays the main role. At a specified time each day, the server uses a network interface to access the databases of local commercial and agricultural facilities to obtain food inventory information. Specifically, it calls API endpoints (e.g., "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory"). The obtained inventory data is stored in the server's database.

[1212] Analysis by generative AI

[1213] The server then preprocesses the collected food inventory data and converts it into an analyzable format. Preprocessing includes data cleansing and formatting. The server then inputs the preprocessed data into the generation AI. Based on the collected data, the generation AI identifies ingredients that are close to their expiration date or are likely to be discarded. Conditions such as "expires_in_days < 3" are used for this analysis.

[1214] Emotion recognition by emotion engine

[1215] The device senses the user's facial expressions and tone of voice using a camera and microphone. The emotion engine analyzes this data and recognizes the user's current emotional state (e.g., stress, joy, concentration, etc.). The emotion engine's analysis results are sent to the device providing the service.

[1216] Ingredient information and menu suggestions

[1217] The server sends the list of ingredients predicted to be wasted, obtained as a result of the analysis by the generation AI, to the user's device. This information is sent in JSON format. The means of providing this information is to display the ingredient information in a way that best suits the user's emotions, based on the results of the emotion engine. Furthermore, the generation AI suggests appropriate recipes and menus based on the data from the emotion engine.

[1218] Specific examples

[1219] For example, consider the case where this system is introduced in a depopulated area of ​​Hokkaido. The server collects inventory information from commercial and agricultural facilities every day, and the generation AI identifies ingredients that are close to their expiration date. If the emotion engine recognizes the emotions of the cafe staff and determines that the user is feeling stressed, the device will suggest a menu item that will help reduce stress, such as a simple panini with tomatoes and bread, based on the generation AI's suggestions.

[1220] This system effectively reduces food waste and provides the optimal meal according to the user's emotional state.

[1221] Example prompt statement

[1222] "Collect this week's inventory data."

[1223] "Generate a list of ingredients with a shelf life of less than 3 days"

[1224] "Analyze the user's emotions and suggest the best menu."

[1225] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1226] Step 1:

[1227] The server accesses the database of local commercial and agricultural facilities at a specified time each day. It uses an API endpoint (e.g., "local_supermarket_api / get_inventory" or "local_farm_api / get_inventory") as input to retrieve food inventory information. As output, the retrieved inventory data is stored in the server's database. Specifically, the server sends an API request, parses the JSON data received as a response, and extracts and stores the necessary information.

[1228] Step 2:

[1229] The server preprocesses the food inventory data collected. The input is the inventory data saved in the previous step, and data cleansing (e.g., filling in missing values ​​and removing outliers) and formatting (e.g., standardizing the data format) are performed. The output is the preprocessed data. Specifically, the server reads the data from the database, converts it into a format such as a data frame, and performs the necessary cleansing and formatting.

[1230] Step 3:

[1231] The server inputs the preprocessed data into the generation AI. The input data is formatted food inventory data. The generation AI performs analysis to identify ingredients that are close to their expiration date or are likely to be discarded. The output is a list of ingredients that need to be consumed. Specifically, the server inputs the data into the generation AI model and performs filtering by applying conditions such as "expires_in_days < 3."

[1232] Step 4:

[1233] The device senses the user's facial expressions and tone of voice using a camera and microphone. The input is image and audio data acquired from the camera and microphone. The emotion engine analyzes this data and recognizes the user's emotional state. The output is the recognized emotional state (e.g., stress, enjoyment, concentration). Specifically, the device collects image and audio data, sends it to the emotion engine for analysis, and determines the emotional state.

[1234] Step 5:

[1235] The server sends the list of ingredients with a predicted waste potential obtained as a result of the generation AI's analysis to the user's device. The input is the list of ingredients with a predicted waste potential and the emotional state analysis results of the emotion engine. The means of providing this information is to display the ingredient information in an optimal form for the user based on the emotional state. The output is adjusted ingredient information and recipe suggestions. Specifically, the server generates appropriate messages and recipes based on the ingredient list and emotional state and sends them to the device.

[1236] Step 6:

[1237] The device displays the cooking menu and recipes suggested by the generation AI based on the ingredient information provided. The input is the ingredient information and recipe sent from the server. The output is the cooking menu and recipe displayed to the user. In concrete terms, the device displays the received information on the screen, and the user views it.

[1238] Step 7:

[1239] The user prepares and serves a dish based on the suggested recipe. The input is the displayed recipe information. The output is the prepared dish and serving data. In concrete terms, the user prepares the dish according to the recipe and inputs post-serving data (e.g., number of servings and remaining ingredients) into the terminal.

[1240] Step 8:

[1241] The terminal sends the food serving data entered by the user to the server. The input is the data after serving (e.g., number of servings and remaining ingredients). The output is the serving data stored on the server. Specifically, the terminal sends the entered data to the server, and the server stores it in a database.

[1242] Step 9:

[1243] The server aggregates the provided data and tracks the food waste reduction effect. The input is the provided data. The output is a report of the aggregated food waste reduction effect. Specifically, the server aggregates the provided data, calculates the reduction effect for each period (e.g., number of dishes served, amount of food waste reduced), and generates a report.

[1244] Step 10:

[1245] The server periodically notifies the relevant parties of the generated report. The input is the summary report. The output is the report sent to the relevant parties. Specifically, the server sends the generated report to the relevant parties via email or other means, and periodically updates it.

[1246] (Application example 2)

[1247] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1248] Conventional food inventory management and recipe recommendation systems do not take into account the user's emotional state, which can result in low user satisfaction. It is also difficult to efficiently utilize ingredients that are likely to be wasted. Furthermore, there is a lack of a mechanism for clearly tracking and reporting the effectiveness of food waste reduction. Therefore, the challenge is to achieve both appropriate recipe recommendations based on the user's emotional state and food waste reduction.

[1249] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1250] In this invention, the server includes a collection means, a generation AI means, an emotion engine that recognizes the user's emotional state, a means for proposing a dish menu, a means for preparing a dish, a means for generating and executing a delivery order, and a means for tracking the food waste reduction effect and reporting the results. This makes it possible to propose an appropriate dish menu based on the user's emotional state, efficiently use ingredients that are predicted to be wasted, and clearly track and report the food waste reduction effect.

[1251] "Collection means" refers to the means used to collect food inventory information from local commercial and agricultural facilities.

[1252] "Generative AI means" refers to means including artificial intelligence for analyzing collected food inventory information and identifying food ingredient information that is predicted to be discarded.

[1253] The "means for providing to the user" is a means for displaying to the user the ingredient information analyzed by the generating AI means.

[1254] An "emotion engine" is a means for detecting a user's facial expression, tone of voice, etc., and recognizing their emotional state.

[1255] The "means for suggesting a dish menu" is a means for suggesting an appropriate dish menu to the user based on the emotional state of the user recognized by the emotion engine.

[1256] The "means for creating a dish" refers to the means by which the user actually creates a dish based on the provided ingredient information and the proposed dish menu.

[1257] The "means for generating and executing a delivery order" refers to a means for generating a delivery order based on the proposed food menu and ordering food from a partner restaurant.

[1258] "Means for tracking the effects of food waste reduction and reporting the results" refers to a means for tracking the effects of food waste reduction based on the dishes created and reporting the results to relevant parties.

[1259] The present invention is a system that includes a collection means, a generation AI means, a provision means, an emotion engine, a menu suggestion means, a cooking means, a delivery order generation and execution means, and a means for tracking the effect of food waste reduction and reporting the results. Specific embodiments of this system are described below.

[1260] Data collection and analysis

[1261] First, the server uses the collection method to access the databases of local commercial and agricultural facilities and obtain food inventory information via API. Specifically, food inventory information is collected by calling endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" through the network interface. The collected inventory data is stored in the server's database.

[1262] The server then preprocesses the collected food inventory data and converts it into an analyzable format. This preprocessed data is then input into the generation AI to analyze ingredients that are close to their expiration date or likely to be discarded. The generation AI filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that need to be consumed within the next few days.

[1263] Emotion Recognition and Menu Suggestion

[1264] The user's device uses an emotion engine to sense the user's facial expressions and tone of voice using a camera and microphone to recognize their emotional state. The recognized emotional state is sent to the server. The server then suggests appropriate cooking menus based on the user's emotional state recognized by the emotion engine and the results of the analysis described above. For example, if the server recognizes that the user is feeling stressed, it will suggest easy-to-make, relaxing dishes.

[1265] Cooking and delivery orders

[1266] When the user selects a suggested menu item, the server generates a delivery order based on the selected menu item. The delivery order is sent to a local partner restaurant, which delivers the food to the user. After the food is delivered, the user inputs the details of the food and the number of servings into the terminal, and the data is sent to the server.

[1267] Tracking and reporting food waste reduction

[1268] The server receives and aggregates the food serving data sent by users and tracks the effectiveness of food waste reduction. Specifically, it generates a report of the aggregated results in the form of "Number of dishes served this week: 500 plates, Food waste reduction: 50 kilograms" and notifies relevant parties on a regular basis.

[1269] Examples of specific examples and prompts

[1270] If this system were to be implemented in a depopulated area of ​​Hokkaido, the server would collect inventory information daily from commercial and agricultural facilities. The generative AI would then identify ingredients that are nearing their expiration date, and the emotion engine would recognize the emotions of the cafe staff. For example, if the emotion engine recognized that the user was feeling stressed, the server would suggest a menu item suitable for reducing stress, such as a simple panini made with tomatoes and bread. Operating this system would effectively reduce food waste and enable optimal recipe suggestions based on the user's emotional state.

[1271] Example prompt for a generative AI model:

[1272] Ingredients: Tomato, Best before date: 2 days

[1273] User Emotion: Stress

[1274] Menu suggestion: Easy to make, relaxing meals

[1275] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1276] Step 1:

[1277] The server accesses the database of local commercial and agricultural facilities at the specified time and retrieves food inventory information via API, specifically calling endpoints such as "local_supermarket_api / get_inventory" and "local_farm_api / get_inventory" using the network interface.

[1278] Input: API endpoint URL

[1279] Output: Food inventory information in JSON format

[1280] Specific behavior: The server sends an API request, receives food inventory information as a response, and stores it in a database.

[1281] Step 2:

[1282] The server preprocesses the collected food inventory data and converts it into an analyzable format, extracts necessary fields from the collected data, and cleans the data.

[1283] Input: Stored food inventory information in JSON format

[1284] Output: Preprocessed food inventory data

[1285] Specific operations: Normalize data, correct outliers, and extract necessary data.

[1286] Step 3:

[1287] The server inputs the preprocessed data into the generation AI means, which analyzes ingredients that are close to their expiration date or are likely to be discarded. The generation AI filters ingredients based on conditions such as "expires_in_days < 3" and creates a list of ingredients that are likely to be discarded.

[1288] Input: Preprocessed food inventory data

[1289] Output: List of ingredients predicted to be wasted

[1290] What it does: It uses a generative AI model to filter ingredients that meet the criteria and extract the results in list form.

[1291] Step 4:

[1292] The device uses an emotion engine to recognize the user's emotional state by detecting their facial expressions and tone of voice using a camera and microphone, and the emotional state is transmitted from the device to the server.

[1293] Input: User's facial expression data, tone of voice data

[1294] Output: Emotional state data

[1295] What it does: It uses a camera and microphone to collect data, which is then analyzed by an emotion engine to identify emotional states such as stress, enjoyment, and concentration.

[1296] Step 5:

[1297] The server uses a generative AI to suggest appropriate meal plans based on the user's emotional state recognized by the emotion engine and the list of ingredients that are predicted to be wasted. For example, if the user is feeling stressed, the server will suggest simple dishes that will relax them.

[1298] Input: Emotional state data, food waste prediction list

[1299] Output: Suggested food menu

[1300] Specific operation: Using generative AI means, prompts are created to generate the optimal cooking menu based on the emotional state and ingredient information, and the results are generated.

[1301] Step 6:

[1302] The user selects a suggested dish menu on the terminal, and this selection information is sent to the server.

[1303] Input: Menu data for special dishes

[1304] Output: User menu selection information

[1305] Specific behavior: Displays the suggested food menu on the device screen and provides a UI interface to receive the user's selection.

[1306] Step 7:

[1307] The server generates a delivery order based on the food menu selected by the user and sends it to the partner restaurant.

[1308] Input: User menu selection information

[1309] Output: Delivery order information

[1310] Specific operation: Based on the selected menu information, a delivery order is generated and sent to the partner restaurant's ordering system.

[1311] Step 8:

[1312] The food is delivered to the user based on the delivery order. After that, the user inputs the details of the food and the number of servings into the terminal, and the data is sent to the server.

[1313] Input: User input data after food is served

[1314] Output: Food offering information data

[1315] Specific operation: Provides a UI interface for inputting the provided dish information on the device, and sends the collected data to the server.

[1316] Step 9:

[1317] The server receives and aggregates the food provision data sent, tracks the effectiveness of food waste reduction, and generates a report of the aggregated results and notifies relevant parties on a regular basis.

[1318] Input: Food offering information data

[1319] Output: Food waste reduction effect report

[1320] Specific operation: The provided information stored in the database is compiled, a report is generated in the form of "Number of dishes provided this week: 500 plates, amount of food waste reduced: 50 kilograms," and the relevant parties are notified.

[1321] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1322] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1323] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1324] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1325] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1326] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1327] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1328] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1329] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1330] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1331] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1332] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1333] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1334] 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.

[1335] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1336] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1337] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1338] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1339] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1340] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1341] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1342] The following is further disclosed regarding the above embodiment.

[1343] (Claim 1)

[1344] Collection means;

[1345] a generating AI means for analyzing the food inventory information collected by the collecting means;

[1346] a means for providing a user with information about ingredients that are predicted to be discarded, obtained by the analysis;

[1347] A means for creating a dish based on the ingredient information provided by the user;

[1348] A means to track and report on food waste reduction efforts;

[1349] A system including:

[1350] (Claim 2)

[1351] 10. The system of claim 1, wherein the collecting means includes a network interface for collecting food inventory information.

[1352] (Claim 3)

[1353] The system of claim 1, wherein the generating AI means implements an algorithm for analyzing collected food inventory information and identifying food ingredient information that is predicted to be discarded.

[1354] "Example 1"

[1355] (Claim 1)

[1356] a means of collecting food inventory information from commercial and agricultural establishments;

[1357] a generating AI means for analyzing the food inventory information collected by the collecting means;

[1358] A means for the generating AI means to identify information on ingredients that are close to their expiration date or that are expected to be discarded;

[1359] a means for providing a user with the ingredient information obtained by the analysis;

[1360] a means for suggesting a dish based on the ingredient information provided by the user;

[1361] a means for the user to prepare the suggested dish;

[1362] means for tracking data of recipes created by said users;

[1363] A means to report on food waste reduction effects,

[1364] A system including:

[1365] (Claim 2)

[1366] 10. The system of claim 1, wherein the collecting means includes a network interface for collecting food inventory information.

[1367] (Claim 3)

[1368] The system of claim 1, wherein the generating AI means implements an algorithm for analyzing collected food inventory information and identifying food ingredient information that is predicted to be discarded.

[1369] "Application Example 1"

[1370] (Claim 1)

[1371] Collection means;

[1372] a generating AI means for analyzing the food inventory information collected by the collecting means;

[1373] a means for providing a user with information about ingredients that are predicted to be discarded, obtained by the analysis;

[1374] A means for creating a dish based on the ingredient information provided by the user;

[1375] A means to track and report on food waste reduction efforts;

[1376] the providing means providing information to a user's terminal through real-time notifications or a dashboard;

[1377] The cooking creation means is a means for suggesting an appropriate recipe using a generation AI installed on the user's device;

[1378] A system including:

[1379] (Claim 2)

[1380] 10. The system of claim 1, wherein the collecting means includes a network interface for collecting food inventory information.

[1381] (Claim 3)

[1382] The system of claim 1, wherein the generating AI means implements an algorithm for analyzing collected food inventory information and identifying food ingredient information that is predicted to be discarded.

[1383] "Example 2: Combining Emotion Engines"

[1384] (Claim 1)

[1385] Collection means;

[1386] a generating AI means for analyzing the food inventory information collected by the collecting means;

[1387] a means for providing a user with information about ingredients that are predicted to be discarded, obtained by the analysis;

[1388] A means for creating a dish based on the ingredient information provided by the user;

[1389] A means to track and report on food waste reduction efforts;

[1390] A system including an emotion engine that recognizes user emotions.

[1391] (Claim 2)

[1392] 10. The system of claim 1, wherein the collecting means includes a network interface for collecting food inventory information.

[1393] (Claim 3)

[1394] The system of claim 1, wherein the generating AI means implements an algorithm for analyzing collected food inventory information and identifying food ingredient information that is predicted to be discarded.

[1395] "Application example 2 when combining emotion engines"

[1396] (Claim 1)

[1397] Collection means;

[1398] a generating AI means for analyzing the food inventory information collected by the collecting means;

[1399] a means for providing a user with information about ingredients that are predicted to be discarded, obtained by the analysis;

[1400] an emotion engine that recognizes the user's emotional state;

[1401] means for suggesting an appropriate food menu based on the emotional state of the user recognized by the emotion engine;

[1402] A means for creating a dish based on the ingredient information and the proposed dish menu provided by the user;

[1403] means for generating and executing a delivery order for the created food;

[1404] A means to track and report on food waste reduction efforts;

[1405] A system including:

[1406] (Claim 2)

[1407] 10. The system of claim 1, wherein the collecting means includes a network interface for collecting food inventory information.

[1408] (Claim 3)

[1409] The system of claim 1, wherein the generative AI means implements an algorithm for analyzing collected food inventory information and identifying ingredient information that is predicted to be discarded, and includes a generative AI model and prompt sentences for suggesting a cooking menu based on the user's emotional state. [Explanation of symbols]

[1410] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. Collection means; a generating AI means for analyzing the food inventory information collected by the collecting means; a means for providing a user with information about ingredients that are predicted to be discarded, obtained by the analysis; A means for creating a dish based on the ingredient information provided by the user; A means to track and report on food waste reduction efforts; A system including:

2. 10. The system of claim 1, wherein the collecting means includes a network interface for collecting food inventory information.

3. The system according to claim 1, wherein the generating AI means implements an algorithm for analyzing collected food inventory information and identifying information on ingredients that are predicted to be discarded.

Images