system

Abstract

The system according to the embodiment aims to efficiently manage ingredients in the refrigerator, create shopping lists, and suggest recipes. [Solution] A system according to an embodiment includes a collection unit, a creation unit, a suggestion unit, an analysis unit, and a presentation unit. The collection unit checks the status of ingredients. The creation unit creates a shopping list based on the information collected by the collection unit. The suggestion unit suggests recipes based on information about ingredients in the refrigerator, based on the shopping list created by the creation unit. The analysis unit analyzes the status of the refrigerator based on the recipe suggested by the suggestion unit. The presentation unit presents the information analyzed by the analysis unit.

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] With conventional technology, managing ingredients in the refrigerator, creating shopping lists, and suggesting recipes were all done manually, making it difficult to do this efficiently.

[0005] The system according to the embodiment aims to efficiently manage ingredients in the refrigerator, create shopping lists, and suggest recipes. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a creation unit, a suggestion unit, an analysis unit, and a presentation unit. The collection unit checks the condition of ingredients. The creation unit creates a shopping list based on the information collected by the collection unit. The suggestion unit suggests recipes based on information about ingredients in the refrigerator, based on the shopping list created by the creation unit. The analysis unit analyzes the condition of the refrigerator based on the recipe suggested by the suggestion unit. The presentation unit presents the information analyzed by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently manage ingredients in the refrigerator, create shopping lists, and suggest recipes. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] 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), and Bluetooth (registered trademark).

[0015] 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."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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).

[0019] 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A refrigerator management system according to an embodiment of the present invention utilizes generative AI to add new functions to existing refrigerators. This system checks the status of ingredients, creates shopping lists, suggests recipes, analyzes the refrigerator status, and presents information. For example, in a refrigerator management system, AI tracks ingredients and beverages in the refrigerator and checks their status. This allows users to easily understand the expiration dates and inventory levels of ingredients. AI also creates shopping lists based on ingredients with approaching expiration dates or low inventory. For example, if milk is running low in the refrigerator, the AI ​​automatically adds it to the shopping list. Furthermore, barcodes and RFID tags are attached to ingredients, and the AI ​​automatically tracks detailed information about the ingredients. For example, by scanning the barcode, the AI ​​records the type of ingredient and purchase date. The AI ​​also suggests recipes tailored to the contents of the refrigerator. For example, the AI ​​suggests appropriate recipes based on the ingredients in the refrigerator. Furthermore, to support existing refrigerators, an external smart unit with built-in cameras and sensors is provided. This unit analyzes the refrigerator status and presents information on a screen and speaker. For example, the unit issues an alert if the refrigerator door is open. Finally, a function is provided that allows users to view the history of previously created menus and recipes. This allows users to easily check past menus and recipes, and the refrigerator management system can automatically manage the status of ingredients and support efficient shopping and cooking.

[0029] A refrigerator management system according to an embodiment includes a collection unit, a creation unit, a suggestion unit, an analysis unit, and a presentation unit. The collection unit checks the status of ingredients. For example, the collection unit can check the expiration dates and stock levels of ingredients in the refrigerator. For example, the collection unit scans barcodes of ingredients in the refrigerator to check expiration dates. The collection unit can also measure the stock levels of ingredients in the refrigerator using a sensor. For example, the collection unit measures the weight of ingredients in the refrigerator to check stock levels. The creation unit creates a shopping list based on the information collected by the collection unit. For example, the creation unit adds ingredients that are close to their expiration dates or that are low in stock to the list. For example, the creation unit automatically adds milk to the shopping list when the refrigerator is low in milk. The suggestion unit suggests recipes based on information about ingredients in the refrigerator based on the shopping list created by the creation unit. For example, the suggestion unit suggests appropriate recipes based on ingredients in the refrigerator. For example, the suggestion unit suggests recipes using vegetables and meat in the refrigerator. The analysis unit analyzes the status of the refrigerator based on the recipes suggested by the suggestion unit. For example, the analysis unit measures the temperature and humidity inside the refrigerator and analyzes the storage conditions of ingredients. For example, the analysis unit issues a warning if the temperature inside the refrigerator is not appropriate. The presentation unit presents the information analyzed by the analysis unit. For example, the presentation unit presents the information using a screen and a speaker. For example, the presentation unit issues a warning if the refrigerator door is open. In this way, the refrigerator management system according to the embodiment can automatically manage the status of ingredients and support efficient shopping and cooking.

[0030] The refrigerator management system includes a reading unit that reads barcodes or RFID tags. The reading unit reads barcodes or RFID tags. For example, the reading unit scans barcodes attached to ingredients in the refrigerator. The reading unit reads barcodes of ingredients using, for example, a barcode reader. The reading unit can also read RFID tags. For example, the reading unit reads RFID tags of ingredients using an RFID reader. By reading the barcodes or RFID tags, detailed information about ingredients can be tracked. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input data from barcodes or RFID tags into a generation AI and cause the generation AI to track detailed information about ingredients.

[0031] The refrigerator management system includes a tracking unit that tracks the read information. The tracking unit tracks the read information. For example, the tracking unit records and tracks information about ingredients read from barcodes or RFID tags. The tracking unit tracks information such as the type of ingredient, purchase date, and expiration date. The tracking unit can also track the inventory of ingredients. For example, the tracking unit measures the weight of ingredients in the refrigerator and tracks the inventory. In this way, by tracking the read information, the status of ingredients can be managed in detail. Some or all of the above-mentioned processing in the tracking unit may be performed using, or without, AI, for example. For example, the tracking unit can input data read from barcodes or RFID tags into a generation AI and cause the generation AI to track the status of ingredients.

[0032] The refrigerator management system includes a storage unit that stores a history of past menus and recipes. The storage unit stores the history of past menus and recipes. For example, the storage unit records and stores information about menus and recipes created in the past by a user. The storage unit stores information such as the date the menu was created, the ingredients used, and the cooking procedure. The storage unit can also store the history of recipes. For example, the storage unit stores information about recipes used in the past by a user. By storing the history of past menus and recipes, the user can refer to the past information. Some or all of the above-described processing in the storage unit may be performed using, or without, AI, for example. For example, the storage unit may input data about past menus and recipes into a generation AI and have the generation AI store the data.

[0033] The refrigerator management system includes a reference unit that references the stored history. The reference unit references the stored history. For example, the reference unit displays a history of past menus and recipes stored by the storage unit. The reference unit displays, for example, information on menus created by the user in the past and recipes used by the user. The reference unit can also search the stored history. For example, the reference unit searches for past menus and recipes based on specific ingredients or cooking methods. This allows the user to easily check past information by referring to the stored history. Some or all of the above-described processing in the reference unit may be performed using, or without, AI, for example. For example, the reference unit can input the stored history data into a generation AI and have the generation AI refer to the data.

[0034] The collection unit can check the expiration date or inventory amount. The collection unit checks the expiration date or inventory amount. For example, the collection unit checks the expiration date of ingredients in a refrigerator. The collection unit checks the expiration date, for example, by scanning a barcode. The collection unit can also check the inventory amount of ingredients in a refrigerator. For example, the collection unit measures the weight of ingredients using a sensor and checks the inventory amount. This makes it easier to manage ingredients by checking the expiration date or inventory amount. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input data on the expiration date or inventory amount into the generation AI and have the generation AI check the data.

[0035] The creation unit can create a shopping list based on ingredients that are close to their expiration date or that are low in stock. The creation unit creates a shopping list based on ingredients that are close to their expiration date or that are low in stock. For example, the creation unit checks the expiration dates of ingredients in the refrigerator and adds ingredients that are close to their expiration date to the list. For example, the creation unit automatically adds milk to the shopping list if its expiration date is approaching. The creation unit can also check the inventory of ingredients in the refrigerator and add ingredients that are low in stock to the list. For example, the creation unit automatically adds eggs to the shopping list if their inventory is low in the refrigerator. This enables efficient shopping by creating a shopping list based on ingredients that are close to their expiration date or that are low in stock. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input data on expiration dates and inventory amounts into the generation AI and cause the generation AI to create a shopping list.

[0036] The suggestion unit can suggest recipes based on information about ingredients in the refrigerator. The suggestion unit suggests recipes based on information about ingredients in the refrigerator. For example, the suggestion unit checks the ingredients in the refrigerator and suggests appropriate recipes based on that information. The suggestion unit suggests, for example, recipes using vegetables and meat in the refrigerator. The suggestion unit can also suggest new recipes based on combinations of ingredients in the refrigerator. For example, the suggestion unit suggests original recipes by combining ingredients in the refrigerator. This makes it possible to make effective use of ingredients by suggesting recipes based on information about ingredients in the refrigerator. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input information about ingredients in the refrigerator into a generation AI and have the generation AI suggest recipes.

[0037] The analysis unit can analyze the state of the refrigerator. The analysis unit analyzes the state of the refrigerator. For example, the analysis unit measures the temperature and humidity inside the refrigerator and analyzes the storage state of ingredients. For example, if the temperature inside the refrigerator is not appropriate, the analysis unit issues a warning. The analysis unit can also analyze the arrangement of ingredients inside the refrigerator. For example, if the arrangement of ingredients inside the refrigerator is not appropriate, the analysis unit suggests rearranging them. In this way, analyzing the state of the refrigerator enables efficient operation of the refrigerator. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the temperature and humidity inside the refrigerator into the generation AI and have the generation AI analyze the state.

[0038] The presentation unit can present information using a screen and a speaker. The presentation unit presents information using a screen and a speaker. For example, the presentation unit issues a warning if the refrigerator door is open. The presentation unit, for example, displays a warning message on the screen and issues an audio warning through the speaker. The presentation unit can also display the status of ingredients in the refrigerator. For example, the presentation unit displays the expiration date and stock amount of ingredients on the screen. By presenting information on the screen and the speaker, the user can confirm the information visually and audibly. Some or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input status data of ingredients in the refrigerator to the generation AI and cause the generation AI to present the information.

[0039] The collection unit can analyze the user's past consumption patterns and select the optimal checking method when checking the status of ingredients. The collection unit analyzes the user's past consumption patterns and selects the optimal checking method when checking the status of ingredients. For example, the collection unit prioritizes checking and notifying ingredients that the user frequently consumes. For example, the collection unit focuses on checking ingredients that the user has wasted in the past and makes suggestions to reduce waste. The collection unit can also adjust the timing of checking the status of ingredients based on the user's consumption patterns. For example, the collection unit prioritizes checking and notifying ingredients that the user consumes during a specific time period. This allows waste to be reduced by selecting the optimal checking method based on the user's past consumption patterns. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit can input the user's consumption pattern data into a generation AI and have the generation AI select the optimal checking method.

[0040] The collection unit can apply different confirmation algorithms to each type of ingredient when checking the status of the ingredients. The collection unit applies different confirmation algorithms to each type of ingredient when checking the status of the ingredients. For example, the collection unit applies a confirmation algorithm that emphasizes freshness to fresh foods such as vegetables and fruits. The collection unit, for example, measures the color and hardness of vegetables to check their freshness. The collection unit can also apply a confirmation algorithm that emphasizes expiration dates to preserved foods such as canned and bottled foods. For example, the collection unit scans barcodes to check the expiration dates of canned foods. The collection unit can also apply a confirmation algorithm that emphasizes maintaining the frozen state to frozen foods. For example, the collection unit measures the temperature of frozen foods to check their frozen state. In this way, applying different confirmation algorithms to each type of ingredient allows for more accurate confirmation of the status of the ingredients. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit can input different confirmation algorithms for each type of ingredient into the generation AI and have the generation AI perform the confirmation.

[0041] When checking the status of ingredients, the collection unit can prioritize checking highly relevant ingredients taking into account the user's geographical location information. When checking the status of ingredients, the collection unit prioritizes checking highly relevant ingredients taking into account the user's geographical location information. For example, when the user is at home, the collection unit checks all ingredients in the refrigerator. The collection unit checks, for example, the expiration dates and stock amounts of ingredients in the refrigerator. Furthermore, when the user is out, the collection unit can prioritize checking portable ingredients and ingredients with an approaching expiration date. For example, the collection unit checks and notifies the user of the stock amount of portable ingredients. Furthermore, when the user is traveling, the collection unit can prioritize checking ingredients that can be stored for a long period of time. For example, the collection unit checks and notifies the user of the expiration dates of ingredients that can be stored for a long period of time. This enables efficient ingredient management by prioritizing checking highly relevant ingredients taking into account the user's geographical location information. Some or all of the above-described processing by the collection unit may be performed using AI, for example, or may be performed without AI. For example, the collection unit may input the user's geographical location information to the generation AI and cause the generation AI to check highly relevant ingredients.

[0042] When checking the status of ingredients, the collection unit can analyze the user's social media activity and check the status of related ingredients. When checking the status of ingredients, the collection unit analyzes the user's social media activity and checks the status of related ingredients. For example, if the user mentions a specific ingredient on social media, the collection unit prioritizes checking the status of that ingredient. For example, the collection unit checks the status of ingredients related to a recipe shared by the user on social media. The collection unit can also check the status of related ingredients based on posts from cooking accounts the user follows on social media. For example, the collection unit checks the status of specific ingredients based on posts from the cooking accounts the user follows. This allows the status of related ingredients to be efficiently checked by analyzing the user's social media activity. Some or all of the above-described processing by the collection unit may be performed using, or without, AI. For example, the collection unit may input the user's social media activity data into the generation AI and cause the generation AI to check the status of related ingredients.

[0043] When creating a shopping list, the creation unit can adjust the level of detail of the list based on the importance of the ingredients. When creating a shopping list, the creation unit adjusts the level of detail of the list based on the importance of the ingredients. For example, the creation unit includes detailed information for important ingredients in the list. The creation unit includes, for example, the purchase location and price of important ingredients in the list. The creation unit can also include concise information for less important ingredients in the list. For example, the creation unit includes only the names and quantities of less important ingredients in the list. The creation unit can also adjust the display order of the list according to the importance of the ingredients. For example, the creation unit displays important ingredients at the top of the list so that they can be purchased preferentially. This enables efficient shopping by adjusting the level of detail of the list based on the importance of the ingredients. Some or all of the above-described processing in the creation unit may be performed using, or without, AI. For example, the creation unit may input ingredient importance data to a generation AI and cause the generation AI to adjust the level of detail of the list.

[0044] When creating a shopping list, the creation unit can apply different list creation algorithms depending on the category of ingredients. When creating a shopping list, the creation unit applies different list creation algorithms depending on the category of ingredients. For example, the creation unit applies a list creation algorithm that emphasizes freshness to fresh foods. The creation unit creates a list based on, for example, the expiration date or freshness of fresh foods. The creation unit can also apply a list creation algorithm that emphasizes expiration dates to preserved foods. For example, the creation unit creates a list based on the expiration date of preserved foods. The creation unit can also apply a list creation algorithm that emphasizes maintaining the frozen state to frozen foods. For example, the creation unit creates a list based on the storage state of frozen foods. This enables efficient shopping by applying different list creation algorithms depending on the category of ingredients. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input ingredient category data to the generation AI and cause the generation AI to apply the list creation algorithm.

[0045] When creating a shopping list, the creation unit can determine the priority of the list based on when the ingredients were purchased. When creating a shopping list, the creation unit determines the priority of the list based on when the ingredients were purchased. For example, the creation unit prioritizes ingredients with an approaching expiration date in the list. For example, the creation unit displays milk with an approaching expiration date at the top of the list. The creation unit can also prioritize ingredients with low inventory in the list. For example, the creation unit displays eggs with low inventory at the top of the list. The creation unit can also prioritize ingredients that the user frequently purchases in the list. For example, the creation unit displays bread that the user frequently purchases at the top of the list. This enables efficient shopping by determining the priority of the list based on when the ingredients were purchased. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input data on when ingredients were purchased into the generation AI and cause the generation AI to determine the priority of the list.

[0046] When creating a shopping list, the creation unit can adjust the order of the list based on the relevance of ingredients. When creating a shopping list, the creation unit adjusts the order of the list based on the relevance of ingredients. For example, the creation unit lists ingredients of the same category together in the list. For example, the creation unit lists vegetables together in the list. The creation unit can also list ingredients purchased at the same place together in the list. For example, the creation unit lists ingredients purchased at a supermarket together in the list. The creation unit can also list ingredients based on the order required for cooking. For example, the creation unit lists ingredients based on cooking steps. This enables efficient shopping by adjusting the order of the list based on the relevance of ingredients. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input ingredient relevance data to the generation AI and cause the generation AI to adjust the order of the list.

[0047] The suggestion unit can adjust the level of detail of a recipe based on the importance of ingredients when suggesting a recipe. The suggestion unit adjusts the level of detail of a recipe based on the importance of ingredients when suggesting a recipe. For example, the suggestion unit includes detailed information in recipes that use important ingredients. For example, the suggestion unit describes in detail cooking and storage methods for important ingredients. The suggestion unit can also include concise information in recipes that use less important ingredients. For example, the suggestion unit describes only the names and amounts of ingredients with less importance. The suggestion unit can also adjust the display order of recipes based on the importance of ingredients. For example, the suggestion unit displays recipes that use important ingredients at the top and suggests them preferentially. This enables efficient cooking by adjusting the level of detail of a recipe based on the importance of ingredients. Some or all of the above-described processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input ingredient importance data to a generation AI and cause the generation AI to adjust the level of detail of the recipe.

[0048] The suggestion unit can apply different recipe suggestion algorithms depending on the ingredient category when suggesting a recipe. The suggestion unit applies different recipe suggestion algorithms depending on the ingredient category when suggesting a recipe. For example, the suggestion unit applies a suggestion algorithm that emphasizes freshness to recipes that use fresh food. The suggestion unit proposes recipes based on, for example, the freshness of the fresh food. The suggestion unit can also apply a suggestion algorithm that emphasizes expiration dates to recipes that use preserved food. For example, the suggestion unit proposes recipes based on the expiration dates of the preserved food. The suggestion unit can also apply a suggestion algorithm that emphasizes maintaining the frozen state to recipes that use frozen food. For example, the suggestion unit proposes recipes based on the storage state of the frozen food. This enables efficient cooking by applying different recipe suggestion algorithms depending on the ingredient category. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input ingredient category data to the generation AI and cause the generation AI to apply the recipe suggestion algorithm.

[0049] When suggesting a recipe, the suggestion unit can determine the priority of the recipes based on when the ingredients were purchased. When suggesting a recipe, the suggestion unit determines the priority of the recipes based on when the ingredients were purchased. For example, the suggestion unit prioritizes recipes that use ingredients that are close to their expiration date. For example, the suggestion unit displays recipes that use milk that is close to its expiration date at the top. The suggestion unit can also prioritize recipes that use ingredients that are low in stock. For example, the suggestion unit displays recipes that use eggs that are low in stock at the top. The suggestion unit can also prioritize recipes that use ingredients that the user frequently purchases. For example, the suggestion unit displays recipes that use bread that the user frequently purchases at the top. This enables efficient cooking by determining the priority of recipes based on when the ingredients were purchased. Some or all of the above-described processing by the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input data on when ingredients were purchased to the generation AI and cause the generation AI to determine the priority of the recipes.

[0050] The suggestion unit can adjust the order of recipes based on the relevance of ingredients when suggesting a recipe. The suggestion unit adjusts the order of recipes based on the relevance of ingredients when suggesting a recipe. For example, the suggestion unit collectively suggests recipes that use ingredients from the same category. For example, the suggestion unit collectively suggests recipes that use vegetables. The suggestion unit can also suggest recipes based on the order required for cooking. For example, the suggestion unit suggests recipes based on cooking steps. The suggestion unit can also adjust the display order of recipes based on the relevance of ingredients. For example, the suggestion unit displays recipes that use highly related ingredients at the top. This enables efficient cooking by adjusting the order of recipes based on the relevance of ingredients. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input ingredient relevance data into the generation AI and cause the generation AI to adjust the order of recipes.

[0051] When analyzing the state of the refrigerator, the analysis unit can predict the current state by referring to past data. When analyzing the state of the refrigerator, the analysis unit can predict the current state by referring to past data. For example, the analysis unit predicts the current consumption status of ingredients based on past refrigerator usage data. For example, the analysis unit predicts the current expiration date of ingredients based on past ingredient consumption patterns. The analysis unit can also predict current temperature fluctuations inside the refrigerator based on past refrigerator temperature data. For example, the analysis unit predicts the current temperature fluctuations inside the refrigerator based on past temperature data. The analysis unit can also predict the current expiration date of ingredients based on past ingredient consumption patterns. For example, the analysis unit predicts the current expiration date of ingredients based on past consumption patterns. This enables efficient operation of the refrigerator by predicting the current state by referring to past data. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit may input past data into a generation AI and cause the generation AI to predict the current state.

[0052] When analyzing the state of the refrigerator, the analysis unit can apply different analysis methods depending on the refrigerator's usage. When analyzing the state of the refrigerator, the analysis unit applies different analysis methods depending on the refrigerator's usage. For example, if the refrigerator is opened and closed frequently, the analysis unit applies an analysis method that emphasizes temperature fluctuations. The analysis unit analyzes temperature fluctuations, for example, based on the number of times the refrigerator is opened and closed. The analysis unit can also apply an analysis method that emphasizes the deterioration of ingredients if the refrigerator has not been used for a long period of time. The analysis unit performs analysis based on, for example, the deterioration of ingredients in the refrigerator. The analysis unit can also apply an analysis method that emphasizes the arrangement of ingredients if the refrigerator is full. The analysis unit performs analysis based on, for example, the arrangement of ingredients in the refrigerator. This enables efficient operation of the refrigerator by applying different analysis methods depending on the refrigerator's usage. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input refrigerator usage data to the generation AI and cause the generation AI to apply different analysis methods.

[0053] The analysis unit can perform the analysis taking into account the geographical distribution of refrigerators when analyzing the condition of the refrigerators. The analysis unit performs the analysis taking into account the geographical distribution of refrigerators when analyzing the condition of the refrigerators. For example, the analysis unit performs the analysis taking into account the climatic conditions of the area where the refrigerators are installed. The analysis unit analyzes fluctuations in temperature and humidity inside the refrigerator based on, for example, the temperature and humidity of the area. The analysis unit can also perform the analysis taking into account the consumption pattern of the household where the refrigerator is installed. For example, the analysis unit analyzes food consumption status based on the household consumption pattern. The analysis unit can also perform the analysis taking into account the availability of food ingredients in the area where the refrigerator is installed. For example, the analysis unit analyzes food consumption status based on the availability of food ingredients in the area. In this way, performing the analysis taking into account the geographical distribution of refrigerators enables efficient refrigerator operation. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input refrigerator geographical distribution data to the generation AI and cause the generation AI to perform the analysis.

[0054] The analysis unit can improve the accuracy of the analysis by referring to related literature when analyzing the condition of the refrigerator. The analysis unit improves the accuracy of the analysis by referring to related literature when analyzing the condition of the refrigerator. For example, the analysis unit performs the analysis by referring to literature on the latest food preservation technologies. The analysis unit analyzes the preservation conditions of food ingredients in the refrigerator based on, for example, the latest food preservation technologies. The analysis unit can also perform the analysis by referring to research data on food deterioration. The analysis unit analyzes the preservation conditions of food ingredients based on, for example, research data on food deterioration. The analysis unit can also perform the analysis by referring to literature on refrigerator energy efficiency. The analysis unit analyzes refrigerator operation methods based on, for example, literature on refrigerator energy efficiency. By improving the accuracy of the analysis by referring to related literature, efficient refrigerator operation is possible. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input related literature data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0055] The presentation unit can select an optimal display method by referring to the user's past operation history when presenting information. The presentation unit selects an optimal display method by referring to the user's past operation history when presenting information. For example, the presentation unit prioritizes providing a display method that the user has previously preferred. The presentation unit displays information based on, for example, a display format or layout used in the past. The presentation unit can also predict and provide an optimal display method based on the user's past operation history. The presentation unit can predict a display method that the user prefers based on, for example, the past operation history. The presentation unit can also provide a customized display method based on a display method that the user has previously used. The presentation unit provides an optimal display method to the user based on, for example, the past operation history. This reduces the burden on the user by selecting an optimal display method by referring to the user's past operation history. Some or all of the above-described processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input the user's past operation history data to a generation AI and cause the generation AI to select an optimal display method.

[0056] The presentation unit can adjust the level of detail of the display based on the importance of the information when presenting the information. The presentation unit adjusts the level of detail of the display based on the importance of the information when presenting the information. For example, the presentation unit displays important information with a detailed explanation. The presentation unit displays, for example, detailed storage and cooking methods for important ingredients. The presentation unit can also display less important information with a concise explanation. The presentation unit, for example, displays only the name and amount of less important ingredients. The presentation unit can also adjust the display order based on the importance of the information. For example, the presentation unit displays important information at the top so that it can be viewed preferentially. By adjusting the level of detail of the display based on the importance of the information, important information can be viewed preferentially. Some or all of the above-described processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input information importance data to a generation AI and cause the generation AI to adjust the level of detail of the display.

[0057] The presentation unit can select the optimal display method by taking into consideration the user's device information when presenting information. The presentation unit selects the optimal display method by taking into consideration the user's device information when presenting information. For example, if the user is using a smartphone, the presentation unit provides a display method tailored to the screen size. The presentation unit can provide, for example, a display format optimized for the smartphone screen size. Furthermore, if the user is using a tablet, the presentation unit can also provide a display method optimized for a large screen. The presentation unit can provide, for example, a display format optimized for the tablet screen size. Furthermore, if the user is using a smartwatch, the presentation unit can also provide a simple and highly visible display method. The presentation unit can provide, for example, a display format optimized for the smartwatch screen size. This reduces the burden on the user by selecting the optimal display method by taking into consideration the user's device information. Some or all of the above-described processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input the user's device information to the generation AI and cause the generation AI to select the optimal display method.

[0058] The presentation unit can adjust the display order based on the relevance of the information when presenting the information. The presentation unit adjusts the display order based on the relevance of the information when presenting the information. For example, the presentation unit displays information of the same category together. For example, the presentation unit displays information about vegetables together. The presentation unit can also prioritize displaying highly relevant information. For example, the presentation unit prioritizes displaying information about fluctuations in temperature and humidity inside a refrigerator. The presentation unit can also adjust the display order based on the relevance of the information. For example, the presentation unit displays highly relevant information at the top. By adjusting the display order based on the relevance of the information, related information can be efficiently checked. Some or all of the above-described processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input information relevance data to a generation AI and cause the generation AI to adjust the display order.

[0059] The reading unit can apply different reading algorithms to different types of ingredients when reading barcodes or RFID tags. The reading unit applies different reading algorithms to different types of ingredients when reading barcodes or RFID tags. For example, the reading unit applies a reading algorithm that emphasizes freshness to fresh foods such as vegetables and fruits. The reading unit performs reading based on, for example, the freshness of the fresh food. The reading unit can also apply a reading algorithm that emphasizes expiration dates to preserved foods such as canned and bottled foods. The reading unit performs reading based on, for example, the expiration dates of preserved foods. The reading unit can also apply a reading algorithm that emphasizes maintaining the frozen state to frozen foods. The reading unit performs reading based on, for example, the storage state of the frozen food. In this way, by applying different reading algorithms to different types of ingredients, the condition of the ingredients can be more accurately confirmed. Some or all of the above-mentioned processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input different reading algorithms for different types of ingredients to the generation AI and have the generation AI perform the reading.

[0060] When reading barcodes or RFID tags, the reading unit can prioritize reading highly relevant ingredients taking into account the user's geographical location information. When reading barcodes or RFID tags, the reading unit prioritizes reading highly relevant ingredients taking into account the user's geographical location information. For example, when the user is at home, the reading unit reads all ingredients in the refrigerator. The reading unit reads, for example, the expiration dates and stock amounts of ingredients in the refrigerator. Furthermore, when the user is out, the reading unit can prioritize reading portable ingredients or ingredients with an approaching expiration date. For example, the reading unit reads and notifies the user of the stock amount of portable ingredients. Furthermore, when the user is traveling, the reading unit can prioritize reading ingredients that can be stored for a long period of time. For example, the reading unit reads and notifies the user of the expiration dates of ingredients that can be stored for a long period of time. This enables efficient ingredient management by prioritizing reading highly relevant ingredients taking into account the user's geographical location information. Some or all of the above-described processing by the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input the user's geographical location information into the generation AI and have the generation AI read highly relevant ingredients.

[0061] The tracing unit can select the optimal tracing method by referring to past tracing data when tracing ingredients. The tracing unit selects the optimal tracing method by referring to past tracing data when tracing ingredients. For example, the tracing unit selects the optimal tracing method based on past tracing data. For example, the tracing unit prioritizes tracing ingredients with an approaching expiration date based on past tracing data. The tracing unit can also analyze past tracing data and select the most efficient tracing method. For example, the tracing unit selects the optimal tracing method based on past tracing data. This enables efficient ingredient management by selecting the optimal tracing method by referring to past tracing data. Some or all of the above-described processing in the tracing unit may be performed using, for example, AI, or may be performed without using AI. For example, the tracing unit can input past tracing data to a generation AI and cause the generation AI to select the optimal tracing method.

[0062] When tracking ingredients, the tracking unit can prioritize tracking highly relevant ingredients by taking into account the user's geographical location information. When tracking ingredients, the tracking unit prioritizes tracking highly relevant ingredients by taking into account the user's geographical location information. For example, when the user is at home, the tracking unit tracks all ingredients in the refrigerator. The tracking unit tracks, for example, the expiration dates and stock amounts of ingredients in the refrigerator. Furthermore, when the user is out, the tracking unit can prioritize tracking portable ingredients or ingredients with an approaching expiration date. For example, the tracking unit tracks and notifies the user of the stock amount of portable ingredients. Furthermore, when the user is traveling, the tracking unit can prioritize tracking ingredients that can be stored for a long period of time. For example, the tracking unit tracks and notifies the user of the expiration dates of ingredients that can be stored for a long period of time. This enables efficient ingredient management by prioritizing tracking highly relevant ingredients by taking into account the user's geographical location information. Some or all of the above-described processing by the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input the user's geographical location information into the generation AI and cause the generation AI to track highly related ingredients.

[0063] The storage unit can select the optimal storage method by referring to past storage data when saving data. The storage unit selects the optimal storage method by referring to past storage data when saving data. For example, the storage unit selects the optimal storage format based on past storage data. The storage unit adjusts the storage frequency based on past storage data, for example. The storage unit can also analyze past storage data and select the most efficient storage method. The storage unit selects the optimal storage method based on past storage data, for example. This enables efficient data management by selecting the optimal storage method by referring to past storage data. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input past storage data to a generation AI and have the generation AI select the optimal storage method.

[0064] The storage unit can adjust the storage order based on the relevance of the data when storing the data. The storage unit adjusts the storage order based on the relevance of the data when storing the data. For example, the storage unit stores data of the same category together. For example, the storage unit stores data related to vegetables together. The storage unit can also prioritize storing highly related data. For example, the storage unit prioritizes storing data related to temperature and humidity fluctuations in a refrigerator. The storage unit can also adjust the storage order based on the relevance of the data. For example, the storage unit stores highly related data at a higher level. This enables efficient data management by adjusting the storage order based on the relevance of the data. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input data related to the data to a generation AI and cause the generation AI to adjust the storage order.

[0065] The reference unit can select the optimal display method by referring to past reference history when referencing data. The reference unit selects the optimal display method by referring to past reference history when referencing data. For example, the reference unit prioritizes providing a display method that the user has previously preferred. The reference unit displays, for example, based on a display format or layout used in the past. The reference unit can also predict and provide an optimal display method based on the user's past reference history. For example, the reference unit predicts a display method that the user prefers based on the past reference history. The reference unit can also provide a customized display method based on a display method that the user has previously used. For example, the reference unit provides the optimal display method to the user based on the past reference history. This reduces the burden on the user by selecting the optimal display method by referring to the past reference history. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input past reference history data to a generation AI and cause the generation AI to select the optimal display method.

[0066] When referencing data, the reference unit can refer to the user's calendar information and make suggestions based on the schedule. When referencing data, the reference unit can refer to the user's calendar information and make suggestions based on the schedule. For example, the reference unit can refer to plans registered in the user's calendar and display related data. For example, the reference unit can display data on ingredients related to an event registered in the calendar. The reference unit can also suggest data related to a specific event from the user's calendar information. For example, the reference unit can suggest recipes related to an event registered in the calendar. The reference unit can also display optimal data tailored to the schedule based on the user's calendar information. For example, the reference unit can suggest when to consume ingredients based on the plan registered in the calendar. This enables efficient data management by making suggestions based on the schedule by referring to the user's calendar information. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or without AI. For example, the reference unit can input the user's calendar information into a generation AI and cause the generation AI to execute suggestions based on the schedule.

[0067] The reference unit can adjust the reference order based on the relevance of the data when referencing the data. The reference unit adjusts the reference order based on the relevance of the data when referencing the data. For example, the reference unit displays data of the same category together. For example, the reference unit displays data related to vegetables together. The reference unit can also prioritize displaying highly related data. For example, the reference unit prioritizes displaying data related to temperature and humidity fluctuations inside a refrigerator. The reference unit can also adjust the display order based on the relevance of the data. For example, the reference unit displays highly related data at the top. This enables efficient data management by adjusting the reference order based on the relevance of the data. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input data relevance data of the data to a generation AI and cause the generation AI to adjust the reference order.

[0068] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0069] The refrigerator management system can further include a voice recognition unit. The voice recognition unit recognizes voice commands from the user and operates the system. For example, if the user commands, "Tell me the milk stock," the voice recognition unit recognizes the command and sends an instruction to the collection unit. The collection unit checks the amount of milk in stock in the refrigerator and sends the information to the presentation unit. The presentation unit provides the stock information to the user via a screen or speaker. Furthermore, if the user commands, "Create a shopping list," the voice recognition unit sends an instruction to the creation unit, which creates the shopping list. Furthermore, if the user commands, "Suggest a recipe," the voice recognition unit sends an instruction to the suggestion unit, which suggests a recipe based on the ingredients in the refrigerator. This improves user convenience by allowing the system to be operated using voice commands.

[0070] The refrigerator management system may further include an energy management unit. The energy management unit monitors the energy consumption of the refrigerator and suggests efficient energy usage. For example, the energy management unit monitors the number of times the refrigerator is opened and closed and the duration of use, and analyzes the energy consumption pattern. For example, if the refrigerator is opened and closed too many times, the energy management unit may suggest to the user to open and close the refrigerator less. The energy management unit may also optimize the temperature settings of the refrigerator to reduce energy consumption. For example, the energy management unit may appropriately adjust the temperature inside the refrigerator to minimize energy consumption. Furthermore, the energy management unit stores energy consumption data of the refrigerator and allows the user to check past energy consumption. This makes it possible to reduce refrigerator operating costs by efficiently managing energy consumption.

[0071] The refrigerator management system may further include a health management unit. The health management unit suggests ingredients and recipes taking into account the user's health condition. For example, the health management unit records the user's allergy information and nutritional intake goals, and suggests ingredients and recipes based on that. For example, the health management unit suggests recipes that avoid ingredients to which the user is allergic. The health management unit can also suggest balanced meals based on the user's nutritional intake goals. For example, the health management unit suggests ingredients that contain the vitamins and minerals the user needs. Furthermore, the health management unit can suggest the timing of ingredient consumption based on the user's health condition. For example, the health management unit suggests ingredients that are suitable for the user to consume after exercise. This makes it possible to support a healthy diet by suggesting ingredients and recipes that suit the user's health condition.

[0072] The refrigerator management system may further include a reminder unit. The reminder unit provides important notifications to the user. For example, the reminder unit notifies the user when an ingredient is nearing its expiration date. The reminder unit may, for example, list ingredients whose expiration date is within one week and notify the user. The reminder unit may also notify the user when refrigerator maintenance is required. For example, the reminder unit may notify the user when it is time to replace the refrigerator filter. The reminder unit may also notify the user when ingredients should be consumed based on the user's schedule. For example, the reminder unit may notify the user of ingredients that are nearing their expiration date before the user leaves on a trip. This important notification allows the user to prevent food waste and perform proper refrigerator maintenance.

[0073] The refrigerator management system may further include a communication unit. The communication unit supports information sharing between users. For example, the communication unit allows family members or roommates to share the status of the refrigerator. For example, the communication unit shares inventory information of ingredients in the refrigerator and coordinates who buys what. The communication unit also allows users to share recipes and ingredient information. For example, the communication unit shares recipes created by a user with other users. Furthermore, the communication unit also allows users to share ingredient purchase histories. For example, the communication unit records and shares who has purchased which ingredients. This supports information sharing between users, enabling efficient ingredient management.

[0074] The processing flow of the first embodiment will be briefly explained below.

[0075] Step 1: The collection unit checks the status of the ingredients. For example, the collection unit can check the expiration dates and stock levels of the ingredients in the refrigerator. The collection unit scans the barcodes of the ingredients in the refrigerator to check the expiration dates. The collection unit can also measure the stock levels of the ingredients in the refrigerator using a sensor. For example, the collection unit measures the weight of the ingredients in the refrigerator to check the stock levels. Step 2: The creation unit creates a shopping list based on the information collected by the collection unit. For example, the creation unit adds ingredients that are close to their expiration date or that are low in stock to the list. When there is little milk in the refrigerator, the creation unit automatically adds it to the shopping list. Step 3: The suggestion unit suggests recipes based on the information about ingredients in the refrigerator, based on the shopping list created by the creation unit. For example, the suggestion unit suggests appropriate recipes based on the ingredients in the refrigerator. The suggestion unit suggests recipes using vegetables and meat in the refrigerator. Step 4: The analysis unit analyzes the state of the refrigerator based on the recipe proposed by the suggestion unit. For example, the analysis unit measures the temperature and humidity inside the refrigerator and analyzes the storage state of the ingredients. If the temperature inside the refrigerator is not appropriate, the analysis unit issues a warning. Step 5: The display unit displays the information analyzed by the analysis unit. For example, the display unit displays the information on a screen and a speaker. The display unit issues a warning if the refrigerator door is open.

[0076] (Example 2) A refrigerator management system according to an embodiment of the present invention utilizes generative AI to add new functions to existing refrigerators. This system checks the status of ingredients, creates shopping lists, suggests recipes, analyzes the refrigerator status, and presents information. For example, in a refrigerator management system, AI tracks ingredients and beverages in the refrigerator and checks their status. This allows users to easily understand the expiration dates and inventory levels of ingredients. AI also creates shopping lists based on ingredients with approaching expiration dates or low inventory. For example, if milk is running low in the refrigerator, the AI ​​automatically adds it to the shopping list. Furthermore, barcodes and RFID tags are attached to ingredients, and the AI ​​automatically tracks detailed information about the ingredients. For example, by scanning the barcode, the AI ​​records the type of ingredient and purchase date. The AI ​​also suggests recipes tailored to the contents of the refrigerator. For example, the AI ​​suggests appropriate recipes based on the ingredients in the refrigerator. Furthermore, to support existing refrigerators, an external smart unit with built-in cameras and sensors is provided. This unit analyzes the refrigerator status and presents information on a screen and speaker. For example, the unit issues an alert if the refrigerator door is open. Finally, a function is provided that allows users to view the history of previously created menus and recipes. This allows users to easily check past menus and recipes, and the refrigerator management system can automatically manage the status of ingredients and support efficient shopping and cooking.

[0077] A refrigerator management system according to an embodiment includes a collection unit, a creation unit, a suggestion unit, an analysis unit, and a presentation unit. The collection unit checks the status of ingredients. For example, the collection unit can check the expiration dates and stock levels of ingredients in the refrigerator. For example, the collection unit scans barcodes of ingredients in the refrigerator to check expiration dates. The collection unit can also measure the stock levels of ingredients in the refrigerator using a sensor. For example, the collection unit measures the weight of ingredients in the refrigerator to check stock levels. The creation unit creates a shopping list based on the information collected by the collection unit. For example, the creation unit adds ingredients that are close to their expiration dates or that are low in stock to the list. For example, the creation unit automatically adds milk to the shopping list when the refrigerator is low in milk. The suggestion unit suggests recipes based on information about ingredients in the refrigerator based on the shopping list created by the creation unit. For example, the suggestion unit suggests appropriate recipes based on ingredients in the refrigerator. For example, the suggestion unit suggests recipes using vegetables and meat in the refrigerator. The analysis unit analyzes the status of the refrigerator based on the recipes suggested by the suggestion unit. For example, the analysis unit measures the temperature and humidity inside the refrigerator and analyzes the storage conditions of ingredients. For example, the analysis unit issues a warning if the temperature inside the refrigerator is not appropriate. The presentation unit presents the information analyzed by the analysis unit. For example, the presentation unit presents the information using a screen and a speaker. For example, the presentation unit issues a warning if the refrigerator door is open. In this way, the refrigerator management system according to the embodiment can automatically manage the status of ingredients and support efficient shopping and cooking.

[0078] The refrigerator management system includes a reading unit that reads barcodes or RFID tags. The reading unit reads barcodes or RFID tags. For example, the reading unit scans barcodes attached to ingredients in the refrigerator. The reading unit reads barcodes of ingredients using, for example, a barcode reader. The reading unit can also read RFID tags. For example, the reading unit reads RFID tags of ingredients using an RFID reader. By reading the barcodes or RFID tags, detailed information about ingredients can be tracked. Some or all of the above-described processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input data from barcodes or RFID tags into a generation AI and cause the generation AI to track detailed information about ingredients.

[0079] The refrigerator management system includes a tracking unit that tracks the read information. The tracking unit tracks the read information. For example, the tracking unit records and tracks information about ingredients read from barcodes or RFID tags. The tracking unit tracks information such as the type of ingredient, purchase date, and expiration date. The tracking unit can also track the inventory of ingredients. For example, the tracking unit measures the weight of ingredients in the refrigerator and tracks the inventory. In this way, by tracking the read information, the status of ingredients can be managed in detail. Some or all of the above-mentioned processing in the tracking unit may be performed using, or without, AI, for example. For example, the tracking unit can input data read from barcodes or RFID tags into a generation AI and cause the generation AI to track the status of ingredients.

[0080] The refrigerator management system includes a storage unit that stores a history of past menus and recipes. The storage unit stores the history of past menus and recipes. For example, the storage unit records and stores information about menus and recipes created in the past by a user. The storage unit stores information such as the date the menu was created, the ingredients used, and the cooking procedure. The storage unit can also store the history of recipes. For example, the storage unit stores information about recipes used in the past by a user. By storing the history of past menus and recipes, the user can refer to the past information. Some or all of the above-described processing in the storage unit may be performed using, or without, AI, for example. For example, the storage unit may input data about past menus and recipes into a generation AI and have the generation AI store the data.

[0081] The refrigerator management system includes a reference unit that references the stored history. The reference unit references the stored history. For example, the reference unit displays a history of past menus and recipes stored by the storage unit. The reference unit displays, for example, information on menus created by the user in the past and recipes used by the user. The reference unit can also search the stored history. For example, the reference unit searches for past menus and recipes based on specific ingredients or cooking methods. This allows the user to easily check past information by referring to the stored history. Some or all of the above-described processing in the reference unit may be performed using, or without, AI, for example. For example, the reference unit can input the stored history data into a generation AI and have the generation AI refer to the data.

[0082] The collection unit can check the expiration date or inventory amount. The collection unit checks the expiration date or inventory amount. For example, the collection unit checks the expiration date of ingredients in a refrigerator. The collection unit checks the expiration date, for example, by scanning a barcode. The collection unit can also check the inventory amount of ingredients in a refrigerator. For example, the collection unit measures the weight of ingredients using a sensor and checks the inventory amount. This makes it easier to manage ingredients by checking the expiration date or inventory amount. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input data on the expiration date or inventory amount into the generation AI and have the generation AI check the data.

[0083] The creation unit can create a shopping list based on ingredients that are close to their expiration date or that are low in stock. The creation unit creates a shopping list based on ingredients that are close to their expiration date or that are low in stock. For example, the creation unit checks the expiration dates of ingredients in the refrigerator and adds ingredients that are close to their expiration date to the list. For example, the creation unit automatically adds milk to the shopping list if its expiration date is approaching. The creation unit can also check the inventory of ingredients in the refrigerator and add ingredients that are low in stock to the list. For example, the creation unit automatically adds eggs to the shopping list if their inventory is low in the refrigerator. This enables efficient shopping by creating a shopping list based on ingredients that are close to their expiration date or that are low in stock. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input data on expiration dates and inventory amounts into the generation AI and cause the generation AI to create a shopping list.

[0084] The suggestion unit can suggest recipes based on information about ingredients in the refrigerator. The suggestion unit suggests recipes based on information about ingredients in the refrigerator. For example, the suggestion unit checks the ingredients in the refrigerator and suggests appropriate recipes based on that information. The suggestion unit suggests, for example, recipes using vegetables and meat in the refrigerator. The suggestion unit can also suggest new recipes based on combinations of ingredients in the refrigerator. For example, the suggestion unit suggests original recipes by combining ingredients in the refrigerator. This makes it possible to make effective use of ingredients by suggesting recipes based on information about ingredients in the refrigerator. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input information about ingredients in the refrigerator into a generation AI and have the generation AI suggest recipes.

[0085] The analysis unit can analyze the state of the refrigerator. The analysis unit analyzes the state of the refrigerator. For example, the analysis unit measures the temperature and humidity inside the refrigerator and analyzes the storage state of ingredients. For example, if the temperature inside the refrigerator is not appropriate, the analysis unit issues a warning. The analysis unit can also analyze the arrangement of ingredients inside the refrigerator. For example, if the arrangement of ingredients inside the refrigerator is not appropriate, the analysis unit suggests rearranging them. In this way, analyzing the state of the refrigerator enables efficient operation of the refrigerator. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data on the temperature and humidity inside the refrigerator into the generation AI and have the generation AI analyze the state.

[0086] The presentation unit can present information using a screen and a speaker. The presentation unit presents information using a screen and a speaker. For example, the presentation unit issues a warning if the refrigerator door is open. The presentation unit, for example, displays a warning message on the screen and issues an audio warning through the speaker. The presentation unit can also display the status of ingredients in the refrigerator. For example, the presentation unit displays the expiration date and stock amount of ingredients on the screen. By presenting information on the screen and the speaker, the user can confirm the information visually and audibly. Some or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input status data of ingredients in the refrigerator to the generation AI and cause the generation AI to present the information.

[0087] The collection unit can estimate the user's emotions and adjust the frequency of checking the status of ingredients based on the estimated user emotions. The collection unit estimates the user's emotions and adjusts the frequency of checking the status of ingredients based on the estimated user emotions. For example, if the user is stressed, the collection unit reduces the frequency of checking the status of ingredients and provides fewer notifications. For example, if the user is relaxed, the collection unit increases the frequency of checking the status of ingredients and provides more detailed information. Furthermore, if the user is in a hurry, the collection unit can prioritize checking only important ingredients and providing prompt notifications. For example, the collection unit prioritizes checking and notifying ingredients that are close to their expiration date. This reduces the burden on the user by adjusting the frequency of checking the status of ingredients according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI or without AI. For example, the collection unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the confirmation frequency based on the emotion.

[0088] The collection unit can analyze the user's past consumption patterns and select the optimal checking method when checking the status of ingredients. The collection unit analyzes the user's past consumption patterns and selects the optimal checking method when checking the status of ingredients. For example, the collection unit prioritizes checking and notifying ingredients that the user frequently consumes. For example, the collection unit focuses on checking ingredients that the user has wasted in the past and makes suggestions to reduce waste. The collection unit can also adjust the timing of checking the status of ingredients based on the user's consumption patterns. For example, the collection unit prioritizes checking and notifying ingredients that the user consumes during a specific time period. This allows waste to be reduced by selecting the optimal checking method based on the user's past consumption patterns. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit can input the user's consumption pattern data into a generation AI and have the generation AI select the optimal checking method.

[0089] The collection unit can apply different confirmation algorithms to each type of ingredient when checking the status of the ingredients. The collection unit applies different confirmation algorithms to each type of ingredient when checking the status of the ingredients. For example, the collection unit applies a confirmation algorithm that emphasizes freshness to fresh foods such as vegetables and fruits. The collection unit, for example, measures the color and hardness of vegetables to check their freshness. The collection unit can also apply a confirmation algorithm that emphasizes expiration dates to preserved foods such as canned and bottled foods. For example, the collection unit scans barcodes to check the expiration dates of canned foods. The collection unit can also apply a confirmation algorithm that emphasizes maintaining the frozen state to frozen foods. For example, the collection unit measures the temperature of frozen foods to check their frozen state. In this way, applying different confirmation algorithms to each type of ingredient allows for more accurate confirmation of the status of the ingredients. Some or all of the above-described processing in the collection unit may be performed using, or without, AI. For example, the collection unit can input different confirmation algorithms for each type of ingredient into the generation AI and have the generation AI perform the confirmation.

[0090] The collection unit can estimate the user's emotions and determine the priority of checking the status of ingredients based on the estimated user emotions. The collection unit estimates the user's emotions and determines the priority of checking the status of ingredients based on the estimated user emotions. For example, when the user is stressed, the collection unit prioritizes checking only important ingredients and notifying the user. For example, the collection unit prioritizes checking ingredients with an approaching expiration date and notifying the user. Furthermore, when the user is relaxed, the collection unit can check the status of all ingredients in detail and notify the user. For example, the collection unit checks the expiration dates and stock levels of all ingredients in the refrigerator and notifies the user. Furthermore, when the user is in a hurry, the collection unit can prioritize checking ingredients with an approaching expiration date and notify the user quickly. For example, the collection unit prioritizes checking ingredients with an approaching expiration date and notifying the user. This reduces the burden on the user by determining the priority of checking the status of ingredients according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using AI, or may be performed without using AI. For example, the collection unit may input user emotion data into the generation AI and cause the generation AI to determine confirmation priorities based on emotions.

[0091] When checking the status of ingredients, the collection unit can prioritize checking highly relevant ingredients taking into account the user's geographical location information. When checking the status of ingredients, the collection unit prioritizes checking highly relevant ingredients taking into account the user's geographical location information. For example, when the user is at home, the collection unit checks all ingredients in the refrigerator. The collection unit checks, for example, the expiration dates and stock amounts of ingredients in the refrigerator. Furthermore, when the user is out, the collection unit can prioritize checking portable ingredients and ingredients with an approaching expiration date. For example, the collection unit checks and notifies the user of the stock amount of portable ingredients. Furthermore, when the user is traveling, the collection unit can prioritize checking ingredients that can be stored for a long period of time. For example, the collection unit checks and notifies the user of the expiration dates of ingredients that can be stored for a long period of time. This enables efficient ingredient management by prioritizing checking highly relevant ingredients taking into account the user's geographical location information. Some or all of the above-described processing by the collection unit may be performed using AI, for example, or may be performed without AI. For example, the collection unit may input the user's geographical location information to the generation AI and cause the generation AI to check highly relevant ingredients.

[0092] When checking the status of ingredients, the collection unit can analyze the user's social media activity and check the status of related ingredients. When checking the status of ingredients, the collection unit analyzes the user's social media activity and checks the status of related ingredients. For example, if the user mentions a specific ingredient on social media, the collection unit prioritizes checking the status of that ingredient. For example, the collection unit checks the status of ingredients related to a recipe shared by the user on social media. The collection unit can also check the status of related ingredients based on posts from cooking accounts the user follows on social media. For example, the collection unit checks the status of specific ingredients based on posts from the cooking accounts the user follows. This allows the status of related ingredients to be efficiently checked by analyzing the user's social media activity. Some or all of the above-described processing by the collection unit may be performed using, or without, AI. For example, the collection unit may input the user's social media activity data into the generation AI and cause the generation AI to check the status of related ingredients.

[0093] The creation unit can estimate the user's emotions and adjust the presentation of the shopping list based on the estimated user emotions. The creation unit can estimate the user's emotions and adjust the presentation of the shopping list based on the estimated user emotions. For example, when the user is feeling stressed, the creation unit creates a simple, highly visible shopping list. The creation unit can include, for example, only important ingredients in the list to enable quick shopping. The creation unit can also create a shopping list that includes detailed information when the user is relaxed. For example, the creation unit can include detailed information about ingredients and where to purchase them in the list. When the user is in a hurry, the creation unit can include only important ingredients in the list to enable quick shopping. For example, the creation unit can prioritize ingredients with an approaching expiration date in the list. This reduces the burden on the user by adjusting the presentation of the shopping list according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input user emotion data to the generation AI and cause the generation AI to adjust the list expression method based on the emotion.

[0094] When creating a shopping list, the creation unit can adjust the level of detail of the list based on the importance of the ingredients. When creating a shopping list, the creation unit adjusts the level of detail of the list based on the importance of the ingredients. For example, the creation unit includes detailed information for important ingredients in the list. The creation unit includes, for example, the purchase location and price of important ingredients in the list. The creation unit can also include concise information for less important ingredients in the list. For example, the creation unit includes only the names and quantities of less important ingredients in the list. The creation unit can also adjust the display order of the list according to the importance of the ingredients. For example, the creation unit displays important ingredients at the top of the list so that they can be purchased preferentially. This enables efficient shopping by adjusting the level of detail of the list based on the importance of the ingredients. Some or all of the above-described processing in the creation unit may be performed using, or without, AI. For example, the creation unit may input ingredient importance data to a generation AI and cause the generation AI to adjust the level of detail of the list.

[0095] When creating a shopping list, the creation unit can apply different list creation algorithms depending on the category of ingredients. When creating a shopping list, the creation unit applies different list creation algorithms depending on the category of ingredients. For example, the creation unit applies a list creation algorithm that emphasizes freshness to fresh foods. The creation unit creates a list based on, for example, the expiration date or freshness of fresh foods. The creation unit can also apply a list creation algorithm that emphasizes expiration dates to preserved foods. For example, the creation unit creates a list based on the expiration date of preserved foods. The creation unit can also apply a list creation algorithm that emphasizes maintaining the frozen state to frozen foods. For example, the creation unit creates a list based on the storage state of frozen foods. This enables efficient shopping by applying different list creation algorithms depending on the category of ingredients. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input ingredient category data to the generation AI and cause the generation AI to apply the list creation algorithm.

[0096] The creation unit can estimate the user's emotions and adjust the length of the shopping list based on the estimated user emotions. The creation unit can estimate the user's emotions and adjust the length of the shopping list based on the estimated user emotions. For example, if the user is feeling stressed, the creation unit can create a short, to-the-point shopping list. The creation unit can include, for example, only important ingredients in the list to enable quick shopping. The creation unit can also create a longer shopping list with more detailed information if the user is relaxed. For example, the creation unit can include detailed information about ingredients and where to purchase them in the list. The creation unit can also include, for example, only important ingredients in the list to enable quick shopping when the user is in a hurry. For example, the creation unit can prioritize ingredients with an approaching expiration date in the list. This reduces the burden on the user by adjusting the length of the shopping list according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input user emotion data to the generation AI and cause the generation AI to adjust the length of the list based on the emotion.

[0097] When creating a shopping list, the creation unit can determine the priority of the list based on when the ingredients were purchased. When creating a shopping list, the creation unit determines the priority of the list based on when the ingredients were purchased. For example, the creation unit prioritizes ingredients with an approaching expiration date in the list. For example, the creation unit displays milk with an approaching expiration date at the top of the list. The creation unit can also prioritize ingredients with low inventory in the list. For example, the creation unit displays eggs with low inventory at the top of the list. The creation unit can also prioritize ingredients that the user frequently purchases in the list. For example, the creation unit displays bread that the user frequently purchases at the top of the list. This enables efficient shopping by determining the priority of the list based on when the ingredients were purchased. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input data on when ingredients were purchased into the generation AI and cause the generation AI to determine the priority of the list.

[0098] When creating a shopping list, the creation unit can adjust the order of the list based on the relevance of ingredients. When creating a shopping list, the creation unit adjusts the order of the list based on the relevance of ingredients. For example, the creation unit lists ingredients of the same category together in the list. For example, the creation unit lists vegetables together in the list. The creation unit can also list ingredients purchased at the same place together in the list. For example, the creation unit lists ingredients purchased at a supermarket together in the list. The creation unit can also list ingredients based on the order required for cooking. For example, the creation unit lists ingredients based on cooking steps. This enables efficient shopping by adjusting the order of the list based on the relevance of ingredients. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input ingredient relevance data to the generation AI and cause the generation AI to adjust the order of the list.

[0099] The suggestion unit can estimate the user's emotions and adjust the way a recipe is presented based on the estimated user's emotions. The suggestion unit can estimate the user's emotions and adjust the way a recipe is presented based on the estimated user's emotions. For example, if the user is feeling stressed, the suggestion unit can suggest a simple, highly visible recipe. The suggestion unit can display a recipe that lists only important steps. The suggestion unit can also suggest a recipe that includes detailed information if the user is relaxed. For example, the suggestion unit can display a recipe that includes detailed information about ingredients and cooking tips. The suggestion unit can also suggest a recipe that requires a short cooking time if the user is in a hurry. For example, the suggestion unit can display a recipe that can be prepared in a short time. This reduces the burden on the user by adjusting the way a recipe is presented based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit can be performed using, for example, an AI, or without an AI. For example, the suggestion unit can input the user's emotional data into the generation AI and have the generation AI adjust the way the recipe is expressed based on the emotion.

[0100] The suggestion unit can adjust the level of detail of a recipe based on the importance of ingredients when suggesting a recipe. The suggestion unit adjusts the level of detail of a recipe based on the importance of ingredients when suggesting a recipe. For example, the suggestion unit includes detailed information in recipes that use important ingredients. For example, the suggestion unit describes in detail cooking and storage methods for important ingredients. The suggestion unit can also include concise information in recipes that use less important ingredients. For example, the suggestion unit describes only the names and amounts of ingredients with less importance. The suggestion unit can also adjust the display order of recipes based on the importance of ingredients. For example, the suggestion unit displays recipes that use important ingredients at the top and suggests them preferentially. This enables efficient cooking by adjusting the level of detail of a recipe based on the importance of ingredients. Some or all of the above-described processing in the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input ingredient importance data to a generation AI and cause the generation AI to adjust the level of detail of the recipe.

[0101] The suggestion unit can apply different recipe suggestion algorithms depending on the ingredient category when suggesting a recipe. The suggestion unit applies different recipe suggestion algorithms depending on the ingredient category when suggesting a recipe. For example, the suggestion unit applies a suggestion algorithm that emphasizes freshness to recipes that use fresh food. The suggestion unit proposes recipes based on, for example, the freshness of the fresh food. The suggestion unit can also apply a suggestion algorithm that emphasizes expiration dates to recipes that use preserved food. For example, the suggestion unit proposes recipes based on the expiration dates of the preserved food. The suggestion unit can also apply a suggestion algorithm that emphasizes maintaining the frozen state to recipes that use frozen food. For example, the suggestion unit proposes recipes based on the storage state of the frozen food. This enables efficient cooking by applying different recipe suggestion algorithms depending on the ingredient category. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input ingredient category data to the generation AI and cause the generation AI to apply the recipe suggestion algorithm.

[0102] The suggestion unit can estimate the user's emotions and adjust the length of the recipe based on the estimated user emotions. The suggestion unit can estimate the user's emotions and adjust the length of the recipe based on the estimated user emotions. For example, if the user is feeling stressed, the suggestion unit can suggest a short, concise recipe. The suggestion unit can display, for example, a recipe that lists only important steps. The suggestion unit can also suggest a longer recipe with detailed instructions if the user is relaxed. The suggestion unit can display, for example, a recipe that includes detailed information about ingredients and cooking tips. The suggestion unit can also suggest a recipe with a short cooking time if the user is in a hurry. The suggestion unit can display, for example, a recipe that can be cooked in a short time. This reduces the burden on the user by adjusting the length of the recipe according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the suggestion unit can be performed using, for example, an AI, or without an AI. For example, the suggestion unit can input the user's emotional data into the generation AI and have the generation AI adjust the length of the recipe based on the emotion.

[0103] When suggesting a recipe, the suggestion unit can determine the priority of the recipes based on when the ingredients were purchased. When suggesting a recipe, the suggestion unit determines the priority of the recipes based on when the ingredients were purchased. For example, the suggestion unit prioritizes recipes that use ingredients that are close to their expiration date. For example, the suggestion unit displays recipes that use milk that is close to its expiration date at the top. The suggestion unit can also prioritize recipes that use ingredients that are low in stock. For example, the suggestion unit displays recipes that use eggs that are low in stock at the top. The suggestion unit can also prioritize recipes that use ingredients that the user frequently purchases. For example, the suggestion unit displays recipes that use bread that the user frequently purchases at the top. This enables efficient cooking by determining the priority of recipes based on when the ingredients were purchased. Some or all of the above-described processing by the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input data on when ingredients were purchased to the generation AI and cause the generation AI to determine the priority of the recipes.

[0104] The suggestion unit can adjust the order of recipes based on the relevance of ingredients when suggesting a recipe. The suggestion unit adjusts the order of recipes based on the relevance of ingredients when suggesting a recipe. For example, the suggestion unit collectively suggests recipes that use ingredients from the same category. For example, the suggestion unit collectively suggests recipes that use vegetables. The suggestion unit can also suggest recipes based on the order required for cooking. For example, the suggestion unit suggests recipes based on cooking steps. The suggestion unit can also adjust the display order of recipes based on the relevance of ingredients. For example, the suggestion unit displays recipes that use highly related ingredients at the top. This enables efficient cooking by adjusting the order of recipes based on the relevance of ingredients. Some or all of the above-mentioned processing in the suggestion unit may be performed using AI, for example, or may be performed without using AI. For example, the suggestion unit can input ingredient relevance data into the generation AI and cause the generation AI to adjust the order of recipes.

[0105] The analysis unit can estimate the user's emotions and adjust the criteria for analyzing the refrigerator's condition based on the estimated user emotions. The analysis unit estimates the user's emotions and adjusts the criteria for analyzing the refrigerator's condition based on the estimated user emotions. For example, if the user is stressed, the analysis unit bases its analysis on only important information. The analysis unit performs an analysis based on, for example, fluctuations in temperature and humidity inside the refrigerator. Furthermore, if the user is relaxed, the analysis unit can base its analysis on detailed information. For example, the analysis unit performs an analysis based on the arrangement and storage state of ingredients inside the refrigerator. Furthermore, if the user is in a hurry, the analysis unit can quickly analyze and provide only important information. For example, the analysis unit quickly performs an analysis based on fluctuations in temperature and humidity inside the refrigerator. This reduces the burden on the user by adjusting the criteria for analyzing the refrigerator's condition according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input user emotion data to the generation AI and cause the generation AI to adjust the analysis criteria based on the emotion.

[0106] When analyzing the state of the refrigerator, the analysis unit can predict the current state by referring to past data. When analyzing the state of the refrigerator, the analysis unit can predict the current state by referring to past data. For example, the analysis unit predicts the current consumption status of ingredients based on past refrigerator usage data. For example, the analysis unit predicts the current expiration date of ingredients based on past ingredient consumption patterns. The analysis unit can also predict current temperature fluctuations inside the refrigerator based on past refrigerator temperature data. For example, the analysis unit predicts the current temperature fluctuations inside the refrigerator based on past temperature data. The analysis unit can also predict the current expiration date of ingredients based on past ingredient consumption patterns. For example, the analysis unit predicts the current expiration date of ingredients based on past consumption patterns. This enables efficient operation of the refrigerator by predicting the current state by referring to past data. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit may input past data into a generation AI and cause the generation AI to predict the current state.

[0107] When analyzing the state of the refrigerator, the analysis unit can apply different analysis methods depending on the refrigerator's usage. When analyzing the state of the refrigerator, the analysis unit applies different analysis methods depending on the refrigerator's usage. For example, if the refrigerator is opened and closed frequently, the analysis unit applies an analysis method that emphasizes temperature fluctuations. The analysis unit analyzes temperature fluctuations, for example, based on the number of times the refrigerator is opened and closed. The analysis unit can also apply an analysis method that emphasizes the deterioration of ingredients if the refrigerator has not been used for a long period of time. The analysis unit performs analysis based on, for example, the deterioration of ingredients in the refrigerator. The analysis unit can also apply an analysis method that emphasizes the arrangement of ingredients if the refrigerator is full. The analysis unit performs analysis based on, for example, the arrangement of ingredients in the refrigerator. This enables efficient operation of the refrigerator by applying different analysis methods depending on the refrigerator's usage. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input refrigerator usage data to the generation AI and cause the generation AI to apply different analysis methods.

[0108] The analysis unit can estimate the user's emotions and adjust the order in which the refrigerator condition analysis results are displayed based on the estimated user emotions. The analysis unit estimates the user's emotions and adjusts the order in which the refrigerator condition analysis results are displayed based on the estimated user emotions. For example, when the user is feeling stressed, the analysis unit prioritizes displaying important information. The analysis unit prioritizes displaying, for example, fluctuations in temperature and humidity inside the refrigerator. The analysis unit can also display detailed information in an orderly manner when the user is relaxed. The analysis unit displays, for example, the detailed arrangement and storage status of ingredients inside the refrigerator. The analysis unit can also quickly display key information when the user is in a hurry. The analysis unit quickly displays, for example, fluctuations in temperature and humidity inside the refrigerator. This reduces the burden on the user by adjusting the order in which the refrigerator condition analysis results are displayed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input user emotion data to the generation AI and cause the generation AI to adjust the display order based on the emotion.

[0109] The analysis unit can perform the analysis taking into account the geographical distribution of refrigerators when analyzing the condition of the refrigerators. The analysis unit performs the analysis taking into account the geographical distribution of refrigerators when analyzing the condition of the refrigerators. For example, the analysis unit performs the analysis taking into account the climatic conditions of the area where the refrigerators are installed. The analysis unit analyzes fluctuations in temperature and humidity inside the refrigerator based on, for example, the temperature and humidity of the area. The analysis unit can also perform the analysis taking into account the consumption pattern of the household where the refrigerator is installed. For example, the analysis unit analyzes food consumption status based on the household consumption pattern. The analysis unit can also perform the analysis taking into account the availability of food ingredients in the area where the refrigerator is installed. For example, the analysis unit analyzes food consumption status based on the availability of food ingredients in the area. In this way, performing the analysis taking into account the geographical distribution of refrigerators enables efficient refrigerator operation. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input refrigerator geographical distribution data to the generation AI and cause the generation AI to perform the analysis.

[0110] The analysis unit can improve the accuracy of the analysis by referring to related literature when analyzing the condition of the refrigerator. The analysis unit improves the accuracy of the analysis by referring to related literature when analyzing the condition of the refrigerator. For example, the analysis unit performs the analysis by referring to literature on the latest food preservation technologies. The analysis unit analyzes the preservation conditions of food ingredients in the refrigerator based on, for example, the latest food preservation technologies. The analysis unit can also perform the analysis by referring to research data on food deterioration. The analysis unit analyzes the preservation conditions of food ingredients based on, for example, research data on food deterioration. The analysis unit can also perform the analysis by referring to literature on refrigerator energy efficiency. The analysis unit analyzes refrigerator operation methods based on, for example, literature on refrigerator energy efficiency. By improving the accuracy of the analysis by referring to related literature, efficient refrigerator operation is possible. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input related literature data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0111] The presentation unit can estimate the user's emotions and adjust the information display method based on the estimated user emotions. The presentation unit can estimate the user's emotions and adjust the information display method based on the estimated user emotions. For example, when the user is feeling stressed, the presentation unit provides a simple, highly visible display method. The presentation unit can, for example, display only important information. Furthermore, when the user is relaxed, the presentation unit can provide a display method including detailed information. For example, the presentation unit can display detailed information about ingredients and storage methods. Furthermore, when the user is in a hurry, the presentation unit can provide a display method that focuses on the main points. For example, the presentation unit can quickly display only important information. This reduces the burden on the user by adjusting the information display method according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the presentation unit can be performed using, for example, an AI, or without an AI. For example, the presentation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the display method based on the emotion.

[0112] The presentation unit can select an optimal display method by referring to the user's past operation history when presenting information. The presentation unit selects an optimal display method by referring to the user's past operation history when presenting information. For example, the presentation unit prioritizes providing a display method that the user has previously preferred. The presentation unit displays information based on, for example, a display format or layout used in the past. The presentation unit can also predict and provide an optimal display method based on the user's past operation history. The presentation unit can predict a display method that the user prefers based on, for example, the past operation history. The presentation unit can also provide a customized display method based on a display method that the user has previously used. The presentation unit provides an optimal display method to the user based on, for example, the past operation history. This reduces the burden on the user by selecting an optimal display method by referring to the user's past operation history. Some or all of the above-described processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input the user's past operation history data to a generation AI and cause the generation AI to select an optimal display method.

[0113] The presentation unit can adjust the level of detail of the display based on the importance of the information when presenting the information. The presentation unit adjusts the level of detail of the display based on the importance of the information when presenting the information. For example, the presentation unit displays important information with a detailed explanation. The presentation unit displays, for example, detailed storage and cooking methods for important ingredients. The presentation unit can also display less important information with a concise explanation. The presentation unit, for example, displays only the name and amount of less important ingredients. The presentation unit can also adjust the display order based on the importance of the information. For example, the presentation unit displays important information at the top so that it can be viewed preferentially. By adjusting the level of detail of the display based on the importance of the information, important information can be viewed preferentially. Some or all of the above-described processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input information importance data to a generation AI and cause the generation AI to adjust the level of detail of the display.

[0114] The presentation unit can estimate the user's emotions and adjust the display order of information based on the estimated user emotions. The presentation unit estimates the user's emotions and adjusts the display order of information based on the estimated user emotions. For example, when the user is feeling stressed, the presentation unit prioritizes displaying important information. The presentation unit prioritizes displaying, for example, fluctuations in temperature and humidity inside the refrigerator. The presentation unit can also display detailed information in an orderly manner when the user is relaxed. The presentation unit displays, for example, the detailed arrangement and storage status of ingredients inside the refrigerator. The presentation unit can also quickly display key information when the user is in a hurry. The presentation unit quickly displays, for example, fluctuations in temperature and humidity inside the refrigerator. This reduces the burden on the user by adjusting the display order of information according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit may input user emotion data to the generation AI and cause the generation AI to adjust the display order based on the emotion.

[0115] The presentation unit can select the optimal display method by taking into consideration the user's device information when presenting information. The presentation unit selects the optimal display method by taking into consideration the user's device information when presenting information. For example, if the user is using a smartphone, the presentation unit provides a display method tailored to the screen size. The presentation unit can provide, for example, a display format optimized for the smartphone screen size. Furthermore, if the user is using a tablet, the presentation unit can also provide a display method optimized for a large screen. The presentation unit can provide, for example, a display format optimized for the tablet screen size. Furthermore, if the user is using a smartwatch, the presentation unit can also provide a simple and highly visible display method. The presentation unit can provide, for example, a display format optimized for the smartwatch screen size. This reduces the burden on the user by selecting the optimal display method by taking into consideration the user's device information. Some or all of the above-described processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input the user's device information to the generation AI and cause the generation AI to select the optimal display method.

[0116] The presentation unit can adjust the display order based on the relevance of the information when presenting the information. The presentation unit adjusts the display order based on the relevance of the information when presenting the information. For example, the presentation unit displays information of the same category together. For example, the presentation unit displays information about vegetables together. The presentation unit can also prioritize displaying highly relevant information. For example, the presentation unit prioritizes displaying information about fluctuations in temperature and humidity inside a refrigerator. The presentation unit can also adjust the display order based on the relevance of the information. For example, the presentation unit displays highly relevant information at the top. By adjusting the display order based on the relevance of the information, related information can be efficiently checked. Some or all of the above-described processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input information relevance data to a generation AI and cause the generation AI to adjust the display order.

[0117] The reading unit can estimate the user's emotions and adjust the frequency of barcode or RFID tag readings based on the estimated user emotions. The reading unit can estimate the user's emotions and adjust the frequency of barcode or RFID tag readings based on the estimated user emotions. For example, if the user is feeling stressed, the reading unit can reduce the reading frequency and provide less notifications. The reading unit can prioritize reading and notifying only important ingredients, for example. The reading unit can also increase the reading frequency and provide more detailed information if the user is relaxed. For example, the reading unit can read and notify the status of all ingredients in detail. Also, if the user is in a hurry, the reading unit can prioritize reading and notifying only important ingredients quickly. For example, the reading unit prioritizes reading and notifying ingredients with an approaching expiration date. This reduces the burden on the user by adjusting the frequency of barcode or RFID tag readings based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reading unit may be performed using AI, or may be performed without using AI. For example, the reading unit may input user emotion data into the generation AI and cause the generation AI to adjust the reading frequency based on the emotion.

[0118] The reading unit can apply different reading algorithms to different types of ingredients when reading barcodes or RFID tags. The reading unit applies different reading algorithms to different types of ingredients when reading barcodes or RFID tags. For example, the reading unit applies a reading algorithm that emphasizes freshness to fresh foods such as vegetables and fruits. The reading unit performs reading based on, for example, the freshness of the fresh food. The reading unit can also apply a reading algorithm that emphasizes expiration dates to preserved foods such as canned and bottled foods. The reading unit performs reading based on, for example, the expiration dates of preserved foods. The reading unit can also apply a reading algorithm that emphasizes maintaining the frozen state to frozen foods. The reading unit performs reading based on, for example, the storage state of the frozen food. In this way, by applying different reading algorithms to different types of ingredients, the condition of the ingredients can be more accurately confirmed. Some or all of the above-mentioned processing in the reading unit may be performed using, for example, AI, or may be performed without using AI. For example, the reading unit can input different reading algorithms for different types of ingredients to the generation AI and have the generation AI perform the reading.

[0119] The reading unit can estimate the user's emotions and determine the priority of ingredients to be read based on the estimated user emotions. The reading unit estimates the user's emotions and determines the priority of ingredients to be read based on the estimated user emotions. For example, when the user is stressed, the reading unit prioritizes reading and notifying only important ingredients. For example, the reading unit prioritizes reading and notifying ingredients that are close to their expiration date. Furthermore, when the user is relaxed, the reading unit can also read and notify the status of all ingredients in detail. For example, the reading unit reads and notifies the expiration dates and stock amounts of all ingredients in the refrigerator. Furthermore, when the user is in a hurry, the reading unit can prioritize reading and notifying ingredients that are close to their expiration date. For example, the reading unit prioritizes reading and notifying ingredients that are close to their expiration date. This reduces the burden on the user by determining the priority of ingredients to be read based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reading unit may be performed using AI, or may be performed without using AI. For example, the reading unit may input user emotion data into the generation AI and cause the generation AI to determine reading priorities based on emotion.

[0120] When reading barcodes or RFID tags, the reading unit can prioritize reading highly relevant ingredients taking into account the user's geographical location information. When reading barcodes or RFID tags, the reading unit prioritizes reading highly relevant ingredients taking into account the user's geographical location information. For example, when the user is at home, the reading unit reads all ingredients in the refrigerator. The reading unit reads, for example, the expiration dates and stock amounts of ingredients in the refrigerator. Furthermore, when the user is out, the reading unit can prioritize reading portable ingredients or ingredients with an approaching expiration date. For example, the reading unit reads and notifies the user of the stock amount of portable ingredients. Furthermore, when the user is traveling, the reading unit can prioritize reading ingredients that can be stored for a long period of time. For example, the reading unit reads and notifies the user of the expiration dates of ingredients that can be stored for a long period of time. This enables efficient ingredient management by prioritizing reading highly relevant ingredients taking into account the user's geographical location information. Some or all of the above-described processing by the reading unit may be performed using AI, for example, or without AI. For example, the reading unit can input the user's geographical location information into the generation AI and have the generation AI read highly relevant ingredients.

[0121] The tracking unit can estimate the user's emotions and adjust the ingredient tracking method based on the estimated user emotions. The tracking unit can estimate the user's emotions and adjust the ingredient tracking method based on the estimated user emotions. For example, when the user is stressed, the tracking unit prioritizes tracking and notifying only important ingredients. For example, the tracking unit prioritizes tracking and notifying ingredients with an approaching expiration date. Furthermore, when the user is relaxed, the tracking unit can track and notify the status of all ingredients in detail. For example, the tracking unit tracks and notifies the expiration dates and stock amounts of all ingredients in the refrigerator. Furthermore, when the user is in a hurry, the tracking unit can prioritize tracking and notifying ingredients with an approaching expiration date quickly. For example, the tracking unit prioritizes tracking and notifying ingredients with an approaching expiration date. This reduces the burden on the user by adjusting the ingredient tracking method according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the tracking unit may be performed using AI, or may be performed without using AI. For example, the tracking unit may input user emotion data into the generation AI and cause the generation AI to adjust the tracking method based on the emotion.

[0122] The tracing unit can select the optimal tracing method by referring to past tracing data when tracing ingredients. The tracing unit selects the optimal tracing method by referring to past tracing data when tracing ingredients. For example, the tracing unit selects the optimal tracing method based on past tracing data. For example, the tracing unit prioritizes tracing ingredients with an approaching expiration date based on past tracing data. The tracing unit can also analyze past tracing data and select the most efficient tracing method. For example, the tracing unit selects the optimal tracing method based on past tracing data. This enables efficient ingredient management by selecting the optimal tracing method by referring to past tracing data. Some or all of the above-described processing in the tracing unit may be performed using, for example, AI, or may be performed without using AI. For example, the tracing unit can input past tracing data to a generation AI and cause the generation AI to select the optimal tracing method.

[0123] The tracking unit can estimate the user's emotions and determine the priority of ingredients to track based on the estimated user emotions. The tracking unit estimates the user's emotions and determines the priority of ingredients to track based on the estimated user emotions. For example, when the user is feeling stressed, the tracking unit prioritizes tracking and notifying only important ingredients. For example, the tracking unit prioritizes tracking and notifying ingredients with an approaching expiration date. Furthermore, when the user is relaxed, the tracking unit can track the status of all ingredients in detail and notify the user. For example, the tracking unit tracks and notifies the user of the expiration dates and stock amounts of all ingredients in the refrigerator. Furthermore, when the user is in a hurry, the tracking unit can prioritize tracking and notifying ingredients with an approaching expiration date quickly. For example, the tracking unit prioritizes tracking and notifying ingredients with an approaching expiration date. This reduces the burden on the user by determining the priority of ingredients to track based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the tracking unit may be performed using AI, or may be performed without using AI. For example, the tracking unit may input user emotion data to the generation AI and cause the generation AI to determine tracking priorities based on the emotion.

[0124] When tracking ingredients, the tracking unit can prioritize tracking highly relevant ingredients by taking into account the user's geographical location information. When tracking ingredients, the tracking unit prioritizes tracking highly relevant ingredients by taking into account the user's geographical location information. For example, when the user is at home, the tracking unit tracks all ingredients in the refrigerator. The tracking unit tracks, for example, the expiration dates and stock amounts of ingredients in the refrigerator. Furthermore, when the user is out, the tracking unit can prioritize tracking portable ingredients or ingredients with an approaching expiration date. For example, the tracking unit tracks and notifies the user of the stock amount of portable ingredients. Furthermore, when the user is traveling, the tracking unit can prioritize tracking ingredients that can be stored for a long period of time. For example, the tracking unit tracks and notifies the user of the expiration dates of ingredients that can be stored for a long period of time. This enables efficient ingredient management by prioritizing tracking highly relevant ingredients by taking into account the user's geographical location information. Some or all of the above-described processing by the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input the user's geographical location information into the generation AI and cause the generation AI to track highly related ingredients.

[0125] The storage unit can estimate the user's emotions and select data to be saved based on the estimated user emotions. The storage unit estimates the user's emotions and selects data to be saved based on the estimated user emotions. For example, when the user is stressed, the storage unit prioritizes saving only important data. The storage unit prioritizes saving, for example, data on important ingredients. Furthermore, when the user is relaxed, the storage unit can save all data in detail. For example, the storage unit saves data on all ingredients in detail. Furthermore, when the user is in a hurry, the storage unit can quickly save data that highlights the main points. For example, the storage unit quickly saves data on important ingredients. This reduces the burden on the user by selecting data to be saved based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the storage unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the storage unit can input the user's emotional data into the generation AI and cause the generation AI to select data based on the emotion.

[0126] The storage unit can select the optimal storage method by referring to past storage data when saving data. The storage unit selects the optimal storage method by referring to past storage data when saving data. For example, the storage unit selects the optimal storage format based on past storage data. The storage unit adjusts the storage frequency based on past storage data, for example. The storage unit can also analyze past storage data and select the most efficient storage method. The storage unit selects the optimal storage method based on past storage data, for example. This enables efficient data management by selecting the optimal storage method by referring to past storage data. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input past storage data to a generation AI and have the generation AI select the optimal storage method.

[0127] The storage unit can estimate the user's emotions and prioritize the stored data based on the estimated user emotions. The storage unit estimates the user's emotions and prioritizes the stored data based on the estimated user emotions. For example, when the user is stressed, the storage unit prioritizes saving only important data. The storage unit prioritizes saving, for example, data on important ingredients. The storage unit can also save all data in detail when the user is relaxed. The storage unit, for example, saves data on all ingredients in detail. The storage unit can also quickly save data that highlights the main points when the user is in a hurry. The storage unit, for example, quickly saves data on important ingredients. This reduces the burden on the user by prioritizing the stored data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the storage unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the storage unit can input the user's emotional data into the generation AI and have the generation AI determine the priority of the stored data based on the emotion.

[0128] The storage unit can adjust the storage order based on the relevance of the data when storing the data. The storage unit adjusts the storage order based on the relevance of the data when storing the data. For example, the storage unit stores data of the same category together. For example, the storage unit stores data related to vegetables together. The storage unit can also prioritize storing highly related data. For example, the storage unit prioritizes storing data related to temperature and humidity fluctuations in a refrigerator. The storage unit can also adjust the storage order based on the relevance of the data. For example, the storage unit stores highly related data at a higher level. This enables efficient data management by adjusting the storage order based on the relevance of the data. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input data related to the data to a generation AI and cause the generation AI to adjust the storage order.

[0129] The reference unit can estimate the user's emotion and adjust the display method of the referenced data based on the estimated user emotion. The reference unit can estimate the user's emotion and adjust the display method of the referenced data based on the estimated user emotion. For example, when the user is stressed, the reference unit provides a simple, highly visible display method. The reference unit can, for example, display only important data. Furthermore, when the user is relaxed, the reference unit can provide a display method including detailed information. For example, the reference unit can display detailed information about ingredients and storage methods. Furthermore, when the user is in a hurry, the reference unit can provide a display method that focuses on the main points. For example, the reference unit can quickly display only important data. This reduces the burden on the user by adjusting the display method of the referenced data according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reference unit can be performed using, for example, AI, or without AI. For example, the reference unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the display method based on the emotion.

[0130] The reference unit can select the optimal display method by referring to past reference history when referencing data. The reference unit selects the optimal display method by referring to past reference history when referencing data. For example, the reference unit prioritizes providing a display method that the user has previously preferred. The reference unit displays, for example, based on a display format or layout used in the past. The reference unit can also predict and provide an optimal display method based on the user's past reference history. For example, the reference unit predicts a display method that the user prefers based on the past reference history. The reference unit can also provide a customized display method based on a display method that the user has previously used. For example, the reference unit provides the optimal display method to the user based on the past reference history. This reduces the burden on the user by selecting the optimal display method by referring to the past reference history. Some or all of the above-described processing in the reference unit may be performed using, for example, AI, or may be performed without using AI. For example, the reference unit can input past reference history data to a generation AI and cause the generation AI to select the optimal display method.

[0131] When referencing data, the reference unit can refer to the user's calendar information and make suggestions based on the schedule. When referencing data, the reference unit can refer to the user's calendar information and make suggestions based on the schedule. For example, the reference unit can refer to plans registered in the user's calendar and display related data. For example, the reference unit can display data on ingredients related to an event registered in the calendar. The reference unit can also suggest data related to a specific event from the user's calendar information. For example, the reference unit can suggest recipes related to an event registered in the calendar. The reference unit can also display optimal data tailored to the schedule based on the user's calendar information. For example, the reference unit can suggest when to consume ingredients based on the plan registered in the calendar. This enables efficient data management by making suggestions based on the schedule by referring to the user's calendar information. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or without AI. For example, the reference unit can input the user's calendar information into a generation AI and cause the generation AI to execute suggestions based on the schedule.

[0132] The reference unit can estimate the user's emotions and determine the priority of the reference data based on the estimated user emotions. The reference unit estimates the user's emotions and determines the priority of the reference data based on the estimated user emotions. For example, when the user is stressed, the reference unit prioritizes displaying important data. The reference unit prioritizes displaying, for example, data on important ingredients. The reference unit can also display detailed data in an orderly manner when the user is relaxed. The reference unit, for example, displays data on all ingredients in detail. The reference unit can also quickly display data that highlights the main points when the user is in a hurry. The reference unit, for example, quickly displays data on important ingredients. This reduces the burden on the user by determining the priority of the reference data according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reference unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reference unit can input user emotion data into the generation AI and cause the generation AI to determine the priority of the reference data based on emotion.

[0133] The reference unit can adjust the reference order based on the relevance of the data when referencing the data. The reference unit adjusts the reference order based on the relevance of the data when referencing the data. For example, the reference unit displays data of the same category together. For example, the reference unit displays data related to vegetables together. The reference unit can also prioritize displaying highly related data. For example, the reference unit prioritizes displaying data related to temperature and humidity fluctuations inside a refrigerator. The reference unit can also adjust the display order based on the relevance of the data. For example, the reference unit displays highly related data at the top. This enables efficient data management by adjusting the reference order based on the relevance of the data. Some or all of the above-mentioned processing in the reference unit may be performed using AI, for example, or may be performed without using AI. For example, the reference unit can input data relevance data of the data to a generation AI and cause the generation AI to adjust the reference order. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, creation unit, suggestion unit, analysis unit, presentation unit, and reading unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit checks the status of ingredients using the camera 42 or sensors of the smart device 14 and manages expiration dates and inventory amounts using the control unit 46A. The creation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, creates a shopping list based on information from the collection unit. The suggestion unit, realized, for example, by the specific processing unit 290 of the data processing device 12, suggests recipes based on information about ingredients in the refrigerator. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the status of the refrigerator. The presentation unit, realized, for example, by the output device 40 of the smart device 14, presents information. The reading unit, for example, reads barcodes or RFID tags using the camera 42 or barcode reader of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, creation unit, suggestion unit, analysis unit, presentation unit, and reading unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit checks the status of ingredients using the camera 42 or sensors of the smart glasses 214, and manages expiration dates and inventory amounts using the control unit 46A. The creation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and creates a shopping list based on information from the collection unit. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests recipes based on information about ingredients in the refrigerator. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the status of the refrigerator. The presentation unit presents information using, for example, the speaker 240 of the smart glasses 214. The reading unit reads barcodes or RFID tags using, for example, the camera 42 or a barcode reader of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, creation unit, suggestion unit, analysis unit, presentation unit, and reading unit, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit checks the status of ingredients using the camera 42 or sensors of the headset terminal 314, and manages expiration dates and inventory amounts using the control unit 46A. The creation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and creates a shopping list based on information from the collection unit. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests recipes based on information about ingredients in the refrigerator. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the status of the refrigerator. The presentation unit presents information using, for example, the display 343 of the headset terminal 314. The reading unit reads barcodes and RFID tags using, for example, the camera 42 or barcode reader of the headset terminal 314. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, creation unit, suggestion unit, analysis unit, presentation unit, and reading unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit checks the status of ingredients using the camera 42 or sensors of the robot 414, and manages expiration dates and inventory amounts using the control unit 46A. The creation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and creates a shopping list based on information from the collection unit. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests recipes based on information about ingredients in the refrigerator. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the status of the refrigerator. The presentation unit presents information using, for example, the speaker 240 of the robot 414. The reading unit reads barcodes and RFID tags using, for example, the camera 42 or barcode reader of the robot 414.

[0134] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0135] The refrigerator management system can further include a voice recognition unit. The voice recognition unit recognizes voice commands from the user and operates the system. For example, if the user commands, "Tell me the milk stock," the voice recognition unit recognizes the command and sends an instruction to the collection unit. The collection unit checks the amount of milk in stock in the refrigerator and sends the information to the presentation unit. The presentation unit provides the stock information to the user via a screen or speaker. Furthermore, if the user commands, "Create a shopping list," the voice recognition unit sends an instruction to the creation unit, which creates the shopping list. Furthermore, if the user commands, "Suggest a recipe," the voice recognition unit sends an instruction to the suggestion unit, which suggests a recipe based on the ingredients in the refrigerator. This improves user convenience by allowing the system to be operated using voice commands.

[0136] The refrigerator management system may further include an energy management unit. The energy management unit monitors the energy consumption of the refrigerator and suggests efficient energy usage. For example, the energy management unit monitors the number of times the refrigerator is opened and closed and the duration of use, and analyzes the energy consumption pattern. For example, if the refrigerator is opened and closed too many times, the energy management unit may suggest to the user to open and close the refrigerator less. The energy management unit may also optimize the temperature settings of the refrigerator to reduce energy consumption. For example, the energy management unit may appropriately adjust the temperature inside the refrigerator to minimize energy consumption. Furthermore, the energy management unit stores energy consumption data of the refrigerator and allows the user to check past energy consumption. This makes it possible to reduce refrigerator operating costs by efficiently managing energy consumption.

[0137] The refrigerator management system may further include a health management unit. The health management unit suggests ingredients and recipes taking into account the user's health condition. For example, the health management unit records the user's allergy information and nutritional intake goals, and suggests ingredients and recipes based on that. For example, the health management unit suggests recipes that avoid ingredients to which the user is allergic. The health management unit can also suggest balanced meals based on the user's nutritional intake goals. For example, the health management unit suggests ingredients that contain the vitamins and minerals the user needs. Furthermore, the health management unit can suggest the timing of ingredient consumption based on the user's health condition. For example, the health management unit suggests ingredients that are suitable for the user to consume after exercise. This makes it possible to support a healthy diet by suggesting ingredients and recipes that suit the user's health condition.

[0138] The refrigerator management system may further include a reminder unit. The reminder unit provides important notifications to the user. For example, the reminder unit notifies the user when an ingredient is nearing its expiration date. The reminder unit may, for example, list ingredients whose expiration date is within one week and notify the user. The reminder unit may also notify the user when refrigerator maintenance is required. For example, the reminder unit may notify the user when it is time to replace the refrigerator filter. The reminder unit may also notify the user when ingredients should be consumed based on the user's schedule. For example, the reminder unit may notify the user of ingredients that are nearing their expiration date before the user leaves on a trip. This important notification allows the user to prevent food waste and perform proper refrigerator maintenance.

[0139] The refrigerator management system may further include a communication unit. The communication unit supports information sharing between users. For example, the communication unit allows family members or roommates to share the status of the refrigerator. For example, the communication unit shares inventory information of ingredients in the refrigerator and coordinates who buys what. The communication unit also allows users to share recipes and ingredient information. For example, the communication unit shares recipes created by a user with other users. Furthermore, the communication unit also allows users to share ingredient purchase histories. For example, the communication unit records and shares who has purchased which ingredients. This supports information sharing between users, enabling efficient ingredient management.

[0140] The refrigerator management system may further include an emotion deduction unit. The emotion deduction unit deduces the user's emotion and adjusts the system operation. For example, if the user is feeling stressed, the emotion deduction unit reduces the frequency of notifications and provides simple information. For example, the emotion deduction unit notifies the user of only important ingredients and refrains from providing detailed information. Furthermore, if the user is relaxed, the emotion deduction unit can provide detailed information. For example, the emotion deduction unit notifies the user of the status of all ingredients in detail. Furthermore, if the user is in a hurry, the emotion deduction unit can quickly provide important information. For example, the emotion deduction unit prioritizes notifications of ingredients that are close to their expiration date. This allows the system operation to be adjusted according to the user's emotion, thereby reducing the burden on the user.

[0141] The refrigerator management system may further include an emotion estimation unit. The emotion estimation unit estimates the user's emotion and adjusts the recipe suggestion method. For example, if the user is feeling stressed, the emotion estimation unit suggests a simple and hassle-free recipe. The emotion estimation unit suggests, for example, a recipe that requires a short cooking time and few ingredients. The emotion estimation unit can also suggest a detailed recipe if the user is relaxed. The emotion estimation unit suggests, for example, a recipe that includes cooking tips and variations. Furthermore, if the user is in a hurry, the emotion estimation unit can suggest a recipe that can be made quickly. The emotion estimation unit suggests, for example, a recipe that can be made in a short time. In this way, the burden on the user can be reduced by adjusting the recipe suggestion method according to the user's emotion.

[0142] The refrigerator management system may further include an emotion deduction unit. The emotion deduction unit deduces the user's emotion and adjusts the method for creating a shopping list. For example, when the user is feeling stressed, the emotion deduction unit creates a simple, highly visible shopping list. For example, the emotion deduction unit includes only important ingredients in the list, allowing for quick shopping. Furthermore, when the user is relaxed, the emotion deduction unit can create a shopping list including detailed information. For example, the emotion deduction unit includes detailed information about ingredients and where to purchase them in the list. Furthermore, when the user is in a hurry, the emotion deduction unit can include only important ingredients in the list, allowing for quick shopping. For example, the emotion deduction unit prioritizes adding ingredients with an approaching expiration date to the list. In this way, the burden on the user can be reduced by adjusting the method for creating a shopping list according to the user's emotion.

[0143] The refrigerator management system may further include an emotion deduction unit. The emotion deduction unit deduces the user's emotion and adjusts the order in which the refrigerator condition analysis results are displayed. For example, when the user is feeling stressed, the emotion deduction unit prioritizes displaying important information. The emotion deduction unit prioritizes displaying, for example, fluctuations in temperature and humidity inside the refrigerator. Furthermore, when the user is relaxed, the emotion deduction unit can also display detailed information in an orderly manner. For example, the emotion deduction unit displays in detail the arrangement and storage status of ingredients inside the refrigerator. Furthermore, when the user is in a hurry, the emotion deduction unit can quickly display information that focuses on the main points. For example, the emotion deduction unit quickly displays fluctuations in temperature and humidity inside the refrigerator. In this way, the order in which the refrigerator condition analysis results are displayed can be adjusted according to the user's emotion, thereby reducing the burden on the user.

[0144] The refrigerator management system may further include an emotion deduction unit. The emotion deduction unit estimates the user's emotion and adjusts the frequency of checking the status of ingredients. For example, if the user is feeling stressed, the emotion deduction unit reduces the frequency of checking the status of ingredients and reduces notifications. The emotion deduction unit, for example, prioritizes checking and notifying only important ingredients. Furthermore, if the user is relaxed, the emotion deduction unit can increase the frequency of checking the status of ingredients and provide detailed information. For example, the emotion deduction unit checks the status of all ingredients in detail and notifies the user. Furthermore, if the user is in a hurry, the emotion deduction unit can prioritize checking only important ingredients and notify the user quickly. For example, the emotion deduction unit prioritizes checking and notifying ingredients that are close to their expiration date. In this way, the burden on the user can be reduced by adjusting the frequency of checking the status of ingredients according to the user's emotion.

[0145] The processing flow of the second embodiment will be briefly explained below.

[0146] Step 1: The collection unit checks the status of the ingredients. For example, the collection unit can check the expiration dates and stock levels of the ingredients in the refrigerator. The collection unit scans the barcodes of the ingredients in the refrigerator to check the expiration dates. The collection unit can also measure the stock levels of the ingredients in the refrigerator using a sensor. For example, the collection unit measures the weight of the ingredients in the refrigerator to check the stock levels. Step 2: The creation unit creates a shopping list based on the information collected by the collection unit. For example, the creation unit adds ingredients that are close to their expiration date or that are low in stock to the list. When there is little milk in the refrigerator, the creation unit automatically adds it to the shopping list. Step 3: The suggestion unit suggests recipes based on the information about ingredients in the refrigerator, based on the shopping list created by the creation unit. For example, the suggestion unit suggests appropriate recipes based on the ingredients in the refrigerator. The suggestion unit suggests recipes using vegetables and meat in the refrigerator. Step 4: The analysis unit analyzes the state of the refrigerator based on the recipe proposed by the suggestion unit. For example, the analysis unit measures the temperature and humidity inside the refrigerator and analyzes the storage state of the ingredients. If the temperature inside the refrigerator is not appropriate, the analysis unit issues a warning. Step 5: The display unit displays the information analyzed by the analysis unit. For example, the display unit displays the information on a screen and a speaker. The display unit issues a warning if the refrigerator door is open.

[0147] 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.

[0148] 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> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0149] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0151] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0152] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0153] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0154] 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.

[0155] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0156] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0161] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0162] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0163] 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.

[0164] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0165] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0168] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0169] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0170] 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.

[0171] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0172] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0177] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0178] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0179] 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.

[0180] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0181] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0182] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0183] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0184] 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.

[0185] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0186] 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.

[0187] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0188] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0189] 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.

[0190] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0191] 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.

[0192] 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.

[0193] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0194] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0195] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0196] 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.

[0197] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0198] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0199] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0200] 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.

[0201] 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 encompasses both emotions 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.

[0202] 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.

[0203] 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).

[0204] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, 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 expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0205] 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."

[0206] 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.

[0207] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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. A processor also includes 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.

[0212] The hardware resource that executes the specific process 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 process may be a single processor.

[0213] 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.

[0214] 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.

[0215] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0216] 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.

[0217] 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.

[0218] [Explanation of symbols]

[0219] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection section that checks the condition of ingredients; a creation unit that creates a shopping list based on the information collected by the collection unit; a suggestion unit that suggests recipes based on information about ingredients in a refrigerator, based on the shopping list created by the creation unit; an analysis unit that analyzes a state of the refrigerator based on the recipe suggested by the suggestion unit; a presentation unit that presents the information analyzed by the analysis unit. A system characterized by:

2. Equipped with a reading unit that reads barcodes or RFID tags The system of claim 1 .

3. Equipped with a tracking unit that tracks the read information 3. The system of claim 2.

4. Equipped with a storage section that stores the history of past menus and recipes The system of claim 1 .

5. Equipped with a reference section for referencing saved history 5. The system of claim 4.

6. The collecting unit Check expiration date or stock quantity The system of claim 1 .

7. The creation unit Create a shopping list based on ingredients that are nearing expiration or low in stock The system of claim 1 .

8. The proposal unit Suggest recipes based on the ingredients in your refrigerator The system of claim 1 .

Images