System

Abstract

To provide a system that analyzes ingredients in a refrigerator and proposes an optimal recipe to a user.SOLUTION: A system according to an embodiment includes a sensor unit, a proposal unit, a reception unit, an evaluation unit, and a communication unit. The sensor unit analyzes ingredients in a refrigerator. The proposal unit proposes a recipe based on the information analyzed by the sensor unit. The reception unit performs reception for a user to operate in a natural language. The evaluation unit evaluates the reliability of information provided by generative AI. The communication unit performs communication for the sensor unit and the generative AI to communicate with each other.SELECTED DRAWING: Figure 1

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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not adequately suggest recipes that efficiently utilize ingredients in the refrigerator, and there is room for improvement.

[0005] The system of the embodiment aims to analyze ingredients in a refrigerator and suggest optimal recipes to the user. [Means for solving the problem]

[0006] The system according to the embodiment includes a sensor unit, a suggestion unit, a reception unit, an evaluation unit, and a communication unit. The sensor unit analyzes ingredients in the refrigerator. The suggestion unit suggests recipes based on the information analyzed by the sensor unit. The reception unit receives input from the user in natural language. The evaluation unit evaluates the reliability of information provided by the generation AI. The communication unit communicates between the sensor unit and the generation AI. Effect of the Invention

[0007] The system according to the embodiment can analyze ingredients in a refrigerator and suggest optimal recipes to a user. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The home appliance system according to the embodiment of the present invention is a home appliance that utilizes generative AI to realize the Digital Agency's policy of "human-friendly digitalization that leaves no one behind." This home appliance system incorporates generative AI so that users can operate it in natural language. For example, if you say to your refrigerator, "Tell me what you can make with the ingredients in the refrigerator," the generative AI will analyze the ingredients in the refrigerator and suggest a recipe. Also, if you ask your washing machine, "How should I wash these clothes?", the generative AI will analyze the material of the clothes and the washing method, and suggest the optimal washing method. Furthermore, generative AI will be incorporated into home appliances such as air conditioners and lighting, so that users can operate them in natural language. For example, if you say to your air conditioner, "Set the room to a comfortable temperature," the generative AI will analyze the current room temperature and humidity, and set the optimal temperature. Also, if you say to the lighting, "Set the brightness to a relaxing level," the generative AI will analyze the brightness of the room and the time of day, and set the optimal lighting. In this way, by having contact with generative AI through home appliances, everyone will have the opportunity to come into contact with generative AI, thereby reducing the digital divide. This will enable home appliance systems to narrow the digital divide by allowing users to operate them in natural language and assess the reliability of the information provided by the generative AI.

[0029] The home appliance system according to the embodiment includes a sensor unit, a proposal unit, a reception unit, an evaluation unit, and a communication unit. The sensor unit analyzes ingredients in the refrigerator. The sensor unit can recognize ingredients in the refrigerator using, for example, image analysis technology and identify the type and amount of the ingredients. The sensor unit can also evaluate the nutritional value and freshness of the ingredients using ingredient analysis technology. Furthermore, the sensor unit can measure the weight of the ingredients using weight measurement technology and manage inventory. The proposal unit uses a generation AI to propose a recipe based on the information analyzed by the sensor unit. For example, the generation AI generates a recipe suitable for the user by taking into consideration the combination and nutritional balance of ingredients. Furthermore, the proposal unit can also suggest individually customized recipes by learning the user's preferences and past cooking history. Furthermore, the proposal unit can also suggest recipes according to the season and weather by the generation AI. The reception unit accepts requests for the user to operate in natural language. The reception unit analyzes the user's voice command using, for example, voice recognition technology and executes appropriate operations. The reception unit also supports text input, and the user can operate using a keyboard or touch panel. Furthermore, the reception unit supports multiple languages ​​and can handle users who speak different languages. The evaluation unit evaluates the reliability of the information provided by the generation AI. For example, the evaluation unit evaluates the accuracy and practicality of a recipe proposed by the generation AI and provides the user with reliable information. The evaluation unit can also work with an external database to evaluate reliability based on the latest information. Furthermore, the evaluation unit collects feedback from users and continuously improves the accuracy of the generation AI. The communication unit provides a mechanism for communication between the sensor unit and the generation AI. The communication unit transmits and receives data between the sensor unit and the generation AI using, for example, Wi-Fi or Bluetooth (registered trademark). Furthermore, the communication unit can also work with an external database via the Internet to obtain the latest information. Furthermore, the communication unit enables collaboration with different home appliances and realizes seamless operation. As a result, the home appliance system according to the embodiment can be operated by a user in natural language and can reduce the digital gap by evaluating the reliability of information provided by the generation AI.

[0030] The sensor unit analyzes the ingredients in the refrigerator. For example, the sensor unit can recognize the ingredients in the refrigerator using image analysis technology and identify the type and amount of the ingredients. Specifically, a camera installed in the refrigerator periodically takes images of the inside of the refrigerator and analyzes the image data to identify the type and amount of the ingredients. An object recognition algorithm is used for the image analysis, and the ingredients are identified based on the shape and color of the ingredients, the label on the package, and the like. The sensor unit can also evaluate the nutritional value and freshness of the ingredients using ingredient analysis technology. For example, an optical sensor is used to scan the surface of the ingredients, and the nutritional content and freshness are evaluated by analyzing the spectral data of the reflected light. Furthermore, the sensor unit can measure the weight of the ingredients using weight measurement technology and manage inventory. A weight sensor installed on a shelf or drawer of the refrigerator measures the weight of the ingredients, and the inventory status is grasped in real time based on the data. As a result, the sensor unit can collect various information such as the type, amount, nutritional value, freshness, and weight of the ingredients in the refrigerator and provide it to the user. Furthermore, the sensor unit can transmit this data to a cloud server and link with other systems and applications. For example, a user can use a smartphone app to check information about ingredients in the refrigerator and automatically order ingredients that are running low on stock, which allows the sensor unit to improve user convenience and reduce food waste.

[0031] The suggestion unit uses the generation AI to suggest recipes based on the information analyzed by the sensor unit. The generation AI generates recipes suitable for the user, taking into account the combination of ingredients and nutritional balance. Specifically, the generation AI generates recipes using the ingredient information acquired from the sensor unit as input data. The generation AI executes an algorithm to suggest optimal recipes based on information such as the type and amount of ingredients, nutritional value, and freshness. For example, the generation AI considers the combination of ingredients and suggests balanced meals. The generation AI can also learn the user's preferences and past cooking history to suggest individually customized recipes. Based on recipes and evaluations created by the user in the past, the generation AI can learn the user's preferences and make more personalized suggestions. Furthermore, the generation AI can also suggest recipes according to the season and weather. For example, it suggests hot soups and stews in cold seasons, and cold salads and snacks in hot seasons. As a result, the suggestion unit can provide optimal recipes according to the user's needs and situations and support meal preparation. Furthermore, the suggestion unit can collect feedback from users on the recipes suggested by the generation AI and continuously improve the algorithm of the generation AI. This allows the suggestion unit to always make more accurate recipe suggestions based on the latest information and user feedback.

[0032] The reception unit receives requests from users to operate the system in natural language. The reception unit, for example, uses voice recognition technology to analyze the user's voice command and executes an appropriate operation. Specifically, when the user speaks to the refrigerator, a built-in microphone captures the voice and analyzes the voice data. The voice recognition engine converts the voice data into text and executes an appropriate operation based on the text. For example, when the user says, "Tell me about the ingredients in the refrigerator," the reception unit responds to the user by voice with the ingredient information acquired from the sensor unit. The reception unit also supports text input, and the user can operate the system using a keyboard or touch panel. This allows the user to easily operate the system even in environments or situations where voice operation is difficult. Furthermore, the reception unit supports multiple languages ​​and can accommodate users who speak different languages. For example, by supporting major languages ​​such as English, Japanese, and Chinese, the system can accommodate a global user base. This allows the reception unit to enable the user to operate the system in a natural way, improving convenience. Furthermore, the reception unit records the user's voice commands and text input, and can provide faster and more accurate responses based on the user's operation history. This allows the reception unit to improve the user's operational experience and increase the ease of use of the entire system.

[0033] The evaluation unit evaluates the reliability of the information provided by the generation AI. For example, the evaluation unit evaluates the accuracy and practicality of the recipe proposed by the generation AI and provides the user with reliable information. Specifically, an algorithm is executed to evaluate whether the ingredients and steps of the recipe proposed by the generation AI are accurate and whether it is actually possible to cook it. For example, it checks whether the ingredients of the proposed recipe are present in the refrigerator and whether the steps are realistic. The evaluation unit can also work with an external database to evaluate reliability based on the latest information. For example, it obtains the latest data on the nutritional value and cooking method of food and compares it with the contents proposed by the generation AI. Furthermore, the evaluation unit collects feedback from users and continuously improves the accuracy of the generation AI. Based on the results and evaluations of the user's actual try of the proposed recipe, the generation AI's algorithm can be improved and more reliable information can be provided. This allows the evaluation unit to ensure the reliability of the information provided by the generation AI and allow the user to use it with peace of mind. Furthermore, the evaluation unit can check whether the contents proposed by the generation AI take into consideration the health and safety of the user. For example, it suggests recipes suitable for the user based on data on allergy information and dietary restrictions. This enables the evaluation unit to provide highly reliable information while protecting the health and safety of the user.

[0034] The communication unit provides a mechanism for the sensor unit and the generation AI to communicate. The communication unit transmits and receives data between the sensor unit and the generation AI, for example, using Wi-Fi or Bluetooth. Specifically, the data collected by the sensor in the refrigerator is transmitted to the generation AI via Wi-Fi or Bluetooth, and the generation AI returns the analysis results. The communication unit can also link with external databases via the Internet to obtain the latest information. For example, the latest data on the nutritional value and recipes of foods is obtained via the Internet and used for the generation AI's analysis. Furthermore, the communication unit enables linkage with different home appliances, achieving seamless operation. For example, an oven or microwave oven linked with the refrigerator can automatically set cooking settings based on a recipe proposed by the generation AI. This allows the user to operate multiple home appliances in a centralized manner, significantly reducing the effort of cooking. Furthermore, the communication unit also takes security measures to ensure that data is sent and received safely. For example, data encryption and authentication protocols are used to prevent unauthorized access and data leakage. As a result, the communication unit can improve the linkage and operability of the entire system while ensuring the user's privacy and data safety.

[0035] The sensor unit can analyze ingredients in the refrigerator. The sensor unit can recognize ingredients in the refrigerator using, for example, image analysis technology and identify the type and amount of the ingredients. The sensor unit can also evaluate the nutritional value and freshness of the ingredients using ingredient analysis technology. Furthermore, the sensor unit can measure the weight of the ingredients using weight measurement technology and perform inventory management. This makes it possible to analyze the ingredients in the refrigerator and suggest appropriate recipes to the user. Some or all of the above-mentioned processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input image data of ingredients in the refrigerator to the generation AI and cause the generation AI to identify the type and amount of the ingredients.

[0036] The suggestion unit can suggest recipes based on the analysis results by the generation AI. The suggestion unit uses the generation AI to suggest recipes based on the information analyzed by the sensor unit. For example, the generation AI generates a recipe suitable for the user by taking into account the combination of ingredients and nutritional balance. The suggestion unit can also suggest individually customized recipes by learning the user's preferences and past cooking history. The suggestion unit can also suggest recipes according to the season and weather by the generation AI. For example, the generation AI receives food data in the refrigerator as input and outputs a recipe that takes into account the combination of ingredients and nutritional balance. The generation AI can also learn the user's past cooking history and preferences and generate individually customized recipes. As a result, the use of the generation AI improves the accuracy of recipe suggestions.

[0037] The reception unit can receive commands for the user to operate in natural language. The reception unit receives commands for the user to operate in natural language. The reception unit, for example, uses voice recognition technology to analyze the user's voice command and executes an appropriate operation. The reception unit also supports text input, and the user can operate using a keyboard or touch panel. Furthermore, the reception unit supports multiple languages ​​and can also support users who speak different languages. This allows the user to operate in natural language, improving ease of use. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's voice data to the generation AI and cause the generation AI to analyze the voice command.

[0038] The evaluation unit can evaluate the reliability of the information provided by the generation AI. The evaluation unit evaluates the reliability of the information provided by the generation AI. For example, the evaluation unit evaluates the accuracy and practicality of a recipe proposed by the generation AI, and provides the user with reliable information. The evaluation unit can also work with an external database to evaluate reliability based on the latest information. Furthermore, the evaluation unit collects feedback from users and continuously improves the accuracy of the generation AI. For example, the evaluation unit collects the execution results of a recipe proposed by the generation AI as feedback from the user, and improves the accuracy of the recipe based on the feedback. The evaluation unit can also work with an external recipe database or nutrition database to evaluate the reliability of the recipe based on the latest information. This provides the user with a sense of security by evaluating the reliability of the information provided by the generation AI.

[0039] The communication unit can provide a mechanism for the sensor unit and the generation AI to communicate with each other. The communication unit provides a mechanism for the sensor unit and the generation AI to communicate with each other. The communication unit transmits and receives data between the sensor unit and the generation AI using, for example, Wi-Fi or Bluetooth. The communication unit can also link with an external database via the Internet to obtain the latest information. Furthermore, the communication unit enables linkage with different home appliances and realizes seamless operation. As a result, real-time information exchange is possible by communication between the sensor unit and the generation AI. Some or all of the above-mentioned processing in the communication unit may be performed using, for example, AI, or may be performed without using AI. For example, the communication unit can implement a communication protocol that transmits data acquired from the sensor unit to the generation AI, and the generation AI returns an analysis result.

[0040] The suggestion unit can suggest an appropriate temperature setting for the air conditioner. The suggestion unit uses the generation AI to suggest an appropriate temperature setting for the air conditioner. For example, the generation AI analyzes the current room temperature and humidity and sets the optimal temperature setting. In addition, the suggestion unit can also have the generation AI learn the user's preferences and past setting history and suggest an individually customized temperature setting. In addition, the suggestion unit can also have the generation AI suggest a temperature setting according to the season and weather. For example, the generation AI receives room temperature and humidity data as input and outputs an optimal temperature setting. In addition, the generation AI can learn the user's past setting history and preferences and suggest an individually customized temperature setting. In this way, a comfortable indoor environment is provided by suggesting an optimal temperature setting for the air conditioner.

[0041] The suggestion unit can suggest appropriate brightness settings for lighting. The suggestion unit uses the generation AI to suggest appropriate brightness settings for lighting. For example, the generation AI analyzes the brightness and time of day of the room and sets optimal lighting settings. In addition, the suggestion unit can also have the generation AI learn the user's preferences and past setting history and suggest individually customized brightness settings. Furthermore, the suggestion unit can also have the generation AI suggest brightness settings according to the season and weather. For example, the generation AI receives data on the brightness and time of day of the room as input and outputs optimal brightness settings. In addition, the generation AI can learn the user's past setting history and preferences and suggest individually customized brightness settings. In this way, a comfortable lighting environment is provided by suggesting optimal brightness settings for lighting.

[0042] The sensor unit can add a function of monitoring the freshness of ingredients in real time and notifying when the freshness has decreased. The sensor unit, for example, uses a temperature sensor to monitor the freshness of ingredients. For example, the sensor unit collects temperature data inside the refrigerator and evaluates the freshness of the ingredients. The sensor unit can also monitor the freshness of ingredients using a gas sensor. For example, the sensor unit analyzes the components of gas generated from the ingredients and evaluates the freshness. The sensor unit can also monitor the freshness of ingredients using image analysis technology. For example, the sensor unit analyzes the appearance of the ingredients and evaluates the freshness. This reduces the waste of ingredients by monitoring the freshness of the ingredients and notifying when the freshness has decreased. Some or all of the above-mentioned processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input image data of ingredients to the generation AI and cause the generation AI to execute the evaluation of freshness.

[0043] The sensor unit can analyze the nutritional value of ingredients and suggest ingredients according to the user's health condition. The sensor unit, for example, uses ingredient analysis technology to analyze the nutritional value of ingredients. For example, the sensor unit collects ingredient data of ingredients and evaluates the nutritional value. The sensor unit can also analyze the nutritional value of ingredients using calorie calculation technology. For example, the sensor unit collects calorie data of ingredients and evaluates the nutritional value. The sensor unit can also analyze the nutritional value of ingredients using technology to evaluate the balance of nutrients. For example, the sensor unit collects nutrient data of ingredients and evaluates the balance. This supports a healthy diet by suggesting ingredients according to the user's health condition. Some or all of the above-mentioned processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input ingredient data of ingredients to the generation AI and cause the generation AI to execute the evaluation of nutritional value.

[0044] The sensor unit can analyze allergen information of ingredients and warn users with allergies. The sensor unit can analyze allergen information of ingredients using, for example, ingredient analysis technology. For example, the sensor unit collects ingredient data of ingredients and evaluates the allergen information. The sensor unit can also analyze allergen information of ingredients using an allergen list. For example, the sensor unit can compare ingredient data of ingredients with the allergen list and evaluate the allergen information. The sensor unit can also analyze allergen information of ingredients taking into account the allergy information of a user. For example, the sensor unit receives the allergy information of a user as an input and evaluates the allergen information. This supports a safe diet by analyzing allergen information and warning users with allergies. Some or all of the above-mentioned processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input ingredient data of ingredients to a generation AI and cause the generation AI to execute evaluation of the allergen information.

[0045] The sensor unit can analyze the origin information of the ingredients and make suggestions based on the origin to the user. The sensor unit, for example, analyzes the origin information of the ingredients using a production database. For example, the sensor unit collects origin data of the ingredients and evaluates the origin information. The sensor unit can also analyze the origin information of the ingredients using traceability information. For example, the sensor unit collects traceability data of the ingredients and evaluates the origin information. The sensor unit can also analyze the origin information of the ingredients taking into account the user's preferences. For example, the sensor unit receives the user's preferences as input and evaluates the origin information. This expands the options for ingredients by analyzing the origin information and making suggestions to the user based on the origin. Some or all of the above-mentioned processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input the origin data of the ingredients to the generation AI and cause the generation AI to execute the evaluation of the origin information.

[0046] The suggestion unit can analyze the user's past cooking history and suggest recipes according to the preferences. The suggestion unit uses the generation AI to analyze the user's past cooking history and suggest recipes according to the preferences. For example, the suggestion unit uses the generation AI to analyze the user's past cooking history and generate recipes according to the preferences. In addition, the suggestion unit can also suggest recipes that are individually customized by the generation AI learning the user's preferences and past cooking history. In addition, the suggestion unit can also suggest recipes that take into account the user's health condition and nutritional balance. For example, the generation AI receives the user's past cooking history data as input and outputs recipes according to the preferences. In addition, the generation AI can also learn the user's preferences and health condition and generate individually customized recipes. In this way, recipes according to the user's preferences can be suggested by analyzing the past cooking history.

[0047] The suggestion unit can add a function to suggest recipes according to the season and weather. The suggestion unit adds a function to suggest recipes according to the season and weather using the generation AI. For example, the generation AI analyzes seasonal and weather data and suggests optimal recipes. The suggestion unit can also have the generation AI learn the user's preferences and past cooking history and suggest recipes according to the season and weather. The suggestion unit can also have the generation AI suggest recipes that take nutritional balance and health condition into consideration. For example, the generation AI receives seasonal and weather data as input and outputs optimal recipes. The generation AI can also learn the user's preferences and health condition and generate recipes according to the season and weather. This enriches the user's diet by suggesting recipes according to the season and weather.

[0048] The suggestion unit can also suggest a method of preserving ingredients when proposing a recipe. The suggestion unit uses the generation AI to also suggest a method of preserving ingredients when proposing a recipe. For example, the suggestion unit has the generation AI analyze a method of preserving ingredients and suggest an optimal preservation method. The suggestion unit can also have the generation AI learn the user's preferences and past cooking history and suggest a recipe according to the preservation method. Furthermore, the suggestion unit can also have the generation AI suggest a preservation method that takes nutritional balance and health condition into consideration. For example, the generation AI receives food preservation method data as input and outputs an optimal preservation method. The generation AI can also learn the user's preferences and health condition and generate a recipe according to the preservation method. In this way, by also suggesting a method of preserving ingredients when proposing a recipe, food waste is reduced.

[0049] The suggestion unit can add a function of suggesting substitutes for ingredients when proposing a recipe. The suggestion unit adds a function of suggesting substitutes for ingredients when proposing a recipe using the generation AI. For example, the suggestion unit has the generation AI analyze substitutes for ingredients and suggest optimal substitutes. The suggestion unit can also have the generation AI learn the user's preferences and past cooking history and suggest recipes according to the substitutes. Furthermore, the suggestion unit can also have the generation AI suggest substitutes that take nutritional balance and health status into consideration. For example, the generation AI receives ingredient substitute data as input and outputs optimal substitutes. The generation AI can also learn the user's preferences and health status and generate recipes according to the substitutes. This expands the user's options by suggesting substitutes for ingredients when proposing a recipe.

[0050] The reception unit can analyze the user's past operation history and propose the optimal operation method. The reception unit uses the generation AI to analyze the user's past operation history and propose the optimal operation method. For example, the generation AI analyzes the user's past operation history and proposes the optimal operation method. The reception unit can also have the generation AI learn the user's preferences and past operation history and propose an individually customized operation method. Furthermore, the reception unit can also have the generation AI propose an efficient operation method based on the user's operation history. For example, the generation AI receives the user's past operation history data as input and outputs the optimal operation method. The generation AI can also learn the user's preferences and operation history and propose an individually customized operation method. As a result, the optimal operation method can be proposed to the user by analyzing the past operation history.

[0051] The reception unit can add a function of learning the characteristics of the user's voice in order to improve the accuracy of the voice recognition. The reception unit adds a function of learning the characteristics of the user's voice in order to improve the accuracy of the voice recognition by using the generation AI. For example, the reception unit allows the generation AI to analyze the characteristics of the user's voice and improve the accuracy of the voice recognition. The reception unit can also allow the generation AI to analyze the tone and accent of the user's voice and improve the accuracy of the voice recognition. Furthermore, the reception unit can also allow the generation AI to maintain the accuracy of the voice recognition in response to changes in the user's voice. For example, the generation AI receives characteristic data of the user's voice as an input and trains the voice recognition model. The generation AI can also learn the tone and accent of the user's voice and improve the accuracy of the voice recognition. As a result, the accuracy of the voice recognition is improved by learning the characteristics of the user's voice. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input characteristic data of the user's voice to the generation AI and cause the generation AI to train the voice recognition model.

[0052] The reception unit can add visual feedback to the operation interface. The reception unit adds visual feedback to the operation interface using the generation AI. For example, the reception unit causes the generation AI to visually display the success or failure of the operation. The reception unit can also cause the generation AI to visually display the progress of the operation. Furthermore, the reception unit can also cause the generation AI to provide visual feedback based on the operation history of the user. For example, the generation AI provides visual feedback when the operation is successful, giving the user a sense of security. The generation AI can also visually display an error message when the operation fails, and present a countermeasure to the user. This improves the user's operation experience by adding visual feedback. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input operation progress data to the generation AI and cause the generation AI to execute visual feedback.

[0053] The reception unit can add haptic feedback to the operation interface. The reception unit adds haptic feedback to the operation interface using the generation AI. For example, the reception unit allows the generation AI to haptically feed back the success or failure of the operation. The reception unit can also allow the generation AI to haptically feed back the progress of the operation. Furthermore, the reception unit can also allow the generation AI to provide haptic feedback based on the operation history of the user. For example, the generation AI provides haptic feedback when the operation is successful, giving the user a sense of security. The generation AI can also provide haptic feedback such as vibration when the operation fails, and present a countermeasure to the user. Thereby, the addition of haptic feedback improves the user's operation experience. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input operation progress data to the generation AI and cause the generation AI to execute haptic feedback.

[0054] The evaluation unit can collect the execution results of the proposed recipe as feedback and continuously improve the reliability. The evaluation unit can use the generation AI to collect the execution results of the proposed recipe as feedback and continuously improve the reliability. For example, the generation AI collects feedback from the user and improves the accuracy of the recipe. The evaluation unit can also cause the generation AI to adjust the recipe based on the feedback. Furthermore, the evaluation unit can also cause the generation AI to preferentially suggest highly reliable recipes. For example, the generation AI receives feedback data from the user as input and improves the accuracy of the recipe. The generation AI can also adjust the recipe based on the feedback and preferentially suggest highly reliable recipes. This allows the reliability of the recipe to be continuously improved by collecting feedback. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input feedback data from the user to the generation AI and cause the generation AI to adjust the recipe.

[0055] The evaluation unit can cooperate with an external database and evaluate the reliability based on the latest information. The evaluation unit cooperates with an external database using the generation AI and evaluates the reliability based on the latest information. For example, the generation AI cooperates with an external recipe database and acquires the latest recipe information. The evaluation unit can also cooperate with an external nutrition database and evaluate the reliability of nutritional value. Furthermore, the evaluation unit can cooperate with an external ingredient database and acquire quality information of ingredients to evaluate the reliability. For example, the generation AI acquires the latest recipe information from an external recipe database and evaluates the reliability. The generation AI can also acquire nutritional value information from an external nutrition database and evaluate the reliability. Thereby, by cooperating with an external database, the reliability can be evaluated based on the latest information. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input information acquired from an external database to the generation AI and cause the generation AI to execute the evaluation of reliability.

[0056] The evaluation unit can evaluate the nutritional value of the proposed recipe and make a health-conscious suggestion. The evaluation unit uses the generation AI to evaluate the nutritional value of the proposed recipe and make a health-conscious suggestion. For example, the generation AI analyzes the nutritional value of the recipe and makes a health-conscious suggestion. The evaluation unit can also suggest a nutritionally balanced recipe by the generation AI taking into account the health condition of the user. Furthermore, the evaluation unit can preferentially suggest recipes using ingredients with high nutritional value. For example, the generation AI receives nutritional value data of the recipe as an input and makes a health-conscious suggestion. The generation AI can also learn the health condition of the user and suggest a nutritionally balanced recipe. In this way, a health-conscious recipe can be suggested by evaluating the nutritional value. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the nutritional value data of the recipe to the generation AI and cause the generation AI to execute the evaluation of the nutritional value.

[0057] The evaluation unit can evaluate the cost of the proposed recipe and make an economical suggestion. The evaluation unit uses the generation AI to evaluate the cost of the proposed recipe and make an economical suggestion. For example, the generation AI analyzes the cost of the recipe and makes an economical suggestion. The evaluation unit can also suggest a cost-effective recipe by taking into account the user's budget. Furthermore, the evaluation unit can also suggest a nutritious recipe by the generation AI while keeping costs down. For example, the generation AI receives recipe cost data as input and makes an economical suggestion. The generation AI can also learn the user's budget and suggest a cost-effective recipe. This allows an economical recipe to be suggested by evaluating the cost. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input recipe cost data to the generation AI and cause the generation AI to execute cost evaluation.

[0058] The communication unit can add a function to enhance the security of communication and protect data. The communication unit uses the generation AI to enhance the security of communication and add a function to protect data. For example, the generation AI encrypts the communication data to enhance security. The communication unit can also add an authentication process for communication to prevent unauthorized access. The communication unit can also periodically back up the communication data to enhance data protection. For example, the generation AI encrypts the communication data to enhance security. The generation AI can also add an authentication process for communication to prevent unauthorized access. This enhances the security of communication and improves data protection. Some or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input communication data to the generation AI and have the generation AI execute encryption and authentication processes.

[0059] The communication unit can optimize the speed of communication and enable data exchange in real time. The communication unit can optimize the speed of communication and enable data exchange in real time using the generation AI. For example, the generation AI can optimize the bandwidth of communication and improve the speed of data exchange. The communication unit can also minimize the delay in communication and enable data exchange in real time. Furthermore, the communication unit can set the priority of communication and quickly transmit important data. For example, the generation AI can optimize the bandwidth of communication and improve the speed of data exchange. The generation AI can also minimize the delay in communication and enable data exchange in real time. As a result, data exchange in real time is enabled by optimizing the speed of communication. A part or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input communication data to the generation AI and cause the generation AI to optimize the bandwidth and minimize the delay.

[0060] The communication unit can add a function for linking with different home appliances. The communication unit uses the generation AI to add a function for linking with different home appliances. For example, the generation AI links a refrigerator and an air conditioner to set an optimal room temperature. The communication unit can also link a washing machine and a dryer to automate a series of tasks from washing to drying. The communication unit can also link lighting and an air conditioner to provide a comfortable indoor environment. For example, the generation AI receives data of a refrigerator and an air conditioner as input and sets an optimal room temperature. The generation AI can also receive data of a washing machine and a dryer as input and automate a series of tasks from washing to drying. As a result, by adding a function for linking with different home appliances, the link between the home appliances is improved. Some or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input data of different home appliances to the generation AI and cause the generation AI to execute the linking function.

[0061] The communication unit can add a remote operation function via the Internet. The communication unit adds a remote operation function via the Internet using the generation AI. The communication unit, for example, provides a function in which the generation AI allows the user to check the contents of the refrigerator while away from home and purchase the necessary ingredients. The communication unit can also provide a function in which the generation AI allows the user to operate the air conditioner while away from home and set a comfortable room temperature when the user returns home. The communication unit can also provide a function in which the generation AI allows the user to operate the lighting while away from home and take crime prevention measures. For example, the generation AI provides a function in which the user checks the contents of the refrigerator while away from home and purchases the necessary ingredients. The generation AI can also provide a function in which the user operates the air conditioner while away from home and set a comfortable room temperature when the user returns home. By adding the remote operation function, it is possible to operate home appliances while away from home. Some or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input remote operation data to the generation AI and cause the generation AI to execute the remote operation function.

[0062] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0063] The home appliance system may further include a health management unit that monitors the user's health condition. The health management unit collects the user's health data and analyzes it using generative AI. For example, the health management unit collects data such as the user's weight, blood pressure, and heart rate, and evaluates the health condition. The health management unit may also analyze the user's diet history and exercise history to suggest healthy lifestyle habits. Furthermore, the health management unit may also suggest ingredients and recipes according to the user's health condition. This supports the user's health management and promotes a healthy lifestyle.

[0064] The suggestion unit can further add a function of suggesting recipes according to the user's dietary restrictions. For example, if the user needs to avoid a particular ingredient, the suggestion unit can suggest recipes that do not contain that ingredient. Also, if the user needs to ingest a particular nutrient, the suggestion unit can suggest recipes that contain a lot of that nutrient. This makes it possible to provide recipes according to the user's health condition and dietary restrictions.

[0065] The evaluation unit can further collect user feedback and use it as learning data for the generative AI. For example, the evaluation unit collects the results and impressions of users who actually make the suggested recipes and inputs that data into the generative AI. The evaluation unit can also improve the accuracy of the recipes based on user feedback. This makes it possible to continuously improve the accuracy of the generative AI's suggestions by utilizing user feedback.

[0066] The suggestion unit can further add a function of suggesting recipes according to the user's ingredient preferences. For example, if the user likes a particular ingredient, the suggestion unit can suggest recipes that contain a lot of that ingredient. Also, if the user avoids a particular ingredient, the suggestion unit can suggest recipes that do not contain that ingredient. This makes it possible to provide recipes that meet the user's preferences.

[0067] The sensor unit can further analyze the user's allergy information and issue a warning to users who have allergies. For example, the sensor unit collects ingredient data of ingredients and evaluates the allergen information. The sensor unit can also analyze the allergen information of ingredients taking into account the user's allergy information. This makes it possible to support a safe dietary lifestyle by analyzing allergen information and issuing warnings to users who have allergies.

[0068] The process flow of the first embodiment will be briefly described below.

[0069] Step 1: The sensor unit analyzes the ingredients in the refrigerator. The sensor unit uses image analysis technology to recognize the ingredients in the refrigerator and identify their type and amount. It also uses ingredient analysis technology to evaluate the nutritional value and freshness of the ingredients, and uses weight measurement technology to measure the weight of the ingredients and manage inventory. Step 2: The suggestion unit uses the generation AI to suggest recipes based on the information analyzed by the sensor unit. The generation AI considers ingredient combinations and nutritional balance to generate recipes suited to the user. It also learns the user's preferences and past cooking history to suggest individually customized recipes and recipes according to the season and weather. Step 3: The reception unit receives user operations in natural language. It uses voice recognition technology to analyze the user's voice commands and executes the appropriate operations. It also supports text input and is compatible with multiple languages. Step 4: The evaluation unit evaluates the reliability of the information provided by the generation AI. It evaluates the accuracy and practicality of the recipes proposed by the generation AI, and evaluates reliability based on the latest information in collaboration with external databases. It also collects feedback from users and continuously improves the accuracy of the generation AI. Step 5: The communication unit provides a mechanism for communication between the sensor unit and the generation AI. Data is sent and received between the sensor unit and the generation AI using Wi-Fi and Bluetooth, and the latest information is obtained by linking with external databases via the Internet. It also enables linking with different home appliances, realizing seamless operation.

[0070] (Example 2) The home appliance system according to the embodiment of the present invention is a home appliance that utilizes generative AI to realize the Digital Agency's policy of "human-friendly digitalization that leaves no one behind." This home appliance system incorporates generative AI so that users can operate it in natural language. For example, if you say to your refrigerator, "Tell me what you can make with the ingredients in the refrigerator," the generative AI will analyze the ingredients in the refrigerator and suggest a recipe. Also, if you ask your washing machine, "How should I wash these clothes?", the generative AI will analyze the material of the clothes and the washing method, and suggest the optimal washing method. Furthermore, generative AI will be incorporated into home appliances such as air conditioners and lighting, so that users can operate them in natural language. For example, if you say to your air conditioner, "Set the room to a comfortable temperature," the generative AI will analyze the current room temperature and humidity, and set the optimal temperature. Also, if you say to the lighting, "Set the brightness to a relaxing level," the generative AI will analyze the brightness of the room and the time of day, and set the optimal lighting. In this way, by having contact with generative AI through home appliances, everyone will have the opportunity to come into contact with generative AI, thereby reducing the digital divide. This will enable home appliance systems to narrow the digital divide by allowing users to operate them in natural language and assess the reliability of the information provided by the generative AI.

[0071] The home appliance system according to the embodiment includes a sensor unit, a proposal unit, a reception unit, an evaluation unit, and a communication unit. The sensor unit analyzes ingredients in the refrigerator. The sensor unit can recognize ingredients in the refrigerator using, for example, image analysis technology and identify the type and amount of the ingredients. The sensor unit can also evaluate the nutritional value and freshness of the ingredients using ingredient analysis technology. Furthermore, the sensor unit can measure the weight of the ingredients using weight measurement technology and manage inventory. The proposal unit uses a generation AI to propose a recipe based on the information analyzed by the sensor unit. For example, the generation AI generates a recipe suitable for the user by taking into consideration the combination and nutritional balance of ingredients. Furthermore, the proposal unit can also suggest individually customized recipes by learning the user's preferences and past cooking history. Furthermore, the proposal unit can also suggest recipes according to the season and weather by the generation AI. The reception unit accepts requests for the user to operate in natural language. The reception unit analyzes the user's voice command using, for example, voice recognition technology and executes appropriate operations. The reception unit also supports text input, and the user can operate using a keyboard or touch panel. Furthermore, the reception unit supports multiple languages ​​and can handle users who speak different languages. The evaluation unit evaluates the reliability of the information provided by the generation AI. For example, the evaluation unit evaluates the accuracy and practicality of a recipe proposed by the generation AI and provides the user with reliable information. The evaluation unit can also work with an external database to evaluate reliability based on the latest information. Furthermore, the evaluation unit collects feedback from users and continuously improves the accuracy of the generation AI. The communication unit provides a mechanism for communication between the sensor unit and the generation AI. The communication unit transmits and receives data between the sensor unit and the generation AI using, for example, Wi-Fi or Bluetooth. Furthermore, the communication unit can also work with an external database via the Internet to obtain the latest information. Furthermore, the communication unit enables collaboration with different home appliances and realizes seamless operation. As a result, the home appliance system according to the embodiment can be operated by a user in natural language and can reduce the digital gap by evaluating the reliability of information provided by the generation AI.

[0072] The sensor unit analyzes the ingredients in the refrigerator. For example, the sensor unit can recognize the ingredients in the refrigerator using image analysis technology and identify the type and amount of the ingredients. Specifically, a camera installed in the refrigerator periodically takes images of the inside of the refrigerator and analyzes the image data to identify the type and amount of the ingredients. An object recognition algorithm is used for the image analysis, and the ingredients are identified based on the shape and color of the ingredients, the label on the package, and the like. The sensor unit can also evaluate the nutritional value and freshness of the ingredients using ingredient analysis technology. For example, an optical sensor is used to scan the surface of the ingredients, and the nutritional content and freshness are evaluated by analyzing the spectral data of the reflected light. Furthermore, the sensor unit can measure the weight of the ingredients using weight measurement technology and manage inventory. A weight sensor installed on a shelf or drawer of the refrigerator measures the weight of the ingredients, and the inventory status is grasped in real time based on the data. As a result, the sensor unit can collect various information such as the type, amount, nutritional value, freshness, and weight of the ingredients in the refrigerator and provide it to the user. Furthermore, the sensor unit can transmit this data to a cloud server and link with other systems and applications. For example, a user can use a smartphone app to check information about ingredients in the refrigerator and automatically order ingredients that are running low on stock, which allows the sensor unit to improve user convenience and reduce food waste.

[0073] The suggestion unit uses the generation AI to suggest recipes based on the information analyzed by the sensor unit. The generation AI generates recipes suitable for the user, taking into account the combination of ingredients and nutritional balance. Specifically, the generation AI generates recipes using the ingredient information acquired from the sensor unit as input data. The generation AI executes an algorithm to suggest optimal recipes based on information such as the type and amount of ingredients, nutritional value, and freshness. For example, the generation AI considers the combination of ingredients and suggests balanced meals. The generation AI can also learn the user's preferences and past cooking history to suggest individually customized recipes. Based on recipes and evaluations created by the user in the past, the generation AI can learn the user's preferences and make more personalized suggestions. Furthermore, the generation AI can also suggest recipes according to the season and weather. For example, it suggests hot soups and stews in cold seasons, and cold salads and snacks in hot seasons. As a result, the suggestion unit can provide optimal recipes according to the user's needs and situations and support meal preparation. Furthermore, the suggestion unit can collect feedback from users on the recipes suggested by the generation AI and continuously improve the algorithm of the generation AI. This allows the suggestion unit to always make more accurate recipe suggestions based on the latest information and user feedback.

[0074] The reception unit receives requests from users to operate the system in natural language. The reception unit, for example, uses voice recognition technology to analyze the user's voice command and executes an appropriate operation. Specifically, when the user speaks to the refrigerator, a built-in microphone captures the voice and analyzes the voice data. The voice recognition engine converts the voice data into text and executes an appropriate operation based on the text. For example, when the user says, "Tell me about the ingredients in the refrigerator," the reception unit responds to the user by voice with the ingredient information acquired from the sensor unit. The reception unit also supports text input, and the user can operate the system using a keyboard or touch panel. This allows the user to easily operate the system even in environments or situations where voice operation is difficult. Furthermore, the reception unit supports multiple languages ​​and can accommodate users who speak different languages. For example, by supporting major languages ​​such as English, Japanese, and Chinese, the system can accommodate a global user base. This allows the reception unit to enable the user to operate the system in a natural way, improving convenience. Furthermore, the reception unit records the user's voice commands and text input, and can provide faster and more accurate responses based on the user's operation history. This allows the reception unit to improve the user's operational experience and increase the ease of use of the entire system.

[0075] The evaluation unit evaluates the reliability of the information provided by the generation AI. For example, the evaluation unit evaluates the accuracy and practicality of the recipe proposed by the generation AI and provides the user with reliable information. Specifically, an algorithm is executed to evaluate whether the ingredients and steps of the recipe proposed by the generation AI are accurate and whether it is actually possible to cook it. For example, it checks whether the ingredients of the proposed recipe are present in the refrigerator and whether the steps are realistic. The evaluation unit can also work with an external database to evaluate reliability based on the latest information. For example, it obtains the latest data on the nutritional value and cooking method of food and compares it with the contents proposed by the generation AI. Furthermore, the evaluation unit collects feedback from users and continuously improves the accuracy of the generation AI. Based on the results and evaluations of the user's actual try of the proposed recipe, the generation AI's algorithm can be improved and more reliable information can be provided. This allows the evaluation unit to ensure the reliability of the information provided by the generation AI and allow the user to use it with peace of mind. Furthermore, the evaluation unit can check whether the contents proposed by the generation AI take into consideration the health and safety of the user. For example, it suggests recipes suitable for the user based on data on allergy information and dietary restrictions. This enables the evaluation unit to provide highly reliable information while protecting the health and safety of the user.

[0076] The communication unit provides a mechanism for the sensor unit and the generation AI to communicate. The communication unit transmits and receives data between the sensor unit and the generation AI, for example, using Wi-Fi or Bluetooth. Specifically, the data collected by the sensor in the refrigerator is transmitted to the generation AI via Wi-Fi or Bluetooth, and the generation AI returns the analysis results. The communication unit can also link with external databases via the Internet to obtain the latest information. For example, the latest data on the nutritional value and recipes of foods is obtained via the Internet and used for the generation AI's analysis. Furthermore, the communication unit enables linkage with different home appliances, achieving seamless operation. For example, an oven or microwave oven linked with the refrigerator can automatically set cooking settings based on a recipe proposed by the generation AI. This allows the user to operate multiple home appliances in a centralized manner, significantly reducing the effort of cooking. Furthermore, the communication unit also takes security measures to ensure that data is sent and received safely. For example, data encryption and authentication protocols are used to prevent unauthorized access and data leakage. As a result, the communication unit can improve the linkage and operability of the entire system while ensuring the user's privacy and data safety.

[0077] The sensor unit can analyze ingredients in the refrigerator. The sensor unit can recognize ingredients in the refrigerator using, for example, image analysis technology and identify the type and amount of the ingredients. The sensor unit can also evaluate the nutritional value and freshness of the ingredients using ingredient analysis technology. Furthermore, the sensor unit can measure the weight of the ingredients using weight measurement technology and perform inventory management. This makes it possible to analyze the ingredients in the refrigerator and suggest appropriate recipes to the user. Some or all of the above-mentioned processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input image data of ingredients in the refrigerator to the generation AI and cause the generation AI to identify the type and amount of the ingredients.

[0078] The suggestion unit can suggest recipes based on the analysis results by the generation AI. The suggestion unit uses the generation AI to suggest recipes based on the information analyzed by the sensor unit. For example, the generation AI generates a recipe suitable for the user by taking into account the combination of ingredients and nutritional balance. The suggestion unit can also suggest individually customized recipes by learning the user's preferences and past cooking history. The suggestion unit can also suggest recipes according to the season and weather by the generation AI. For example, the generation AI receives food data in the refrigerator as input and outputs a recipe that takes into account the combination of ingredients and nutritional balance. The generation AI can also learn the user's past cooking history and preferences and generate individually customized recipes. As a result, the use of the generation AI improves the accuracy of recipe suggestions.

[0079] The reception unit can receive commands for the user to operate in natural language. The reception unit receives commands for the user to operate in natural language. The reception unit, for example, uses voice recognition technology to analyze the user's voice command and executes an appropriate operation. The reception unit also supports text input, and the user can operate using a keyboard or touch panel. Furthermore, the reception unit supports multiple languages ​​and can also support users who speak different languages. This allows the user to operate in natural language, improving ease of use. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's voice data to the generation AI and cause the generation AI to analyze the voice command.

[0080] The evaluation unit can evaluate the reliability of the information provided by the generation AI. The evaluation unit evaluates the reliability of the information provided by the generation AI. For example, the evaluation unit evaluates the accuracy and practicality of a recipe proposed by the generation AI, and provides the user with reliable information. The evaluation unit can also work with an external database to evaluate reliability based on the latest information. Furthermore, the evaluation unit collects feedback from users and continuously improves the accuracy of the generation AI. For example, the evaluation unit collects the execution results of a recipe proposed by the generation AI as feedback from the user, and improves the accuracy of the recipe based on the feedback. The evaluation unit can also work with an external recipe database or nutrition database to evaluate the reliability of the recipe based on the latest information. This provides the user with a sense of security by evaluating the reliability of the information provided by the generation AI.

[0081] The communication unit can provide a mechanism for the sensor unit and the generation AI to communicate with each other. The communication unit provides a mechanism for the sensor unit and the generation AI to communicate with each other. The communication unit transmits and receives data between the sensor unit and the generation AI using, for example, Wi-Fi or Bluetooth. The communication unit can also link with an external database via the Internet to obtain the latest information. Furthermore, the communication unit enables linkage with different home appliances and realizes seamless operation. As a result, real-time information exchange is possible by communication between the sensor unit and the generation AI. Some or all of the above-mentioned processing in the communication unit may be performed using, for example, AI, or may be performed without using AI. For example, the communication unit can implement a communication protocol that transmits data acquired from the sensor unit to the generation AI, and the generation AI returns an analysis result.

[0082] The suggestion unit can suggest an appropriate temperature setting for the air conditioner. The suggestion unit uses the generation AI to suggest an appropriate temperature setting for the air conditioner. For example, the generation AI analyzes the current room temperature and humidity and sets the optimal temperature setting. In addition, the suggestion unit can also have the generation AI learn the user's preferences and past setting history and suggest an individually customized temperature setting. In addition, the suggestion unit can also have the generation AI suggest a temperature setting according to the season and weather. For example, the generation AI receives room temperature and humidity data as input and outputs an optimal temperature setting. In addition, the generation AI can learn the user's past setting history and preferences and suggest an individually customized temperature setting. In this way, a comfortable indoor environment is provided by suggesting an optimal temperature setting for the air conditioner.

[0083] The suggestion unit can suggest appropriate brightness settings for lighting. The suggestion unit uses the generation AI to suggest appropriate brightness settings for lighting. For example, the generation AI analyzes the brightness and time of day of the room and sets optimal lighting settings. In addition, the suggestion unit can also have the generation AI learn the user's preferences and past setting history and suggest individually customized brightness settings. Furthermore, the suggestion unit can also have the generation AI suggest brightness settings according to the season and weather. For example, the generation AI receives data on the brightness and time of day of the room as input and outputs optimal brightness settings. In addition, the generation AI can learn the user's past setting history and preferences and suggest individually customized brightness settings. In this way, a comfortable lighting environment is provided by suggesting optimal brightness settings for lighting.

[0084] The sensor unit can estimate the user's emotion and adjust the analysis frequency of ingredients based on the estimated user's emotion. The sensor unit estimates the user's emotion using, for example, facial expression recognition technology. For example, the sensor unit analyzes the user's facial expression data and calculates an emotion score. The sensor unit can also estimate the user's emotion using voice analysis technology. For example, the sensor unit analyzes the tone and speed of the user's voice and calculates an emotion score. The sensor unit can also estimate the user's emotion using behavior analysis technology. For example, the sensor unit analyzes the user's behavior pattern and calculates an emotion score. This reduces the user's stress by adjusting the analysis frequency of ingredients according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the sensor unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the sensor unit can input a user's facial expression data to the generation AI and have the generation AI estimate emotions.

[0085] The sensor unit can add a function of monitoring the freshness of ingredients in real time and notifying when the freshness has decreased. The sensor unit, for example, uses a temperature sensor to monitor the freshness of ingredients. For example, the sensor unit collects temperature data inside the refrigerator and evaluates the freshness of the ingredients. The sensor unit can also monitor the freshness of ingredients using a gas sensor. For example, the sensor unit analyzes the components of gas generated from the ingredients and evaluates the freshness. The sensor unit can also monitor the freshness of ingredients using image analysis technology. For example, the sensor unit analyzes the appearance of the ingredients and evaluates the freshness. This reduces the waste of ingredients by monitoring the freshness of the ingredients and notifying when the freshness has decreased. Some or all of the above-mentioned processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input image data of ingredients to the generation AI and cause the generation AI to execute the evaluation of freshness.

[0086] The sensor unit can analyze the nutritional value of ingredients and suggest ingredients according to the user's health condition. The sensor unit, for example, uses ingredient analysis technology to analyze the nutritional value of ingredients. For example, the sensor unit collects ingredient data of ingredients and evaluates the nutritional value. The sensor unit can also analyze the nutritional value of ingredients using calorie calculation technology. For example, the sensor unit collects calorie data of ingredients and evaluates the nutritional value. The sensor unit can also analyze the nutritional value of ingredients using technology to evaluate the balance of nutrients. For example, the sensor unit collects nutrient data of ingredients and evaluates the balance. This supports a healthy diet by suggesting ingredients according to the user's health condition. Some or all of the above-mentioned processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input ingredient data of ingredients to the generation AI and cause the generation AI to execute the evaluation of nutritional value.

[0087] The sensor unit can estimate the user's emotion and adjust the display method of the analysis result based on the estimated user's emotion. The sensor unit estimates the user's emotion using, for example, facial expression recognition technology. For example, the sensor unit analyzes the user's facial expression data and calculates an emotion score. The sensor unit can also estimate the user's emotion using a voice analysis technology. For example, the sensor unit analyzes the tone and speed of the user's voice and calculates an emotion score. The sensor unit can also estimate the user's emotion using a behavior analysis technology. For example, the sensor unit analyzes the user's behavior pattern and calculates an emotion score. This helps the user understand by adjusting the display method of the analysis result according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the sensor unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the sensor unit can input a user's facial expression data to the generation AI and have the generation AI estimate emotions.

[0088] The sensor unit can analyze allergen information of ingredients and warn users with allergies. The sensor unit can analyze allergen information of ingredients using, for example, ingredient analysis technology. For example, the sensor unit collects ingredient data of ingredients and evaluates the allergen information. The sensor unit can also analyze allergen information of ingredients using an allergen list. For example, the sensor unit can compare ingredient data of ingredients with the allergen list and evaluate the allergen information. The sensor unit can also analyze allergen information of ingredients taking into account the allergy information of a user. For example, the sensor unit receives the allergy information of a user as an input and evaluates the allergen information. This supports a safe diet by analyzing allergen information and warning users with allergies. Some or all of the above-mentioned processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input ingredient data of ingredients to a generation AI and cause the generation AI to execute evaluation of the allergen information.

[0089] The sensor unit can analyze the origin information of the ingredients and make suggestions based on the origin to the user. The sensor unit, for example, analyzes the origin information of the ingredients using a production database. For example, the sensor unit collects origin data of the ingredients and evaluates the origin information. The sensor unit can also analyze the origin information of the ingredients using traceability information. For example, the sensor unit collects traceability data of the ingredients and evaluates the origin information. The sensor unit can also analyze the origin information of the ingredients taking into account the user's preferences. For example, the sensor unit receives the user's preferences as input and evaluates the origin information. This expands the options for ingredients by analyzing the origin information and making suggestions to the user based on the origin. Some or all of the above-mentioned processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input the origin data of the ingredients to the generation AI and cause the generation AI to execute the evaluation of the origin information.

[0090] The suggestion unit can estimate the user's emotion and adjust the recipe suggestion method based on the estimated user's emotion. The suggestion unit uses the generation AI to estimate the user's emotion and adjust the recipe suggestion method based on the estimated user's emotion. For example, the suggestion unit uses the generation AI to analyze the user's facial expression data and calculate an emotion score. The suggestion unit can also use the generation AI to analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the suggestion unit can also use the generation AI to analyze the user's behavior pattern and calculate an emotion score. This improves the user's satisfaction by adjusting the recipe suggestion method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the user's facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0091] The suggestion unit can analyze the user's past cooking history and suggest recipes according to the preferences. The suggestion unit uses the generation AI to analyze the user's past cooking history and suggest recipes according to the preferences. For example, the suggestion unit uses the generation AI to analyze the user's past cooking history and generate recipes according to the preferences. In addition, the suggestion unit can also suggest recipes that are individually customized by the generation AI learning the user's preferences and past cooking history. In addition, the suggestion unit can also suggest recipes that take into account the user's health condition and nutritional balance. For example, the generation AI receives the user's past cooking history data as input and outputs recipes according to the preferences. In addition, the generation AI can also learn the user's preferences and health condition and generate individually customized recipes. In this way, recipes according to the user's preferences can be suggested by analyzing the past cooking history.

[0092] The suggestion unit can add a function to suggest recipes according to the season and weather. The suggestion unit adds a function to suggest recipes according to the season and weather using the generation AI. For example, the generation AI analyzes seasonal and weather data and suggests optimal recipes. The suggestion unit can also have the generation AI learn the user's preferences and past cooking history and suggest recipes according to the season and weather. The suggestion unit can also have the generation AI suggest recipes that take nutritional balance and health condition into consideration. For example, the generation AI receives seasonal and weather data as input and outputs optimal recipes. The generation AI can also learn the user's preferences and health condition and generate recipes according to the season and weather. This enriches the user's diet by suggesting recipes according to the season and weather.

[0093] The suggestion unit can estimate the user's emotion and adjust the difficulty of the recipe based on the estimated user's emotion. The suggestion unit uses the generation AI to estimate the user's emotion and adjust the difficulty of the recipe based on the estimated user's emotion. For example, the suggestion unit uses the generation AI to analyze the user's facial expression data and calculate an emotion score. The suggestion unit can also use the generation AI to analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the suggestion unit can also use the generation AI to analyze the user's behavior pattern and calculate an emotion score. This improves the user's cooking experience by adjusting the difficulty of the recipe according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the user's facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0094] The suggestion unit can also suggest a method of preserving ingredients when proposing a recipe. The suggestion unit uses the generation AI to also suggest a method of preserving ingredients when proposing a recipe. For example, the suggestion unit has the generation AI analyze a method of preserving ingredients and suggest an optimal preservation method. The suggestion unit can also have the generation AI learn the user's preferences and past cooking history and suggest a recipe according to the preservation method. Furthermore, the suggestion unit can also have the generation AI suggest a preservation method that takes nutritional balance and health condition into consideration. For example, the generation AI receives food preservation method data as input and outputs an optimal preservation method. The generation AI can also learn the user's preferences and health condition and generate a recipe according to the preservation method. In this way, by also suggesting a method of preserving ingredients when proposing a recipe, food waste is reduced.

[0095] The suggestion unit can add a function of suggesting substitutes for ingredients when proposing a recipe. The suggestion unit adds a function of suggesting substitutes for ingredients when proposing a recipe using the generation AI. For example, the suggestion unit has the generation AI analyze substitutes for ingredients and suggest optimal substitutes. The suggestion unit can also have the generation AI learn the user's preferences and past cooking history and suggest recipes according to the substitutes. Furthermore, the suggestion unit can also have the generation AI suggest substitutes that take nutritional balance and health status into consideration. For example, the generation AI receives ingredient substitute data as input and outputs optimal substitutes. The generation AI can also learn the user's preferences and health status and generate recipes according to the substitutes. This expands the user's options by suggesting substitutes for ingredients when proposing a recipe.

[0096] The reception unit can estimate the user's emotion and adjust the display method of the operation interface based on the estimated user's emotion. The reception unit uses the generation AI to estimate the user's emotion and adjust the display method of the operation interface based on the estimated user's emotion. For example, the reception unit causes the generation AI to analyze the user's facial expression data and calculate an emotion score. The reception unit can also cause the generation AI to analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the reception unit can also cause the generation AI to analyze the user's behavior pattern and calculate an emotion score. This improves the user's operation experience by adjusting the display method of the operation interface according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0097] The reception unit can analyze the user's past operation history and propose the optimal operation method. The reception unit uses the generation AI to analyze the user's past operation history and propose the optimal operation method. For example, the generation AI analyzes the user's past operation history and proposes the optimal operation method. The reception unit can also have the generation AI learn the user's preferences and past operation history and propose an individually customized operation method. Furthermore, the reception unit can also have the generation AI propose an efficient operation method based on the user's operation history. For example, the generation AI receives the user's past operation history data as input and outputs the optimal operation method. The generation AI can also learn the user's preferences and operation history and propose an individually customized operation method. As a result, the optimal operation method can be proposed to the user by analyzing the past operation history.

[0098] The reception unit can add a function of learning the characteristics of the user's voice in order to improve the accuracy of the voice recognition. The reception unit adds a function of learning the characteristics of the user's voice in order to improve the accuracy of the voice recognition by using the generation AI. For example, the reception unit allows the generation AI to analyze the characteristics of the user's voice and improve the accuracy of the voice recognition. The reception unit can also allow the generation AI to analyze the tone and accent of the user's voice and improve the accuracy of the voice recognition. Furthermore, the reception unit can also allow the generation AI to maintain the accuracy of the voice recognition in response to changes in the user's voice. For example, the generation AI receives characteristic data of the user's voice as an input and trains the voice recognition model. The generation AI can also learn the tone and accent of the user's voice and improve the accuracy of the voice recognition. As a result, the accuracy of the voice recognition is improved by learning the characteristics of the user's voice. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input characteristic data of the user's voice to the generation AI and cause the generation AI to train the voice recognition model.

[0099] The reception unit can estimate the user's emotion and simplify the operation procedure based on the estimated user's emotion. The reception unit uses the generation AI to estimate the user's emotion and simplify the operation procedure based on the estimated user's emotion. For example, the reception unit causes the generation AI to analyze the user's facial expression data and calculate an emotion score. The reception unit can also cause the generation AI to analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the reception unit can also cause the generation AI to analyze the user's behavior pattern and calculate an emotion score. This reduces the user's stress by simplifying the operation procedure according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0100] The reception unit can add visual feedback to the operation interface. The reception unit adds visual feedback to the operation interface using the generation AI. For example, the reception unit causes the generation AI to visually display the success or failure of the operation. The reception unit can also cause the generation AI to visually display the progress of the operation. Furthermore, the reception unit can also cause the generation AI to provide visual feedback based on the operation history of the user. For example, the generation AI provides visual feedback when the operation is successful, giving the user a sense of security. The generation AI can also visually display an error message when the operation fails, and present a countermeasure to the user. This improves the user's operation experience by adding visual feedback. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input operation progress data to the generation AI and cause the generation AI to execute visual feedback.

[0101] The reception unit can add haptic feedback to the operation interface. The reception unit adds haptic feedback to the operation interface using the generation AI. For example, the reception unit allows the generation AI to haptically feed back the success or failure of the operation. The reception unit can also allow the generation AI to haptically feed back the progress of the operation. Furthermore, the reception unit can also allow the generation AI to provide haptic feedback based on the operation history of the user. For example, the generation AI provides haptic feedback when the operation is successful, giving the user a sense of security. The generation AI can also provide haptic feedback such as vibration when the operation fails, and present a countermeasure to the user. Thereby, the addition of haptic feedback improves the user's operation experience. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input operation progress data to the generation AI and cause the generation AI to execute haptic feedback.

[0102] The evaluation unit can estimate the user's emotion and adjust the criteria for evaluating the reliability of information based on the estimated user's emotion. The evaluation unit uses the generation AI to estimate the user's emotion and adjust the criteria for evaluating the reliability of information based on the estimated user's emotion. For example, the generation AI analyzes the user's facial expression data and calculates an emotion score. The evaluation unit can also analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the evaluation unit can analyze the user's behavior pattern and calculate an emotion score. This makes it possible to provide more appropriate information by adjusting the criteria for evaluating the reliability of information according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the evaluation unit can input the user's facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0103] The evaluation unit can collect the execution results of the proposed recipe as feedback and continuously improve the reliability. The evaluation unit can use the generation AI to collect the execution results of the proposed recipe as feedback and continuously improve the reliability. For example, the generation AI collects feedback from the user and improves the accuracy of the recipe. The evaluation unit can also cause the generation AI to adjust the recipe based on the feedback. Furthermore, the evaluation unit can also cause the generation AI to preferentially suggest highly reliable recipes. For example, the generation AI receives feedback data from the user as input and improves the accuracy of the recipe. The generation AI can also adjust the recipe based on the feedback and preferentially suggest highly reliable recipes. This allows the reliability of the recipe to be continuously improved by collecting feedback. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input feedback data from the user to the generation AI and cause the generation AI to adjust the recipe.

[0104] The evaluation unit can cooperate with an external database and evaluate the reliability based on the latest information. The evaluation unit cooperates with an external database using the generation AI and evaluates the reliability based on the latest information. For example, the generation AI cooperates with an external recipe database and acquires the latest recipe information. The evaluation unit can also cooperate with an external nutrition database and evaluate the reliability of nutritional value. Furthermore, the evaluation unit can cooperate with an external ingredient database and acquire quality information of ingredients to evaluate the reliability. For example, the generation AI acquires the latest recipe information from an external recipe database and evaluates the reliability. The generation AI can also acquire nutritional value information from an external nutrition database and evaluate the reliability. Thereby, by cooperating with an external database, the reliability can be evaluated based on the latest information. Part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input information acquired from an external database to the generation AI and cause the generation AI to execute the evaluation of reliability.

[0105] The evaluation unit can estimate the user's emotion and adjust the display method of the evaluation result based on the estimated user's emotion. The evaluation unit uses the generation AI to estimate the user's emotion and adjust the display method of the evaluation result based on the estimated user's emotion. For example, the generation AI analyzes the user's facial expression data and calculates an emotion score. The evaluation unit can also analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the evaluation unit can analyze the user's behavior pattern and calculate an emotion score. This helps the user understand by adjusting the display method of the evaluation result according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the evaluation unit can input the user's facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0106] The evaluation unit can evaluate the nutritional value of the proposed recipe and make a health-conscious suggestion. The evaluation unit uses the generation AI to evaluate the nutritional value of the proposed recipe and make a health-conscious suggestion. For example, the generation AI analyzes the nutritional value of the recipe and makes a health-conscious suggestion. The evaluation unit can also suggest a nutritionally balanced recipe by the generation AI taking into account the health condition of the user. Furthermore, the evaluation unit can preferentially suggest recipes using ingredients with high nutritional value. For example, the generation AI receives nutritional value data of the recipe as an input and makes a health-conscious suggestion. The generation AI can also learn the health condition of the user and suggest a nutritionally balanced recipe. In this way, a health-conscious recipe can be suggested by evaluating the nutritional value. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input the nutritional value data of the recipe to the generation AI and cause the generation AI to execute the evaluation of the nutritional value.

[0107] The evaluation unit can evaluate the cost of the proposed recipe and make an economical suggestion. The evaluation unit uses the generation AI to evaluate the cost of the proposed recipe and make an economical suggestion. For example, the generation AI analyzes the cost of the recipe and makes an economical suggestion. The evaluation unit can also suggest a cost-effective recipe by taking into account the user's budget. Furthermore, the evaluation unit can also suggest a nutritious recipe by the generation AI while keeping costs down. For example, the generation AI receives recipe cost data as input and makes an economical suggestion. The generation AI can also learn the user's budget and suggest a cost-effective recipe. This allows an economical recipe to be suggested by evaluating the cost. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input recipe cost data to the generation AI and cause the generation AI to execute cost evaluation.

[0108] The communication unit can estimate the user's emotion and adjust the priority of communication based on the estimated user's emotion. The communication unit uses the generation AI to estimate the user's emotion and adjust the priority of communication based on the estimated user's emotion. For example, the generation AI analyzes the user's facial expression data and calculates an emotion score. The communication unit can also analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the communication unit can analyze the user's behavior pattern and calculate an emotion score. As a result, important information can be quickly conveyed by adjusting the priority of communication according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the communication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the communication unit can input the user's facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0109] The communication unit can add a function to enhance the security of communication and protect data. The communication unit uses the generation AI to enhance the security of communication and add a function to protect data. For example, the generation AI encrypts the communication data to enhance security. The communication unit can also add an authentication process for communication to prevent unauthorized access. The communication unit can also periodically back up the communication data to enhance data protection. For example, the generation AI encrypts the communication data to enhance security. The generation AI can also add an authentication process for communication to prevent unauthorized access. This enhances the security of communication and improves data protection. Some or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input communication data to the generation AI and have the generation AI execute encryption and authentication processes.

[0110] The communication unit can optimize the speed of communication and enable data exchange in real time. The communication unit can optimize the speed of communication and enable data exchange in real time using the generation AI. For example, the generation AI can optimize the bandwidth of communication and improve the speed of data exchange. The communication unit can also minimize the delay in communication and enable data exchange in real time. Furthermore, the communication unit can set the priority of communication and quickly transmit important data. For example, the generation AI can optimize the bandwidth of communication and improve the speed of data exchange. The generation AI can also minimize the delay in communication and enable data exchange in real time. As a result, data exchange in real time is enabled by optimizing the speed of communication. A part or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input communication data to the generation AI and cause the generation AI to optimize the bandwidth and minimize the delay.

[0111] The communication unit can estimate the user's emotion and adjust the frequency of communication based on the estimated user's emotion. The communication unit uses the generation AI to estimate the user's emotion and adjust the frequency of communication based on the estimated user's emotion. For example, the generation AI analyzes the user's facial expression data and calculates an emotion score. The communication unit can also analyze the tone and speed of the user's voice and calculate an emotion score. Furthermore, the communication unit can analyze the user's behavior pattern and calculate an emotion score. This allows information to be provided at an appropriate time by adjusting the frequency of communication according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the communication unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the communication unit can input the user's facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0112] The communication unit can add a function for linking with different home appliances. The communication unit uses the generation AI to add a function for linking with different home appliances. For example, the generation AI links a refrigerator and an air conditioner to set an optimal room temperature. The communication unit can also link a washing machine and a dryer to automate a series of tasks from washing to drying. The communication unit can also link lighting and an air conditioner to provide a comfortable indoor environment. For example, the generation AI receives data of a refrigerator and an air conditioner as input and sets an optimal room temperature. The generation AI can also receive data of a washing machine and a dryer as input and automate a series of tasks from washing to drying. As a result, by adding a function for linking with different home appliances, the link between the home appliances is improved. Some or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input data of different home appliances to the generation AI and cause the generation AI to execute the linking function.

[0113] The communication unit can add a remote operation function via the Internet. The communication unit adds a remote operation function via the Internet using the generation AI. The communication unit, for example, provides a function in which the generation AI allows the user to check the contents of the refrigerator while away from home and purchase the necessary ingredients. The communication unit can also provide a function in which the generation AI allows the user to operate the air conditioner while away from home and set a comfortable room temperature when the user returns home. The communication unit can also provide a function in which the generation AI allows the user to operate the lighting while away from home and take crime prevention measures. For example, the generation AI provides a function in which the user checks the contents of the refrigerator while away from home and purchases the necessary ingredients. The generation AI can also provide a function in which the user operates the air conditioner while away from home and set a comfortable room temperature when the user returns home. By adding the remote operation function, it is possible to operate home appliances while away from home. Some or all of the above-mentioned processing in the communication unit may be performed, for example, using AI, or may be performed without using AI. For example, the communication unit can input remote operation data to the generation AI and cause the generation AI to execute the remote operation function.

[0114] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0115] The home appliance system may further include a health management unit that monitors the user's health condition. The health management unit collects the user's health data and analyzes it using generative AI. For example, the health management unit collects data such as the user's weight, blood pressure, and heart rate, and evaluates the health condition. The health management unit may also analyze the user's diet history and exercise history to suggest healthy lifestyle habits. Furthermore, the health management unit may also suggest ingredients and recipes according to the user's health condition. This supports the user's health management and promotes a healthy lifestyle.

[0116] The sensor unit can further add a function for monitoring the user's stress level. For example, the sensor unit can measure the user's heart rate and electrodermal activity to evaluate the stress level. The sensor unit can also analyze the user's facial expression and tone of voice to estimate the stress level. This makes it possible to provide a relaxing environment according to the user's stress level. For example, if the stress level is high, the temperature of the air conditioner can be adjusted or the brightness of the lights can be changed.

[0117] The suggestion unit can further add a function of suggesting recipes according to the user's dietary restrictions. For example, if the user needs to avoid a particular ingredient, the suggestion unit can suggest recipes that do not contain that ingredient. Also, if the user needs to ingest a particular nutrient, the suggestion unit can suggest recipes that contain a lot of that nutrient. This makes it possible to provide recipes according to the user's health condition and dietary restrictions.

[0118] The reception unit can further estimate the user's emotion and change the color and design of the operation interface based on the estimated user's emotion. For example, if the user is feeling stressed, the reception unit can change the color of the interface to a calm color to encourage the user to relax. Also, if the user is excited, the reception unit can simplify the design of the interface to improve ease of operation. This makes it possible to provide an operation interface that corresponds to the user's emotion.

[0119] The evaluation unit can further collect user feedback and use it as learning data for the generative AI. For example, the evaluation unit collects the results and impressions of users who actually make the suggested recipes and inputs that data into the generative AI. The evaluation unit can also improve the accuracy of the recipes based on user feedback. This makes it possible to continuously improve the accuracy of the generative AI's suggestions by utilizing user feedback.

[0120] The communication unit can further estimate the user's emotions and adjust the priority of communication based on the estimated user's emotions. For example, when the user is in an emergency situation, the communication unit can transmit important information with priority. When the user is relaxed, the communication unit can postpone non-urgent information. This makes it possible to provide information at an appropriate timing according to the user's emotions.

[0121] The suggestion unit can further add a function of suggesting recipes according to the user's ingredient preferences. For example, if the user likes a particular ingredient, the suggestion unit can suggest recipes that contain a lot of that ingredient. Also, if the user avoids a particular ingredient, the suggestion unit can suggest recipes that do not contain that ingredient. This makes it possible to provide recipes that meet the user's preferences.

[0122] The suggestion unit can further estimate the user's emotions and adjust the recipe suggestion method based on the estimated user's emotions. For example, if the user is tired, the suggestion unit can suggest easy recipes. Also, if the user is energetic, the suggestion unit can suggest challenging recipes. This makes it possible to provide a recipe suggestion method that corresponds to the user's emotions.

[0123] The sensor unit can further analyze the user's allergy information and issue a warning to users who have allergies. For example, the sensor unit collects ingredient data of ingredients and evaluates the allergen information. The sensor unit can also analyze the allergen information of ingredients taking into account the user's allergy information. This makes it possible to support a safe dietary lifestyle by analyzing allergen information and issuing warnings to users who have allergies.

[0124] The sensor unit can further estimate the user's emotions and adjust the ingredient analysis frequency based on the estimated user's emotions. For example, if the user is stressed, the sensor unit can reduce the ingredient analysis frequency to reduce the user's stress. On the other hand, if the user is relaxed, the sensor unit can increase the ingredient analysis frequency to provide more detailed information. This makes it possible to adjust the ingredient analysis frequency according to the user's emotions.

[0125] The process flow of the second embodiment will be briefly described below.

[0126] Step 1: The sensor unit analyzes the ingredients in the refrigerator. The sensor unit uses image analysis technology to recognize the ingredients in the refrigerator and identify their type and amount. It also uses ingredient analysis technology to evaluate the nutritional value and freshness of the ingredients, and uses weight measurement technology to measure the weight of the ingredients and manage inventory. Step 2: The suggestion unit uses the generation AI to suggest recipes based on the information analyzed by the sensor unit. The generation AI considers ingredient combinations and nutritional balance to generate recipes suited to the user. It also learns the user's preferences and past cooking history to suggest individually customized recipes and recipes according to the season and weather. Step 3: The reception unit receives user operations in natural language. It uses voice recognition technology to analyze the user's voice commands and executes the appropriate operations. It also supports text input and is compatible with multiple languages. Step 4: The evaluation unit evaluates the reliability of the information provided by the generation AI. It evaluates the accuracy and practicality of the recipes proposed by the generation AI, and evaluates reliability based on the latest information in collaboration with external databases. It also collects feedback from users and continuously improves the accuracy of the generation AI. Step 5: The communication unit provides a mechanism for communication between the sensor unit and the generation AI. Data is sent and received between the sensor unit and the generation AI using Wi-Fi and Bluetooth, and the latest information is obtained by linking with external databases via the Internet. It also enables linking with different home appliances, realizing seamless operation.

[0127] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0128] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0129] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements including the sensor unit, the suggestion unit, the reception unit, the evaluation unit, and the communication unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the sensor unit analyzes ingredients in the refrigerator using the camera 42 of the smart device 14, and identifies the type and amount of the ingredients by the specific processing unit 290 of the data processing device 12. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI proposes a recipe taking into consideration the combination of ingredients and nutritional balance. The reception unit is realized, for example, by the control unit 46A of the smart device 14, and analyzes the user's voice command using voice recognition technology. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the reliability of the information provided by the generation AI. The communication unit transmits and receives data between the sensor unit and the generation AI using, for example, the communication I / F 44 of the smart device 14 and the communication I / F 26 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0131] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0132] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0133] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] 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.

[0135] 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 the voice according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0137] 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 performed in a secure state.

[0138] Fig. 4 shows an example of 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.

[0139] 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.

[0140] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0141] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0142] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0143] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0144] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0145] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements including the sensor unit, the suggestion unit, the reception unit, the evaluation unit, and the communication 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 sensor unit analyzes ingredients in the refrigerator using the camera 42 of the smart glasses 214, and identifies the type and amount of ingredients by the specific processing unit 290 of the data processing device 12. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI proposes a recipe taking into account the combination of ingredients and nutritional balance. The reception unit is realized, for example, by the control unit 46A of the smart glasses 214, and analyzes the user's voice command using voice recognition technology. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the reliability of information provided by the generation AI. The communication unit transmits and receives data between the sensor unit and the generation AI using, for example, the communication I / F 44 of the smart glasses 214 and the communication I / F 26 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0147] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0148] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0149] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] 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.

[0151] 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 the voice according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0153] 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 performed in a secure state.

[0154] 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.

[0155] 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.

[0156] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0157] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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.

[0158] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0159] 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 voice indicating a user input for 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.

[0160] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0161] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements including the sensor unit, suggestion unit, reception unit, evaluation unit, and communication unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the sensor unit analyzes ingredients in the refrigerator using the camera 42 of the headset type terminal 314, and identifies the type and amount of ingredients by the specific processing unit 290 of the data processing device 12. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI proposes a recipe taking into consideration the combination of ingredients and nutritional balance. The reception unit is realized, for example, by the control unit 46A of the headset type terminal 314, and analyzes the user's voice command using voice recognition technology. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the reliability of information provided by the generation AI. The communication unit transmits and receives data between the sensor unit and the generation AI using, for example, the communication I / F 44 of the headset type terminal 314 and the communication I / F 26 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0163] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0164] 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.

[0165] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0166] 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.

[0167] 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 the voice according to instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0169] 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 performed in a secure state.

[0170] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0171] 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.

[0172] 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.

[0173] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0174] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0175] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0176] 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 a voice indicating a user input for 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.

[0177] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0178] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0179] Each of the multiple elements including the sensor unit, suggestion unit, reception unit, evaluation unit, and communication unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the sensor unit analyzes ingredients in the refrigerator using the camera 42 of the robot 414, and identifies the type and amount of ingredients by the specific processing unit 290 of the data processing device 12. The suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and the generation AI proposes a recipe taking into consideration the combination of ingredients and nutritional balance. The reception unit is realized, for example, by the control unit 46A of the robot 414, and analyzes the user's voice command using voice recognition technology. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the reliability of information provided by the generation AI. The communication unit transmits and receives data between the sensor unit and the generation AI using, for example, the communication I / F 44 of the robot 414 and the communication I / F 26 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0180] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0181] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0182] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0183] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0184] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0185] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0186] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0187] 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.

[0188] 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 Universal Serial Bus (USB) 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.

[0189] In addition, 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 upon request from the data processing device 12.

[0190] 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.

[0191] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0192] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0193] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0194] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0195] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0196] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0197] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0198] (Appendix 1) A sensor unit that analyzes ingredients in the refrigerator; a suggestion unit that suggests a recipe based on the information analyzed by the sensor unit; a reception unit for allowing a user to operate in natural language; An evaluation unit that evaluates the reliability of information provided by the generation AI; A communication unit for communication between the sensor unit and the generation AI. A system characterized by: (Appendix 2) The sensor unit includes: Analyzing ingredients in the refrigerator 2. The system of claim 1, (Appendix 3) The suggestion unit, Generative AI suggests recipes based on analysis results 2. The system of claim 1, (Appendix 4) The reception unit is Accepts user requests for natural language operations 2. The system of claim 1, (Appendix 5) The evaluation unit is Evaluate the reliability of information provided by generative AI 2. The system of claim 1, (Appendix 6) The communication unit is Provides a mechanism for communication between the sensor unit and the generation AI 2. The system of claim 1, (Appendix 7) The suggestion unit, Suggest appropriate temperature settings for air conditioners 2. The system of claim 1, (Appendix 8) The suggestion unit, Suggest appropriate lighting settings 2. The system of claim 1, (Appendix 9) The sensor unit includes: Estimate the user's emotions and adjust the frequency of ingredient analysis based on the estimated user emotions 2. The system of claim 1, (Appendix 10) The sensor unit includes: Add a feature to monitor the freshness of ingredients in real time and notify you when the freshness decreases 2. The system of claim 1, (Appendix 11) The sensor unit includes: Analyze the nutritional value of ingredients and suggest ingredients based on the user's health condition 2. The system of claim 1, (Appendix 12) The sensor unit includes: Infer user emotions and adjust the way analysis results are displayed based on the inferred user emotions 2. The system of claim 1, (Appendix 13) The sensor unit includes: Analyzes allergen information for ingredients and warns users with allergies 2. The system of claim 1, (Appendix 14) The sensor unit includes: Analyze the origin of ingredients and make suggestions to users based on their origin 2. The system of claim 1, (Appendix 15) The suggestion unit, Infer user emotions and adjust recipe suggestions based on the inferred user emotions 2. The system of claim 1, (Appendix 16) The suggestion unit, Analyzes the user's cooking history and suggests recipes based on their preferences 2. The system of claim 1, (Appendix 17) The suggestion unit, Add a feature to suggest recipes according to the season and weather 2. The system of claim 1, (Appendix 18) The suggestion unit, Infer user emotions and adjust the difficulty of recipes based on the estimated user emotions 2. The system of claim 1, (Appendix 19) The suggestion unit, When suggesting recipes, it also suggests ways to preserve ingredients. 2. The system of claim 1, (Appendix 20) The suggestion unit, Add a feature to suggest substitutes for ingredients when suggesting recipes 2. The system of claim 1, (Appendix 21) The reception unit is To estimate a user's emotion and adjust a display method of an operation interface based on the estimated user's emotion. 2. The system of claim 1, (Appendix 22) The reception unit is Analyze the user's past operation history and suggest the optimal operation method 2. The system of claim 1, (Appendix 23) The reception unit is Add a feature to learn the characteristics of the user's voice to improve the accuracy of voice recognition. 2. The system of claim 1, (Appendix 24) The reception unit is To estimate a user's emotion and simplify an operation procedure based on the estimated user's emotion. 2. The system of claim 1, (Appendix 25) The reception unit is Add visual feedback to the control interface 2. The system of claim 1, (Appendix 26) The reception unit is Adding haptic feedback to the control interface 2. The system of claim 1, (Appendix 27) The evaluation unit is Estimating user sentiment and adjusting criteria for evaluating the reliability of information based on the estimated user sentiment 2. The system of claim 1, (Appendix 28) The evaluation unit is Feedback is collected from the execution results of the proposed recipes to continuously improve reliability 2. The system of claim 1, (Appendix 29) The evaluation unit is Linking with external databases to evaluate reliability based on the latest information 2. The system of claim 1, (Appendix 30) The evaluation unit is Inferring user emotion and adjusting the way rating results are displayed based on the estimated user emotion 2. The system of claim 1, (Appendix 31) The evaluation unit is Evaluate the nutritional value of suggested recipes and provide health-conscious suggestions 2. The system of claim 1, (Appendix 32) The evaluation unit is Evaluate the cost of proposed recipes and provide economical suggestions 2. The system of claim 1, (Appendix 33) The communication unit is To estimate a user's emotion and adjust a communication priority based on the estimated user's emotion. 2. The system of claim 1, (Appendix 34) The communication unit is Strengthen communication security and add features to protect data 2. The system of claim 1, (Appendix 35) The communication unit is Optimize the speed of communication and enable real-time data exchange 2. The system of claim 1, (Appendix 36) The communication unit is To estimate a user's emotion and adjust a frequency of communication based on the estimated user's emotion. 2. The system of claim 1, (Appendix 37) The communication unit is Adding connectivity with different home appliances 2. The system of claim 1, (Appendix 38) The communication unit is Adding remote operation functionality via the Internet 2. The system of claim 1, [Explanation of symbols]

[0199] 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 sensor unit that analyzes ingredients in the refrigerator; a suggestion unit that suggests a recipe based on the information analyzed by the sensor unit; a reception unit for allowing a user to operate in natural language; An evaluation unit that evaluates the reliability of information provided by the generation AI; A communication unit for communication between the sensor unit and the generation AI. A system characterized by:

2. The suggestion unit, Generative AI suggests recipes based on analysis results 2. The system of claim 1 .

3. The evaluation unit is Evaluate the reliability of information provided by generative AI 2. The system of claim 1 .

4. The communication unit is Provide a mechanism for communication between the sensor unit and the generation AI 2. The system of claim 1 .

5. The suggestion unit, Suggest appropriate temperature settings for air conditioners 2. The system of claim 1 .

6. The suggestion unit, Suggest appropriate lighting settings 2. The system of claim 1 .

7. The sensor unit includes: Estimate the user's emotions and adjust the frequency of ingredient analysis based on the estimated user emotions 2. The system of claim 1 .

Images