system

Abstract

The system according to the embodiment aims to efficiently utilize ingredients in the refrigerator and automatically generate recipes that meet the user's requirements. [Solution] The system according to the embodiment includes a photographing unit, a discrimination unit, an input unit, a generation unit, a generation AI unit, and a provision unit. The photographing unit photographs ingredients. The discrimination unit discriminates ingredients from the photo taken by the photographing unit. The input unit inputs recipe conditions. The generation unit creates a prompt input sentence based on the conditions input by the input unit and the ingredients discriminated by the discrimination unit. The generation AI unit inputs the prompt input sentence generated by the generation unit to a generation AI to generate a recipe. The provision unit provides the recipe generated by the generation AI unit to the user.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making efficient use of ingredients in the refrigerator and automatically generating recipes that meet the user's requirements.

[0005] The system according to the embodiment aims to efficiently utilize ingredients in the refrigerator and automatically generate recipes that meet the user's requirements. [Means for solving the problem]

[0006] The system according to the embodiment includes a photographing unit, a discrimination unit, an input unit, a generation unit, a generation AI unit, and a provision unit. The photographing unit photographs ingredients. The discrimination unit discriminates ingredients from the photo taken by the photographing unit. The input unit inputs recipe conditions. The generation unit creates a prompt input sentence based on the conditions input by the input unit and the ingredients discriminated by the discrimination unit. The generation AI unit inputs the prompt input sentence generated by the generation unit to the generation AI to generate a recipe. The provision unit provides the recipe generated by the generation AI unit to the user. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently utilize ingredients in the refrigerator and automatically generate recipes that meet the user's requirements. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

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

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

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

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

[0028] (Example 1) A system according to an embodiment of the present invention is a smartphone app that photographs ingredients in a refrigerator and identifies them from the photograph. This smartphone app allows a user to photograph ingredients in the refrigerator and identify them from the photograph. Next, the user inputs recipe requirements. These requirements include calories, desired cooking time, desired cuisine, cooking skill level, whether to include suggestions (shopping orders) if ingredients are missing, and priority (taste, time, use of ingredients from the refrigerator, etc.). The app creates a prompt input sentence based on the input requirements and the identified ingredients and inputs it into a generation AI. The generation AI generates a recipe based on the input prompt and provides the result to the user via the app. If ingredients are missing, the generation AI queries the generation AI to determine whether substitute ingredients are available in the refrigerator and coordinates with online delivery to order the missing ingredients. Furthermore, the system provides a recipe list in order according to the priority of the requirements. For example, a user photographs ingredients in the refrigerator. The app then uses image recognition technology to identify ingredients from the photograph. For example, the user photographs vegetables, meat, and other items in the refrigerator, and the app automatically recognizes them. Next, the user inputs recipe requirements. Conditions include calories, desired cooking time, desired cuisine type, cook level, whether to include suggestions (shopping orders) if ingredients are missing, and priority (taste, time, use of ingredients from the refrigerator, etc.). For example, if a user wants "low-calorie Japanese food that can be made in 30 minutes," they enter these conditions into the app. The app creates a prompt input sentence based on the entered conditions and the identified ingredients. For example, it generates a prompt such as "Please tell me a low-calorie Japanese recipe that can be made in 30 minutes using ingredients in the refrigerator." The generated prompt input sentence is input into the generation AI. The generation AI generates a recipe based on the input prompt. For example, the generation AI generates "a low-calorie Japanese recipe that can be made in 30 minutes using ingredients in the refrigerator." The generated recipe is provided to the user via the app. The user can check the generated recipe through the app and start cooking. If an ingredient is missing, the user can query the generation AI to see if there are any substitute ingredients in the refrigerator. For example, the generation AI may suggest "ingredients that can be substituted using ingredients in the refrigerator."Furthermore, it also works with online delivery services to order missing ingredients. For example, the app can work with an online delivery service to automatically order missing ingredients. Finally, it provides a recipe list order based on the priority of the criteria. For example, if the user prioritizes "taste," the app will display recipes that emphasize "taste" at the top. This allows the smartphone app to efficiently manage the ingredients in the user's refrigerator and quickly provide recipes based on the user's desired criteria.

[0029] The smartphone app according to the embodiment includes a photographing unit, a discrimination unit, an input unit, a generation unit, a generation AI unit, and a provision unit. The photographing unit allows a user to photograph ingredients in a refrigerator. For example, the photographing unit can photograph ingredients using a smartphone camera. The photographing unit can also have a function to automatically adjust lighting conditions in the refrigerator to take optimal photos. For example, if the lighting in the refrigerator is dim, a flash can be used to take bright photos. The discrimination unit discriminates ingredients from photos taken by the photographing unit. For example, the discrimination unit discriminates ingredients from photos using image recognition technology. Image recognition technology includes deep learning and computer vision technology. The input unit allows a user to input recipe conditions. For example, the input unit supports text input, voice input, gesture input, and the like. The generation unit creates a prompt input sentence based on the conditions input by the input unit and the ingredients discriminated by the discrimination unit. For example, the generation unit automatically generates a prompt input sentence using a natural language processing algorithm. The generation AI unit inputs the prompt input sentence generated by the generation unit into a generation AI to generate a recipe. The generation AI includes text generation AI (e.g., LLM) and multimodal generation AI. The providing unit is a component that provides the recipe generated by the generation AI unit to the user. For example, the providing unit displays the recipe on the app. The providing unit may also have a function to estimate the user's emotions and adjust the way the recipe is displayed based on the estimated user emotions. This allows the smartphone app according to the embodiment to efficiently manage ingredients in the refrigerator and quickly provide recipes based on the user's desired conditions.

[0030] The smartphone app includes a suggestion unit that suggests specific substitute ingredients when an ingredient is missing. The suggestion unit is a component that suggests substitute ingredients when an ingredient is missing. For example, the suggestion unit queries the generation AI to suggest substitute ingredients in the refrigerator. The suggestion unit may also include an algorithm that selects substitute ingredients based on similarities in nutritional value and taste. For example, the suggestion unit allows the generation AI to suggest "ingredients that can be substituted using ingredients in the refrigerator." This allows the user to easily find substitute ingredients to make up for the missing ingredients. Some or all of the above-described processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit may cause the generation AI to suggest substitute ingredients.

[0031] The smartphone app includes an ordering unit that works in cooperation with online delivery to order missing ingredients. The ordering unit is a component that works in cooperation with online delivery to order missing ingredients. For example, the ordering unit works in cooperation with an online delivery service to automatically order missing ingredients. The ordering unit can use a delivery service designated by the user. For example, the ordering unit places an order for missing ingredients with the online delivery service selected by the user. This allows the user to quickly obtain the ingredients they need. Some or all of the above-described processing in the ordering unit may be performed using, for example, AI, or may be performed without using AI. For example, the ordering unit can have the generation AI place an order for the missing ingredients.

[0032] The smartphone app includes an order provider that provides an order for a recipe list according to the priority of conditions set by the user. The order provider is a component that provides an order for a recipe list according to the priority of conditions set by the user. For example, if the user prioritizes "taste," the order provider displays recipes that emphasize "taste" at the top. The order provider can also include an algorithm that determines the priority of recipes based on the user's preferences and health status. For example, if the user prioritizes "low calories," the order provider displays low-calorie recipes at the top. This allows the user to prioritize recipes that meet the user's desired conditions. Some or all of the above-described processing in the order provider may be performed using, for example, AI, or may be performed without using AI. For example, the order provider can have a generation AI determine the priority of recipes.

[0033] The discrimination unit can identify ingredients from photographs using image recognition technology. Image recognition technology includes deep learning and computer vision technology. For example, the discrimination unit can use deep learning to analyze the shape and color of ingredients and identify them. The discrimination unit can also use computer vision technology to extract the characteristics of ingredients and identify them. For example, the discrimination unit can improve discrimination accuracy by analyzing not only the shape and color of ingredients but also the text information on the packaging. In this way, the use of image recognition technology improves the accuracy of ingredient discrimination. Some or all of the above-mentioned processing in the discrimination unit may be performed using, for example, AI, or may be performed without using AI. For example, the discrimination unit can have a generation AI perform ingredient discrimination.

[0034] The generation unit may include an algorithm that automatically generates a prompt input sentence based on conditions entered by a user. The generation unit automatically generates the prompt input sentence using a natural language processing algorithm. For example, if a user requests "low-calorie Japanese food that can be made within 30 minutes," the generation unit generates a prompt such as "Please tell me a recipe for a low-calorie Japanese food that can be made within 30 minutes using ingredients in the refrigerator." The generation unit may also include an algorithm that generates a prompt based on conditions entered by a user. For example, the generation unit uses an algorithm that analyzes conditions entered by a user and generates an optimal prompt. This automatically generates a prompt input sentence based on conditions entered by a user, thereby improving the efficiency of recipe generation. Some or all of the above-described processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit may cause a generation AI to generate the prompt.

[0035] The photographing unit can automatically set appropriate photographing conditions, taking into account the temperature and humidity inside the refrigerator, when photographing. The photographing unit is equipped with sensors for measuring the temperature and humidity inside the refrigerator. For example, the photographing unit measures the temperature inside the refrigerator using a temperature sensor and the humidity inside the refrigerator using a humidity sensor. When the temperature inside the refrigerator is low, the photographing unit adjusts the exposure to take a clear photograph. When the humidity inside the refrigerator is high, the photographing unit can also clean the lens before photographing to prevent lens fogging. Furthermore, the photographing unit can automatically set the optimal white balance based on the temperature and humidity data. This allows clear photographs to be taken by automatically setting the optimal photographing conditions, taking into account the temperature and humidity inside the refrigerator. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can input temperature and humidity data into the generation AI and have the generation AI set the optimal photographing conditions.

[0036] When photographing, the photographing unit can identify the location of ingredients using shelf position information within the refrigerator. The photographing unit is equipped with a sensor for acquiring shelf position information within the refrigerator. For example, the photographing unit acquires shelf position information using a position sensor. The photographing unit prioritizes photographing ingredients on a specific shelf based on the shelf position information. The photographing unit can also automatically adjust the photographing range using the shelf position information. Furthermore, the photographing unit can identify the location of ingredients based on the shelf position information and efficiently photograph them. In this way, ingredients can be efficiently photographed by identifying the location of ingredients using shelf position information within the refrigerator. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can input shelf position information to a generation AI and cause the generation AI to identify the location of ingredients.

[0037] The photographing unit can automatically adjust the lighting conditions inside the refrigerator when photographing to take an optimal photograph. The photographing unit is equipped with a lighting control algorithm for adjusting the lighting conditions inside the refrigerator. For example, if the lighting inside the refrigerator is dim, the photographing unit uses a flash to take a bright photograph. If the lighting inside the refrigerator is too bright, the photographing unit can also adjust the exposure to achieve appropriate brightness. Furthermore, the photographing unit can automatically adjust the color temperature of the lighting to take a photograph with natural color tones. In this way, by automatically adjusting the lighting conditions inside the refrigerator, a photograph with optimal brightness can be taken. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can cause the generation AI to adjust the lighting conditions.

[0038] When photographing, the photographing unit can check the freshness of ingredients in cooperation with other devices (e.g., a temperature sensor) in the refrigerator. The photographing unit is equipped with a communication module for cooperation with other devices in the refrigerator. For example, the photographing unit prioritizes photographing fresh ingredients based on data from the temperature sensor. The photographing unit can also identify and photograph less fresh ingredients using data from the temperature sensor. Furthermore, the photographing unit can distinguish between fresh and less fresh ingredients based on data from the temperature sensor. This allows photographing ingredients while checking their freshness by cooperating with other devices in the refrigerator. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can input temperature sensor data into the generation AI and cause the generation AI to check the freshness of the ingredients.

[0039] The discrimination unit can improve discrimination accuracy by analyzing not only the shape and color of the food ingredient but also the text information written on the package during discrimination. The discrimination unit is equipped with image recognition technology for analyzing the shape and color of the food ingredient. For example, the discrimination unit may use deep learning to analyze the shape and color of the food ingredient and identify the food ingredient. The discrimination unit may also be equipped with OCR technology for analyzing the text information written on the package. For example, the discrimination unit may use OCR technology to analyze the text information on the package and identify the brand and type of the food ingredient. Furthermore, the discrimination unit can comprehensively analyze the shape, color, and text information to improve discrimination accuracy. This improves discrimination accuracy by analyzing not only the shape and color of the food ingredient but also the text information on the package. Some or all of the above-mentioned processing in the discrimination unit may be performed using, for example, AI, or may be performed without using AI. For example, the discrimination unit may have a generation AI perform food ingredient discrimination.

[0040] The discrimination unit can optimize the discrimination algorithm by referring to past discrimination history during discrimination. The discrimination unit includes a database for storing past discrimination history. For example, the discrimination unit learns the discrimination algorithm based on the past discrimination history and improves accuracy. The discrimination unit can also extract discrimination patterns for specific ingredients from the past discrimination history and reflect them in the algorithm. Furthermore, the discrimination unit can analyze the discrimination history, identify the cause of misdiscrimination, and improve the algorithm. In this way, by referring to the past discrimination history, the discrimination algorithm is optimized and accuracy is improved. Some or all of the above-mentioned processing in the discrimination unit may be performed using, for example, AI, or may be performed without using AI. For example, the discrimination unit can input past discrimination history into the generation AI and have the generation AI optimize the algorithm.

[0041] The discrimination unit can improve discrimination accuracy by taking into account the relationship with other ingredients in the refrigerator when discriminating. The discrimination unit is equipped with an algorithm for analyzing the relationship with other ingredients in the refrigerator. For example, the discrimination unit analyzes the positional relationship of ingredients based on co-occurrence relationships to improve discrimination accuracy. The discrimination unit can also correct the discrimination result by taking into account the type and amount of other ingredients. Furthermore, the discrimination unit can analyze the interrelationships between ingredients to prevent erroneous discrimination. In this way, by taking into account the relationship with other ingredients in the refrigerator, discrimination accuracy is improved. Some or all of the above-mentioned processing in the discrimination unit may be performed using, for example, AI, or may be performed without using AI. For example, the discrimination unit can cause a generation AI to analyze the relationship between ingredients.

[0042] During discrimination, the discrimination unit can complement the discrimination result by referring to the shelf life information of the ingredients. The discrimination unit includes a database for acquiring the shelf life information of the ingredients. For example, the discrimination unit acquires the shelf life information by scanning a barcode and reflects it in the discrimination result. The discrimination unit can also identify ingredients whose shelf life is approaching and reflect this in the discrimination result. Furthermore, the discrimination unit can also use the shelf life information to reflect the priority of ingredient use in the discrimination result. In this way, by referring to the shelf life information of the ingredients, the discrimination result is complemented and accuracy is improved. Some or all of the above-mentioned processing in the discrimination unit may be performed, for example, using AI, or may be performed without using AI. For example, the discrimination unit can cause the generation AI to acquire and analyze the shelf life information.

[0043] The input unit can present optimal input candidates by referring to the user's past input history when inputting data. The input unit includes a database for storing the user's past input history. For example, the input unit presents optimal input candidates based on conditions previously input by the user. The input unit can also prioritize displaying frequently used conditions from the past input history. Furthermore, the input unit can learn the user's input patterns and automatically suggest optimal input candidates. This allows optimal input candidates to be presented by referring to the user's past input history, improving input efficiency. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's past input history to a generation AI and cause the generation AI to present optimal input candidates.

[0044] The input unit can support voice input and gesture input at the time of input, thereby diversifying input methods. The input unit is equipped with recognition technology to support voice input and gesture input. For example, the input unit can use voice recognition technology to allow a user to input conditions simply by speaking. The input unit can also use gesture recognition technology to allow a user to input conditions with hand movements. Furthermore, the input unit can combine voice input and gesture input to provide a more intuitive input method. Thus, by supporting voice input and gesture input, the user can input conditions in a variety of ways. Some or all of the above-described processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can cause a generation AI to recognize voice and gestures.

[0045] The input unit can provide an optimal input interface by taking into account the user's device information at the time of input. The input unit includes a communication module for acquiring the user's device information. For example, if the user is using a smartphone, the input unit can provide an input interface tailored to the screen size. Furthermore, if the user is using a tablet, the input unit can also provide an input interface optimized for a large screen. Furthermore, if the user is using a smartwatch, the input unit can also provide a simple, highly visible input interface. This allows the optimal input interface to be provided by taking into account the user's device information. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input device information to a generation AI and cause the generation AI to provide an optimal input interface.

[0046] The input unit can suggest optimal recipe conditions by referring to the user's schedule information at the time of input. The input unit includes a communication module for acquiring the user's schedule information. For example, the input unit acquires schedule information from a calendar app or a schedule management system and suggests optimal recipe conditions. The input unit can also suggest recipe conditions that match cooking times based on the user's schedule information. Furthermore, the input unit can also suggest recipe conditions related to specific events from the user's schedule information. This makes it possible to suggest optimal recipe conditions by referring to the user's schedule information. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input schedule information to the generation AI and cause the generation AI to suggest optimal recipe conditions.

[0047] The generation unit can apply an optimal prompt generation algorithm by referring to past generation history during generation. The generation unit includes a database for storing past generation history. For example, the generation unit selects an optimal prompt generation algorithm based on the past generation history. The generation unit can also prioritize generating frequently used prompts from the past generation history. Furthermore, the generation unit can analyze the generation history and optimize the prompt generation algorithm. By referring to the past generation history, the optimal prompt generation algorithm can be applied and accuracy can be improved. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input past generation history into the generation AI and cause the generation AI to optimize the algorithm.

[0048] The generation unit can generate prompts taking into account nutritional information of ingredients during generation. The generation unit includes a database for acquiring nutritional information of ingredients. For example, the generation unit acquires nutritional information from a nutrition database or a food composition table and reflects the information in the prompt. The generation unit can also generate prompts that suggest healthy recipes based on the nutritional information of ingredients. Furthermore, the generation unit can also generate prompts that suggest balanced meals taking into account the nutritional information. In this way, prompts that suggest healthy recipes can be generated by taking into account the nutritional information of ingredients. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input nutritional information to the generation AI and cause the generation AI to generate a prompt.

[0049] The generation unit can generate optimal prompts by referring to the user's meal history during generation. The generation unit includes a database for storing the user's meal history. For example, the generation unit obtains the meal history from a meal recording app or database and reflects it in the prompt. The generation unit can also generate optimal prompts based on the user's past meal history. Furthermore, the generation unit can generate prompts that prioritize frequently used ingredients from the meal history. This makes it possible to generate optimal prompts by referring to the user's meal history and suggest recipes that match the user's preferences. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the meal history into the generation AI and cause the generation AI to generate prompts.

[0050] The generation unit can generate prompts taking into account the user's health condition information when generating the prompts. The generation unit includes a database for acquiring the user's health condition information. For example, the generation unit acquires health condition information from a health management app or medical data and reflects the health condition information in the prompts. The generation unit can also generate prompts that suggest healthy recipes based on the user's health condition information. Furthermore, the generation unit can also generate prompts that emphasize specific nutrients by taking into account the health condition information. In this way, prompts that suggest healthy recipes can be generated by taking into account the user's health condition information. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input health condition information to the generation AI and cause the generation AI to generate the prompts.

[0051] During generation, the generation AI unit can apply an optimal recipe generation algorithm by referring to past generation history. The generation AI unit has a database for storing past generation history. For example, the generation AI unit selects an optimal recipe generation algorithm based on the past generation history. The generation AI unit can also prioritize the generation of frequently used recipes from the past generation history. Furthermore, the generation AI unit can analyze the generation history and optimize the recipe generation algorithm. This allows the optimal recipe generation algorithm to be applied by referring to the past generation history, improving accuracy. Some or all of the above-mentioned processing in the generation AI unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation AI unit can input past generation history into the generation AI and cause the generation AI to optimize the algorithm.

[0052] The generation AI unit can generate a recipe taking into account the nutritional information of ingredients. The generation AI unit has a database for acquiring nutritional information of ingredients. For example, the generation AI unit acquires nutritional information from a nutrition database or a food composition table and reflects it in the recipe. The generation AI unit can also generate healthy recipes based on the nutritional information of ingredients. Furthermore, the generation AI unit can generate recipes that suggest balanced meals by taking into account the nutritional information. In this way, healthy recipes can be generated by taking into account the nutritional information of ingredients. Some or all of the above-mentioned processing in the generation AI unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation AI unit can input nutritional information to the generation AI and cause the generation AI to generate a recipe.

[0053] The generation AI unit can generate an optimal recipe by referring to the user's meal history during generation. The generation AI unit has a database for storing the user's meal history. For example, the generation AI unit obtains the meal history from a meal recording app or database and reflects it in the recipe. The generation AI unit can also generate an optimal recipe based on the user's past meal history. Furthermore, the generation AI unit can generate recipes that prioritize frequently used ingredients from the meal history. This makes it possible to generate optimal recipes by referring to the user's meal history and suggest recipes that suit the user's preferences. Some or all of the above-mentioned processing in the generation AI unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation AI unit can input the meal history into the generation AI and have the generation AI generate a recipe.

[0054] The generation AI unit can generate a recipe taking into account the user's health condition information. The generation AI unit has a database for acquiring the user's health condition information. For example, the generation AI unit acquires health condition information from a health management app or medical data and reflects the information in the recipe. The generation AI unit can also generate healthy recipes based on the user's health condition information. Furthermore, the generation AI unit can generate recipes that emphasize specific nutrients by taking into account the health condition information. In this way, healthy recipes can be generated by taking into account the user's health condition information. Some or all of the above-mentioned processing in the generation AI unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation AI unit can input health condition information to the generation AI and cause the generation AI to generate a recipe.

[0055] When providing the recipe, the providing unit can select the optimal recipe display method by referring to the user's past usage history. The providing unit includes a database for storing the user's past usage history. For example, the providing unit selects the optimal recipe display method based on the past usage history. The providing unit can also prioritize and provide frequently used display methods based on the past usage history. Furthermore, the providing unit can analyze the usage history and optimize the recipe display method. This allows the optimal recipe display method to be selected by referring to the user's past usage history, enabling a display that is easy for the user to use. Some or all of the above-described processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the past usage history into the generation AI and cause the generation AI to select the optimal display method.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] When taking a photograph, the photographing unit can automatically set appropriate photographing conditions, taking into account the temperature and humidity inside the refrigerator. For example, the photographing unit measures the temperature inside the refrigerator using a temperature sensor and the humidity inside the refrigerator using a humidity sensor. When the temperature inside the refrigerator is low, the photographing unit adjusts the exposure to take a clear photograph. When the humidity inside the refrigerator is high, the photographing unit can also clean the lens before taking a photograph to prevent lens fogging. Furthermore, the photographing unit can automatically set the optimal white balance based on the temperature and humidity data. This allows clear photographs to be taken by automatically setting the optimal photographing conditions, taking into account the temperature and humidity inside the refrigerator. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can input temperature and humidity data into the generation AI and have the generation AI set the optimal photographing conditions.

[0058] When photographing, the photographing unit can identify the location of ingredients using shelf position information within the refrigerator. For example, the photographing unit acquires shelf position information using a position sensor. The photographing unit prioritizes photographing ingredients on a specific shelf based on the shelf position information. The photographing unit can also automatically adjust the photographing range using the shelf position information. Furthermore, the photographing unit can identify the location of ingredients based on the shelf position information and efficiently photograph them. In this way, ingredients can be efficiently photographed by identifying the location of ingredients using shelf position information within the refrigerator. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can input shelf position information to the generation AI and cause the generation AI to identify the location of ingredients.

[0059] During discrimination, the discrimination unit can analyze not only the shape and color of the food ingredient but also the text information written on the package to improve discrimination accuracy. For example, the discrimination unit uses deep learning to analyze the shape and color of the food ingredient and identify the food ingredient. The discrimination unit can also be equipped with OCR technology for analyzing the text information written on the package. For example, the discrimination unit uses OCR technology to analyze the text information on the package and identify the brand and type of the food ingredient. Furthermore, the discrimination unit can comprehensively analyze the shape, color, and text information to improve discrimination accuracy. In this way, by analyzing not only the shape and color of the food ingredient but also the text information on the package, discrimination accuracy is improved. Some or all of the above-mentioned processing in the discrimination unit may be performed using, for example, AI, or may be performed without using AI. For example, the discrimination unit can have a generation AI perform food ingredient discrimination.

[0060] During input, the input unit can present optimal input candidates by referring to the user's past input history. For example, the input unit presents optimal input candidates based on conditions previously input by the user. The input unit can also prioritize displaying frequently used conditions from the past input history. Furthermore, the input unit can learn the user's input patterns and automatically suggest optimal input candidates. This allows optimal input candidates to be presented by referring to the user's past input history, improving input efficiency. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the past input history to a generation AI and cause the generation AI to present optimal input candidates.

[0061] The generation unit can generate prompts taking into account the user's health condition information. For example, the generation unit acquires health condition information from a health management app or medical data and reflects the information in the prompt. The generation unit can also generate prompts that suggest healthy recipes based on the user's health condition information. Furthermore, the generation unit can generate prompts that emphasize specific nutrients taking into account the health condition information. In this way, a prompt that suggests healthy recipes can be generated by taking into account the user's health condition information. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input health condition information to the generation AI and cause the generation AI to generate a prompt.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The camera unit is a component that allows the user to take pictures of ingredients in the refrigerator. For example, the camera unit can take pictures of ingredients using a smartphone camera. The camera unit can also have a function to automatically adjust the lighting conditions inside the refrigerator to take optimal photos. For example, if the lighting inside the refrigerator is dim, the flash can be used to take bright photos. Step 2: The discrimination unit is the part that discriminates ingredients from the photos taken by the photographing unit. For example, the discrimination unit discriminates ingredients from the photos using image recognition technology. Image recognition technology includes deep learning and computer vision technology. Step 3: The input unit is a section where the user inputs recipe conditions. For example, the input unit supports text input, voice input, gesture input, etc. Step 4: The generator creates a prompt input sentence based on the conditions entered by the input unit and the ingredients identified by the discriminator. For example, the generator automatically generates the prompt input sentence using a natural language processing algorithm. Step 5: The generation AI unit inputs the prompt input sentence generated by the generation unit into the generation AI and generates a recipe. The generation AI includes text generation AI (e.g., LLM) and multimodal generation AI. Step 6: The providing unit is a component that provides the recipe generated by the generation AI unit to the user. For example, the providing unit displays the recipe on an app. The providing unit may also have a function to estimate the user's emotions and adjust the way the recipe is displayed based on the estimated user emotions.

[0064] (Example 2) A system according to an embodiment of the present invention is a smartphone app that photographs ingredients in a refrigerator and identifies them from the photograph. This smartphone app allows a user to photograph ingredients in the refrigerator and identify them from the photograph. Next, the user inputs recipe requirements. These requirements include calories, desired cooking time, desired cuisine, cooking skill level, whether to include suggestions (shopping orders) if ingredients are missing, and priority (taste, time, use of ingredients from the refrigerator, etc.). The app creates a prompt input sentence based on the input requirements and the identified ingredients and inputs it into a generation AI. The generation AI generates a recipe based on the input prompt and provides the result to the user via the app. If ingredients are missing, the generation AI queries the generation AI to determine whether substitute ingredients are available in the refrigerator and coordinates with online delivery to order the missing ingredients. Furthermore, the system provides a recipe list in order according to the priority of the requirements. For example, a user photographs ingredients in the refrigerator. The app then uses image recognition technology to identify ingredients from the photograph. For example, the user photographs vegetables, meat, and other items in the refrigerator, and the app automatically recognizes them. Next, the user inputs recipe requirements. Conditions include calories, desired cooking time, desired cuisine type, cook level, whether to include suggestions (shopping orders) if ingredients are missing, and priority (taste, time, use of ingredients from the refrigerator, etc.). For example, if a user wants "low-calorie Japanese food that can be made in 30 minutes," they enter these conditions into the app. The app creates a prompt input sentence based on the entered conditions and the identified ingredients. For example, it generates a prompt such as "Please tell me a low-calorie Japanese recipe that can be made in 30 minutes using ingredients in the refrigerator." The generated prompt input sentence is input into the generation AI. The generation AI generates a recipe based on the input prompt. For example, the generation AI generates "a low-calorie Japanese recipe that can be made in 30 minutes using ingredients in the refrigerator." The generated recipe is provided to the user via the app. The user can check the generated recipe through the app and start cooking. If an ingredient is missing, the user can query the generation AI to see if there are any substitute ingredients in the refrigerator. For example, the generation AI may suggest "ingredients that can be substituted using ingredients in the refrigerator."Furthermore, it also works with online delivery services to order missing ingredients. For example, the app can work with an online delivery service to automatically order missing ingredients. Finally, it provides a recipe list order based on the priority of the criteria. For example, if the user prioritizes "taste," the app will display recipes that emphasize "taste" at the top. This allows the smartphone app to efficiently manage the ingredients in the user's refrigerator and quickly provide recipes based on the user's desired criteria.

[0065] The smartphone app according to the embodiment includes a photographing unit, a discrimination unit, an input unit, a generation unit, a generation AI unit, and a provision unit. The photographing unit allows a user to photograph ingredients in a refrigerator. For example, the photographing unit can photograph ingredients using a smartphone camera. The photographing unit can also have a function to automatically adjust lighting conditions in the refrigerator to take optimal photos. For example, if the lighting in the refrigerator is dim, a flash can be used to take bright photos. The discrimination unit discriminates ingredients from photos taken by the photographing unit. For example, the discrimination unit discriminates ingredients from photos using image recognition technology. Image recognition technology includes deep learning and computer vision technology. The input unit allows a user to input recipe conditions. For example, the input unit supports text input, voice input, gesture input, and the like. The generation unit creates a prompt input sentence based on the conditions input by the input unit and the ingredients discriminated by the discrimination unit. For example, the generation unit automatically generates a prompt input sentence using a natural language processing algorithm. The generation AI unit inputs the prompt input sentence generated by the generation unit into a generation AI to generate a recipe. The generation AI includes text generation AI (e.g., LLM) and multimodal generation AI. The providing unit is a component that provides the recipe generated by the generation AI unit to the user. For example, the providing unit displays the recipe on the app. The providing unit may also have a function to estimate the user's emotions and adjust the way the recipe is displayed based on the estimated user emotions. This allows the smartphone app according to the embodiment to efficiently manage ingredients in the refrigerator and quickly provide recipes based on the user's desired conditions.

[0066] The smartphone app includes a suggestion unit that suggests specific substitute ingredients when an ingredient is missing. The suggestion unit is a component that suggests substitute ingredients when an ingredient is missing. For example, the suggestion unit queries the generation AI to suggest substitute ingredients in the refrigerator. The suggestion unit may also include an algorithm that selects substitute ingredients based on similarities in nutritional value and taste. For example, the suggestion unit allows the generation AI to suggest "ingredients that can be substituted using ingredients in the refrigerator." This allows the user to easily find substitute ingredients to make up for the missing ingredients. Some or all of the above-described processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit may cause the generation AI to suggest substitute ingredients.

[0067] The smartphone app includes an ordering unit that works in cooperation with online delivery to order missing ingredients. The ordering unit is a component that works in cooperation with online delivery to order missing ingredients. For example, the ordering unit works in cooperation with an online delivery service to automatically order missing ingredients. The ordering unit can use a delivery service designated by the user. For example, the ordering unit places an order for missing ingredients with the online delivery service selected by the user. This allows the user to quickly obtain the ingredients they need. Some or all of the above-described processing in the ordering unit may be performed using, for example, AI, or may be performed without using AI. For example, the ordering unit can have the generation AI place an order for the missing ingredients.

[0068] The smartphone app includes an order provider that provides an order for a recipe list according to the priority of conditions set by the user. The order provider is a component that provides an order for a recipe list according to the priority of conditions set by the user. For example, if the user prioritizes "taste," the order provider displays recipes that emphasize "taste" at the top. The order provider can also include an algorithm that determines the priority of recipes based on the user's preferences and health status. For example, if the user prioritizes "low calories," the order provider displays low-calorie recipes at the top. This allows the user to prioritize recipes that meet the user's desired conditions. Some or all of the above-described processing in the order provider may be performed using, for example, AI, or may be performed without using AI. For example, the order provider can have a generation AI determine the priority of recipes.

[0069] The discrimination unit can identify ingredients from photographs using image recognition technology. Image recognition technology includes deep learning and computer vision technology. For example, the discrimination unit can use deep learning to analyze the shape and color of ingredients and identify them. The discrimination unit can also use computer vision technology to extract the characteristics of ingredients and identify them. For example, the discrimination unit can improve discrimination accuracy by analyzing not only the shape and color of ingredients but also the text information on the packaging. In this way, the use of image recognition technology improves the accuracy of ingredient discrimination. Some or all of the above-mentioned processing in the discrimination unit may be performed using, for example, AI, or may be performed without using AI. For example, the discrimination unit can have a generation AI perform ingredient discrimination.

[0070] The generation unit may include an algorithm that automatically generates a prompt input sentence based on conditions entered by a user. The generation unit automatically generates the prompt input sentence using a natural language processing algorithm. For example, if a user requests "low-calorie Japanese food that can be made within 30 minutes," the generation unit generates a prompt such as "Please tell me a recipe for a low-calorie Japanese food that can be made within 30 minutes using ingredients in the refrigerator." The generation unit may also include an algorithm that generates a prompt based on conditions entered by a user. For example, the generation unit uses an algorithm that analyzes conditions entered by a user and generates an optimal prompt. This automatically generates a prompt input sentence based on conditions entered by a user, thereby improving the efficiency of recipe generation. Some or all of the above-described processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit may cause a generation AI to generate the prompt.

[0071] The photographing unit can estimate the user's emotions and adjust the timing of photographing based on the estimated user's emotions. The photographing unit is equipped with an emotion estimation algorithm for estimating the user's emotions. For example, the photographing unit estimates the user's emotions using facial expression recognition technology. The photographing unit takes photographs at a natural timing when the user is relaxed. The photographing unit can also take photographs quickly when the user is in a hurry. Furthermore, when the user is excited, the photographing unit can take continuous photographs and select the optimal photo. This allows the ingredients to be photographed at the optimal timing by adjusting the photographing timing according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the photographing unit may be performed using AI, for example, or without AI. For example, the photographing unit can cause the generation AI to estimate the user's emotions.

[0072] The photographing unit can automatically set appropriate photographing conditions, taking into account the temperature and humidity inside the refrigerator, when photographing. The photographing unit is equipped with sensors for measuring the temperature and humidity inside the refrigerator. For example, the photographing unit measures the temperature inside the refrigerator using a temperature sensor and the humidity inside the refrigerator using a humidity sensor. When the temperature inside the refrigerator is low, the photographing unit adjusts the exposure to take a clear photograph. When the humidity inside the refrigerator is high, the photographing unit can also clean the lens before photographing to prevent lens fogging. Furthermore, the photographing unit can automatically set the optimal white balance based on the temperature and humidity data. This allows clear photographs to be taken by automatically setting the optimal photographing conditions, taking into account the temperature and humidity inside the refrigerator. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can input temperature and humidity data into the generation AI and have the generation AI set the optimal photographing conditions.

[0073] When photographing, the photographing unit can identify the location of ingredients using shelf position information within the refrigerator. The photographing unit is equipped with a sensor for acquiring shelf position information within the refrigerator. For example, the photographing unit acquires shelf position information using a position sensor. The photographing unit prioritizes photographing ingredients on a specific shelf based on the shelf position information. The photographing unit can also automatically adjust the photographing range using the shelf position information. Furthermore, the photographing unit can identify the location of ingredients based on the shelf position information and efficiently photograph them. In this way, ingredients can be efficiently photographed by identifying the location of ingredients using shelf position information within the refrigerator. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can input shelf position information to a generation AI and cause the generation AI to identify the location of ingredients.

[0074] The photographing unit can estimate the user's emotions and prioritize the ingredients to be photographed based on the estimated user emotions. The photographing unit is equipped with an emotion estimation algorithm for estimating the user's emotions. For example, the photographing unit estimates the user's emotions using facial expression recognition technology. When the user is relaxed, the photographing unit photographs all ingredients in the refrigerator evenly. When the user is in a hurry, the photographing unit can prioritize photographing ingredients that are used frequently. When the user is excited, the photographing unit can focus on photographing specific ingredients. This allows the priority of ingredients to be photographed according to the user's emotions, thereby enabling ingredients that meet the user's needs to be photographed preferentially. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the photographing unit may be performed using AI, for example, or without AI. For example, the photographing unit can cause the generation AI to estimate the user's emotions.

[0075] The photographing unit can automatically adjust the lighting conditions inside the refrigerator when photographing to take an optimal photograph. The photographing unit is equipped with a lighting control algorithm for adjusting the lighting conditions inside the refrigerator. For example, if the lighting inside the refrigerator is dim, the photographing unit uses a flash to take a bright photograph. If the lighting inside the refrigerator is too bright, the photographing unit can also adjust the exposure to achieve appropriate brightness. Furthermore, the photographing unit can automatically adjust the color temperature of the lighting to take a photograph with natural color tones. In this way, by automatically adjusting the lighting conditions inside the refrigerator, a photograph with optimal brightness can be taken. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can cause the generation AI to adjust the lighting conditions.

[0076] When photographing, the photographing unit can check the freshness of ingredients in cooperation with other devices (e.g., a temperature sensor) in the refrigerator. The photographing unit is equipped with a communication module for cooperation with other devices in the refrigerator. For example, the photographing unit prioritizes photographing fresh ingredients based on data from the temperature sensor. The photographing unit can also identify and photograph less fresh ingredients using data from the temperature sensor. Furthermore, the photographing unit can distinguish between fresh and less fresh ingredients based on data from the temperature sensor. This allows photographing ingredients while checking their freshness by cooperating with other devices in the refrigerator. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can input temperature sensor data into the generation AI and cause the generation AI to check the freshness of the ingredients.

[0077] The discrimination unit can estimate the user's emotion and adjust the display method of the discrimination result based on the estimated user's emotion. The discrimination unit includes an emotion estimation algorithm for estimating the user's emotion. For example, the discrimination unit estimates the user's emotion using facial expression recognition technology. The discrimination unit displays a detailed discrimination result when the user is relaxed. The discrimination unit can also display a concise discrimination result when the user is in a hurry. Furthermore, the discrimination unit can adopt a visually appealing display method when the user is excited. This allows for adjusting the display method of the discrimination result according to the user's emotion, thereby enabling a display that is easy for the user to view. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the discrimination unit may be performed using AI, for example, or without AI. For example, the discrimination unit can cause the generation AI to estimate the user's emotion.

[0078] The discrimination unit can improve discrimination accuracy by analyzing not only the shape and color of the food ingredient but also the text information written on the package during discrimination. The discrimination unit is equipped with image recognition technology for analyzing the shape and color of the food ingredient. For example, the discrimination unit may use deep learning to analyze the shape and color of the food ingredient and identify the food ingredient. The discrimination unit may also be equipped with OCR technology for analyzing the text information written on the package. For example, the discrimination unit may use OCR technology to analyze the text information on the package and identify the brand and type of the food ingredient. Furthermore, the discrimination unit can comprehensively analyze the shape, color, and text information to improve discrimination accuracy. This improves discrimination accuracy by analyzing not only the shape and color of the food ingredient but also the text information on the package. Some or all of the above-mentioned processing in the discrimination unit may be performed using, for example, AI, or may be performed without using AI. For example, the discrimination unit may have a generation AI perform food ingredient discrimination.

[0079] The discrimination unit can optimize the discrimination algorithm by referring to past discrimination history during discrimination. The discrimination unit includes a database for storing past discrimination history. For example, the discrimination unit learns the discrimination algorithm based on the past discrimination history and improves accuracy. The discrimination unit can also extract discrimination patterns for specific ingredients from the past discrimination history and reflect them in the algorithm. Furthermore, the discrimination unit can analyze the discrimination history, identify the cause of misdiscrimination, and improve the algorithm. In this way, by referring to the past discrimination history, the discrimination algorithm is optimized and accuracy is improved. Some or all of the above-mentioned processing in the discrimination unit may be performed using, for example, AI, or may be performed without using AI. For example, the discrimination unit can input past discrimination history into the generation AI and have the generation AI optimize the algorithm.

[0080] The discrimination unit can estimate the user's emotion and prioritize the discrimination results based on the estimated user's emotion. The discrimination unit includes an emotion estimation algorithm for estimating the user's emotion. For example, the discrimination unit estimates the user's emotion using facial expression recognition technology. The discrimination unit displays all discrimination results evenly when the user is relaxed. Furthermore, the discrimination unit can prioritize the display of discrimination results for important ingredients when the user is in a hurry. Furthermore, the discrimination unit can highlight the display of discrimination results for specific ingredients when the user is excited. Thus, by prioritizing the discrimination results according to the user's emotion, important information can be displayed preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the discrimination unit may be performed using AI, or may be performed without AI. For example, the discrimination unit can cause the generation AI to estimate the user's emotion.

[0081] The discrimination unit can improve discrimination accuracy by taking into account the relationship with other ingredients in the refrigerator when discriminating. The discrimination unit is equipped with an algorithm for analyzing the relationship with other ingredients in the refrigerator. For example, the discrimination unit analyzes the positional relationship of ingredients based on co-occurrence relationships to improve discrimination accuracy. The discrimination unit can also correct the discrimination result by taking into account the type and amount of other ingredients. Furthermore, the discrimination unit can analyze the interrelationships between ingredients to prevent erroneous discrimination. In this way, by taking into account the relationship with other ingredients in the refrigerator, discrimination accuracy is improved. Some or all of the above-mentioned processing in the discrimination unit may be performed using, for example, AI, or may be performed without using AI. For example, the discrimination unit can cause a generation AI to analyze the relationship between ingredients.

[0082] During discrimination, the discrimination unit can complement the discrimination result by referring to the shelf life information of the ingredients. The discrimination unit includes a database for acquiring the shelf life information of the ingredients. For example, the discrimination unit acquires the shelf life information by scanning a barcode and reflects it in the discrimination result. The discrimination unit can also identify ingredients whose shelf life is approaching and reflect this in the discrimination result. Furthermore, the discrimination unit can also use the shelf life information to reflect the priority of ingredient use in the discrimination result. In this way, by referring to the shelf life information of the ingredients, the discrimination result is complemented and accuracy is improved. Some or all of the above-mentioned processing in the discrimination unit may be performed, for example, using AI, or may be performed without using AI. For example, the discrimination unit can cause the generation AI to acquire and analyze the shelf life information.

[0083] The input unit can estimate a user's emotion and adjust the display method of the input interface based on the estimated user emotion. The input unit includes an emotion estimation algorithm for estimating the user's emotion. For example, the input unit estimates the user's emotion using facial expression recognition technology. The input unit provides detailed input options when the user is relaxed. The input unit can also provide a simple input interface when the user is in a hurry. Furthermore, the input unit can also provide a visually appealing input interface when the user is excited. This allows the display method of the input interface to be adjusted according to the user's emotion, thereby providing an interface that is easy for the user to use. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can cause the generation AI to estimate the user's emotion.

[0084] The input unit can present optimal input candidates by referring to the user's past input history when inputting data. The input unit includes a database for storing the user's past input history. For example, the input unit presents optimal input candidates based on conditions previously input by the user. The input unit can also prioritize displaying frequently used conditions from the past input history. Furthermore, the input unit can learn the user's input patterns and automatically suggest optimal input candidates. This allows optimal input candidates to be presented by referring to the user's past input history, improving input efficiency. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's past input history to a generation AI and cause the generation AI to present optimal input candidates.

[0085] The input unit can support voice input and gesture input at the time of input, thereby diversifying input methods. The input unit is equipped with recognition technology to support voice input and gesture input. For example, the input unit can use voice recognition technology to allow a user to input conditions simply by speaking. The input unit can also use gesture recognition technology to allow a user to input conditions with hand movements. Furthermore, the input unit can combine voice input and gesture input to provide a more intuitive input method. Thus, by supporting voice input and gesture input, the user can input conditions in a variety of ways. Some or all of the above-described processing in the input unit may be performed using AI, for example, or may be performed without using AI. For example, the input unit can cause a generation AI to recognize voice and gestures.

[0086] The input unit can estimate the user's emotions and prioritize input items based on the estimated user emotions. The input unit includes an emotion estimation algorithm for estimating the user's emotions. For example, the input unit estimates the user's emotions using facial expression recognition technology. The input unit displays all input items evenly when the user is relaxed. The input unit can also prioritize important input items when the user is in a hurry. Furthermore, the input unit can highlight specific input items when the user is excited. This allows important items to be input preferentially by prioritizing input items according to the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the input unit may be performed using AI, or may be performed without AI. For example, the input unit can cause the generation AI to estimate the user's emotions.

[0087] The input unit can provide an optimal input interface by taking into account the user's device information at the time of input. The input unit includes a communication module for acquiring the user's device information. For example, if the user is using a smartphone, the input unit can provide an input interface tailored to the screen size. Furthermore, if the user is using a tablet, the input unit can also provide an input interface optimized for a large screen. Furthermore, if the user is using a smartwatch, the input unit can also provide a simple, highly visible input interface. This allows the optimal input interface to be provided by taking into account the user's device information. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input device information to a generation AI and cause the generation AI to provide an optimal input interface.

[0088] The input unit can suggest optimal recipe conditions by referring to the user's schedule information at the time of input. The input unit includes a communication module for acquiring the user's schedule information. For example, the input unit acquires schedule information from a calendar app or a schedule management system and suggests optimal recipe conditions. The input unit can also suggest recipe conditions that match cooking times based on the user's schedule information. Furthermore, the input unit can also suggest recipe conditions related to specific events from the user's schedule information. This makes it possible to suggest optimal recipe conditions by referring to the user's schedule information. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input schedule information to the generation AI and cause the generation AI to suggest optimal recipe conditions.

[0089] The generation unit can estimate the user's emotion and adjust the expression method of the generated prompt based on the estimated user's emotion. The generation unit includes an emotion estimation algorithm for estimating the user's emotion. For example, the generation unit estimates the user's emotion using facial expression recognition technology. The generation unit generates detailed prompts when the user is relaxed. The generation unit can also generate concise prompts when the user is in a hurry. Furthermore, the generation unit can generate visually appealing prompts when the user is excited. This allows the generation of prompts that are easy for the user to understand by adjusting the expression method of the prompt according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can cause the generation AI to estimate the user's emotion.

[0090] The generation unit can apply an optimal prompt generation algorithm by referring to past generation history during generation. The generation unit includes a database for storing past generation history. For example, the generation unit selects an optimal prompt generation algorithm based on the past generation history. The generation unit can also prioritize generating frequently used prompts from the past generation history. Furthermore, the generation unit can analyze the generation history and optimize the prompt generation algorithm. By referring to the past generation history, the optimal prompt generation algorithm can be applied and accuracy can be improved. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input past generation history into the generation AI and cause the generation AI to optimize the algorithm.

[0091] The generation unit can generate prompts taking into account nutritional information of ingredients during generation. The generation unit includes a database for acquiring nutritional information of ingredients. For example, the generation unit acquires nutritional information from a nutrition database or a food composition table and reflects the information in the prompt. The generation unit can also generate prompts that suggest healthy recipes based on the nutritional information of ingredients. Furthermore, the generation unit can also generate prompts that suggest balanced meals taking into account the nutritional information. In this way, prompts that suggest healthy recipes can be generated by taking into account the nutritional information of ingredients. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input nutritional information to the generation AI and cause the generation AI to generate a prompt.

[0092] The generation unit can estimate the user's emotion and determine the priority of prompts to be generated based on the estimated user's emotion. The generation unit includes an emotion estimation algorithm for estimating the user's emotion. For example, the generation unit estimates the user's emotion using facial expression recognition technology. The generation unit uniformly displays all prompts when the user is relaxed. The generation unit can also prioritize important prompts when the user is in a hurry. Furthermore, the generation unit can emphasize and display specific prompts when the user is excited. This allows prompts to be prioritized according to the user's emotion, thereby prioritizing important prompts. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using AI, or without AI. For example, the generation unit can cause the generation AI to estimate the user's emotion.

[0093] The generation unit can generate optimal prompts by referring to the user's meal history during generation. The generation unit includes a database for storing the user's meal history. For example, the generation unit obtains the meal history from a meal recording app or database and reflects it in the prompt. The generation unit can also generate optimal prompts based on the user's past meal history. Furthermore, the generation unit can generate prompts that prioritize frequently used ingredients from the meal history. This makes it possible to generate optimal prompts by referring to the user's meal history and suggest recipes that match the user's preferences. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the meal history into the generation AI and cause the generation AI to generate prompts.

[0094] The generation unit can generate prompts taking into account the user's health condition information when generating the prompts. The generation unit includes a database for acquiring the user's health condition information. For example, the generation unit acquires health condition information from a health management app or medical data and reflects the health condition information in the prompts. The generation unit can also generate prompts that suggest healthy recipes based on the user's health condition information. Furthermore, the generation unit can also generate prompts that emphasize specific nutrients by taking into account the health condition information. In this way, prompts that suggest healthy recipes can be generated by taking into account the user's health condition information. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input health condition information to the generation AI and cause the generation AI to generate the prompts.

[0095] The generation AI unit can estimate the user's emotions and adjust the way the recipe is presented based on the estimated user's emotions. The generation AI unit includes an emotion estimation algorithm for estimating the user's emotions. For example, the generation AI unit estimates the user's emotions using facial expression recognition technology. The generation AI unit generates a detailed recipe when the user is relaxed. The generation AI unit can also generate a concise recipe when the user is in a hurry. Furthermore, the generation AI unit can generate a visually appealing recipe when the user is excited. This allows the recipe presentation to be adjusted according to the user's emotions, thereby generating a recipe that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the generation AI unit may be performed using AI or without AI. For example, the generation AI unit can cause the generation AI to estimate the user's emotions.

[0096] During generation, the generation AI unit can apply an optimal recipe generation algorithm by referring to past generation history. The generation AI unit has a database for storing past generation history. For example, the generation AI unit selects an optimal recipe generation algorithm based on the past generation history. The generation AI unit can also prioritize the generation of frequently used recipes from the past generation history. Furthermore, the generation AI unit can analyze the generation history and optimize the recipe generation algorithm. This allows the optimal recipe generation algorithm to be applied by referring to the past generation history, improving accuracy. Some or all of the above-mentioned processing in the generation AI unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation AI unit can input past generation history into the generation AI and cause the generation AI to optimize the algorithm.

[0097] The generation AI unit can generate a recipe taking into account the nutritional information of ingredients. The generation AI unit has a database for acquiring nutritional information of ingredients. For example, the generation AI unit acquires nutritional information from a nutrition database or a food composition table and reflects it in the recipe. The generation AI unit can also generate healthy recipes based on the nutritional information of ingredients. Furthermore, the generation AI unit can generate recipes that suggest balanced meals by taking into account the nutritional information. In this way, healthy recipes can be generated by taking into account the nutritional information of ingredients. Some or all of the above-mentioned processing in the generation AI unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation AI unit can input nutritional information to the generation AI and cause the generation AI to generate a recipe.

[0098] The generation AI unit can estimate the user's emotions and prioritize the recipes to be generated based on the estimated user emotions. The generation AI unit includes an emotion estimation algorithm for estimating the user's emotions. For example, the generation AI unit estimates the user's emotions using facial expression recognition technology. The generation AI unit displays all recipes equally when the user is relaxed. The generation AI unit can also prioritize important recipes when the user is in a hurry. The generation AI unit can also highlight specific recipes when the user is excited. This allows important recipes to be prioritized by determining the priority of recipes according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation AI unit may be performed using AI or without AI. For example, the generation AI unit can cause the generation AI to estimate the user's emotions.

[0099] The generation AI unit can generate an optimal recipe by referring to the user's meal history during generation. The generation AI unit has a database for storing the user's meal history. For example, the generation AI unit obtains the meal history from a meal recording app or database and reflects it in the recipe. The generation AI unit can also generate an optimal recipe based on the user's past meal history. Furthermore, the generation AI unit can generate recipes that prioritize frequently used ingredients from the meal history. This makes it possible to generate optimal recipes by referring to the user's meal history and suggest recipes that suit the user's preferences. Some or all of the above-mentioned processing in the generation AI unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation AI unit can input the meal history into the generation AI and have the generation AI generate a recipe.

[0100] The generation AI unit can generate a recipe taking into account the user's health condition information. The generation AI unit has a database for acquiring the user's health condition information. For example, the generation AI unit acquires health condition information from a health management app or medical data and reflects the information in the recipe. The generation AI unit can also generate healthy recipes based on the user's health condition information. Furthermore, the generation AI unit can generate recipes that emphasize specific nutrients by taking into account the health condition information. In this way, healthy recipes can be generated by taking into account the user's health condition information. Some or all of the above-mentioned processing in the generation AI unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation AI unit can input health condition information to the generation AI and cause the generation AI to generate a recipe.

[0101] The providing unit can estimate the user's emotions and adjust the recipe display method based on the estimated user emotions. The providing unit includes an emotion estimation algorithm for estimating the user's emotions. For example, the providing unit estimates the user's emotions using facial expression recognition technology. The providing unit provides a detailed recipe display when the user is relaxed. The providing unit can also provide a concise recipe display when the user is in a hurry. Furthermore, the providing unit can also provide a visually appealing recipe display when the user is excited. This allows the recipe display method to be adjusted according to the user's emotions, resulting in a user-friendly display. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit may be performed using AI, or may be performed without AI. For example, the providing unit can cause the generation AI to estimate the user's emotions.

[0102] When providing the recipe, the providing unit can select the optimal recipe display method by referring to the user's past usage history. The providing unit includes a database for storing the user's past usage history. For example, the providing unit selects the optimal recipe display method based on the past usage history. The providing unit can also prioritize and provide frequently used display methods based on the past usage history. Furthermore, the providing unit can analyze the usage history and optimize the recipe display method. This allows the optimal recipe display method to be selected by referring to the user's past usage history, enabling a display that is easy for the user to use. Some or all of the above-described processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the past usage history into the generation AI and cause the generation AI to select the optimal display method. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned photographing unit, discrimination unit, input unit, generation unit, generation AI unit, provision unit, suggestion unit, ordering unit, order provision unit, and emotion estimation unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the photographing unit photographs ingredients using the camera 42 of the smart device 14, and the discrimination unit uses image recognition technology by the specific processing unit 290 of the data processing device 12 to identify the ingredients. The input unit inputs user requirements using the reception device 38 of the smart device 14, and the generation unit creates a prompt input sentence by the specific processing unit 290 of the data processing device 12. The generation AI unit inputs a prompt to the generation AI by the specific processing unit 290 of the data processing device 12 and generates a recipe. The provision unit provides the generated recipe to the user using the output device 40 of the smart device 14. The suggestion unit suggests substitute ingredients by the specific processing unit 290 of the data processing device 12, and the ordering unit orders the missing ingredients in cooperation with online delivery by the specific processing unit 290 of the data processing device 12. The order providing unit provides the order of the recipe list by the specific processing unit 290 of the data processing device 12, and the emotion estimating unit estimates the emotion of the user by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned photographing unit, discrimination unit, input unit, generation unit, generation AI unit, provision unit, suggestion unit, ordering unit, order provision unit, and emotion estimation unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the photographing unit photographs ingredients using the camera 42 of the smart glasses 214, and the discrimination unit uses image recognition technology by the specific processing unit 290 of the data processing device 12 to identify the ingredients. The input unit inputs user requirements using the microphone 238 of the smart glasses 214, and the generation unit creates a prompt input sentence by the specific processing unit 290 of the data processing device 12. The generation AI unit inputs a prompt to the generation AI by the specific processing unit 290 of the data processing device 12 and generates a recipe. The provision unit provides the generated recipe to the user using the speaker 240 of the smart glasses 214. The suggestion unit suggests substitute ingredients by the specific processing unit 290 of the data processing device 12, and the ordering unit orders missing ingredients in cooperation with online delivery by the specific processing unit 290 of the data processing device 12. The order providing unit provides the order of the recipe list by the specific processing unit 290 of the data processing device 12, and the emotion estimating unit estimates the emotion of the user by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned photographing unit, discrimination unit, input unit, generation unit, generation AI unit, provision unit, suggestion unit, ordering unit, order provision unit, and emotion estimation unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the photographing unit photographs ingredients using the camera 42 of the headset-type terminal 314, and the discrimination unit uses image recognition technology by the specific processing unit 290 of the data processing device 12 to identify the ingredients. The input unit inputs the user's requirements using the microphone 238 of the headset-type terminal 314, and the generation unit creates a prompt input sentence by the specific processing unit 290 of the data processing device 12. The generation AI unit inputs a prompt to the generation AI by the specific processing unit 290 of the data processing device 12 and generates a recipe. The provision unit provides the generated recipe to the user using the display 343 of the headset-type terminal 314. The suggestion unit suggests substitute ingredients by the specific processing unit 290 of the data processing device 12, and the ordering unit orders the missing ingredients in cooperation with online delivery by the specific processing unit 290 of the data processing device 12. The order providing unit provides the order of the recipe list by the specific processing unit 290 of the data processing device 12, and the emotion estimating unit estimates the emotion of the user by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned photographing unit, discrimination unit, input unit, generation unit, generation AI unit, provision unit, suggestion unit, ordering unit, order provision unit, and emotion estimation unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the photographing unit photographs ingredients using the camera 42 of the robot 414, and the discrimination unit uses image recognition technology by the specific processing unit 290 of the data processing device 12 to identify the ingredients. The input unit inputs user requirements using the microphone 238 of the robot 414, and the generation unit creates a prompt input sentence by the specific processing unit 290 of the data processing device 12. The generation AI unit inputs a prompt to the generation AI by the specific processing unit 290 of the data processing device 12 and generates a recipe. The provision unit provides the generated recipe to the user using the speaker 240 of the robot 414. The suggestion unit suggests substitute ingredients by the specific processing unit 290 of the data processing device 12, and the ordering unit orders the missing ingredients in cooperation with online delivery by the specific processing unit 290 of the data processing device 12. The order providing unit provides the order of the recipe list by the specific processing unit 290 of the data processing device 12, and the emotion estimating unit estimates the emotion of the user by the specific processing unit 290 of the data processing device 12.

[0103] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0104] The providing unit can estimate the user's emotions and adjust the recipe display method based on the estimated user emotions. For example, if the user is relaxed, a detailed recipe display can be provided. If the user is in a hurry, a concise recipe display can be provided. Furthermore, if the user is excited, a visually appealing recipe display can be provided. This allows the recipe display method to be adjusted according to the user's emotions, resulting in a display that is easy for the user to view. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the providing unit can cause the generation AI to estimate the user's emotions.

[0105] The input unit can estimate the user's emotions and adjust the display method of the input interface based on the estimated user emotions. For example, if the user is relaxed, detailed input options can be provided. If the user is in a hurry, a simple input interface can be provided. Furthermore, if the user is excited, a visually appealing input interface can be provided. By adjusting the display method of the input interface according to the user's emotions, an interface that is easy for the user to use can be provided. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the input unit can be performed using AI, for example, or without AI. For example, the input unit can cause the generation AI to estimate the user's emotions.

[0106] The generation unit can estimate the user's emotions and adjust the expression style of the generated prompt based on the estimated user's emotions. For example, if the user is relaxed, a detailed prompt can be generated. If the user is in a hurry, a concise prompt can be generated. Furthermore, if the user is excited, a visually appealing prompt can be generated. By adjusting the expression style of the prompt according to the user's emotions, a prompt that is easy for the user to understand can be generated. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can cause the generation AI to estimate the user's emotions.

[0107] The discrimination unit can estimate the user's emotion and adjust the display method of the discrimination result based on the estimated user's emotion. For example, if the user is relaxed, a detailed discrimination result can be displayed. If the user is in a hurry, a concise discrimination result can be displayed. Furthermore, if the user is excited, a visually appealing display method can be adopted. This allows the display method of the discrimination result to be adjusted according to the user's emotion, enabling a display that is easy for the user to view. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the discrimination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the discrimination unit can cause the generation AI to estimate the user's emotion.

[0108] The generation AI unit can estimate the user's emotions and adjust the way the recipe is expressed based on the estimated user's emotions. For example, if the user is relaxed, a detailed recipe can be generated. If the user is in a hurry, a concise recipe can be generated. Furthermore, if the user is excited, a visually appealing recipe can be generated. By adjusting the way the recipe is expressed based on the user's emotions, a recipe that is easy for the user to understand can be generated. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the generation AI unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the generation AI unit can cause the generation AI to estimate the user's emotions.

[0109] When taking a photograph, the photographing unit can automatically set appropriate photographing conditions, taking into account the temperature and humidity inside the refrigerator. For example, the photographing unit measures the temperature inside the refrigerator using a temperature sensor and the humidity inside the refrigerator using a humidity sensor. When the temperature inside the refrigerator is low, the photographing unit adjusts the exposure to take a clear photograph. When the humidity inside the refrigerator is high, the photographing unit can also clean the lens before taking a photograph to prevent lens fogging. Furthermore, the photographing unit can automatically set the optimal white balance based on the temperature and humidity data. This allows clear photographs to be taken by automatically setting the optimal photographing conditions, taking into account the temperature and humidity inside the refrigerator. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can input temperature and humidity data into the generation AI and have the generation AI set the optimal photographing conditions.

[0110] When photographing, the photographing unit can identify the location of ingredients using shelf position information within the refrigerator. For example, the photographing unit acquires shelf position information using a position sensor. The photographing unit prioritizes photographing ingredients on a specific shelf based on the shelf position information. The photographing unit can also automatically adjust the photographing range using the shelf position information. Furthermore, the photographing unit can identify the location of ingredients based on the shelf position information and efficiently photograph them. In this way, ingredients can be efficiently photographed by identifying the location of ingredients using shelf position information within the refrigerator. Some or all of the above-described processing in the photographing unit may be performed using, for example, AI, or may be performed without using AI. For example, the photographing unit can input shelf position information to the generation AI and cause the generation AI to identify the location of ingredients.

[0111] During discrimination, the discrimination unit can analyze not only the shape and color of the food ingredient but also the text information written on the package to improve discrimination accuracy. For example, the discrimination unit uses deep learning to analyze the shape and color of the food ingredient and identify the food ingredient. The discrimination unit can also be equipped with OCR technology for analyzing the text information written on the package. For example, the discrimination unit uses OCR technology to analyze the text information on the package and identify the brand and type of the food ingredient. Furthermore, the discrimination unit can comprehensively analyze the shape, color, and text information to improve discrimination accuracy. In this way, by analyzing not only the shape and color of the food ingredient but also the text information on the package, discrimination accuracy is improved. Some or all of the above-mentioned processing in the discrimination unit may be performed using, for example, AI, or may be performed without using AI. For example, the discrimination unit can have a generation AI perform food ingredient discrimination.

[0112] During input, the input unit can present optimal input candidates by referring to the user's past input history. For example, the input unit presents optimal input candidates based on conditions previously input by the user. The input unit can also prioritize displaying frequently used conditions from the past input history. Furthermore, the input unit can learn the user's input patterns and automatically suggest optimal input candidates. This allows optimal input candidates to be presented by referring to the user's past input history, improving input efficiency. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the past input history to a generation AI and cause the generation AI to present optimal input candidates.

[0113] The generation unit can generate prompts taking into account the user's health condition information. For example, the generation unit acquires health condition information from a health management app or medical data and reflects the information in the prompt. The generation unit can also generate prompts that suggest healthy recipes based on the user's health condition information. Furthermore, the generation unit can generate prompts that emphasize specific nutrients taking into account the health condition information. In this way, a prompt that suggests healthy recipes can be generated by taking into account the user's health condition information. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input health condition information to the generation AI and cause the generation AI to generate a prompt.

[0114] The processing flow of the second embodiment will be briefly explained below.

[0115] Step 1: The camera unit is a component that allows the user to take pictures of ingredients in the refrigerator. For example, the camera unit can take pictures of ingredients using a smartphone camera. The camera unit can also have a function to automatically adjust the lighting conditions inside the refrigerator to take optimal photos. For example, if the lighting inside the refrigerator is dim, the flash can be used to take bright photos. Step 2: The discrimination unit is the part that discriminates ingredients from the photos taken by the photographing unit. For example, the discrimination unit discriminates ingredients from the photos using image recognition technology. Image recognition technology includes deep learning and computer vision technology. Step 3: The input unit is a section where the user inputs recipe conditions. For example, the input unit supports text input, voice input, gesture input, etc. Step 4: The generator creates a prompt input sentence based on the conditions entered by the input unit and the ingredients identified by the discriminator. For example, the generator automatically generates the prompt input sentence using a natural language processing algorithm. Step 5: The generation AI unit inputs the prompt input sentence generated by the generation unit into the generation AI and generates a recipe. The generation AI includes text generation AI (e.g., LLM) and multimodal generation AI. Step 6: The providing unit is a component that provides the recipe generated by the generation AI unit to the user. For example, the providing unit displays the recipe on an app. The providing unit may also have a function to estimate the user's emotions and adjust the way the recipe is displayed based on the estimated user emotions.

[0116] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0117] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0118] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0119] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0120] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0121] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0122] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0123] 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.

[0124] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0125] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0126] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0127] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0128] 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.

[0129] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0130] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0131] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0132] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0133] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0134] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0135] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0136] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0137] 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.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] 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.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] 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.

[0144] 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.

[0145] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0146] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0147] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0148] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0149] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0150] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0151] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0152] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0153] 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.

[0154] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0155] 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.

[0156] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0157] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0158] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0159] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0160] 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.

[0161] 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.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0167] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0170] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0171] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0172] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0173] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0174] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0175] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0176] 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.

[0177] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0178] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0179] 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.

[0180] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0181] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0182] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0183] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0184] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0185] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0186] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0187] [Explanation of symbols]

[0188] 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 photography department that photographs ingredients, a discrimination unit that discriminates ingredients from the photograph taken by the photographing unit; an input section for inputting recipe conditions; a generation unit that generates a prompt input sentence based on the conditions input by the input unit and the ingredients identified by the identification unit; a generation AI unit that inputs the prompt input sentence generated by the generation unit to a generation AI unit and generates a recipe; a providing unit that provides a user with the recipe generated by the generating AI unit; Equipped with A system characterized by:

2. Equipped with a suggestion section that suggests specific substitute ingredients when ingredients are in short supply 2. The system of claim 1.

3. Equipping the ordering department with the ability to order missing ingredients in conjunction with online delivery 2. The system of claim 1.

4. The system includes an order providing unit that provides the order of the recipe list according to the priority of the conditions set by the user.

2. The system of claim 1.

5. The determination unit Identifying ingredients from photos using image recognition technology 2. The system of claim 1.

6. The generation unit It has an algorithm that automatically generates prompt input sentences based on the conditions entered by the user.

2. The system of claim 1.

7. The imaging unit is Estimates the user's emotions and adjusts the timing of taking photos based on the estimated user emotions.

2. The system of claim 1.

8. The imaging unit is When taking a photo, the system automatically sets appropriate shooting conditions by taking into account the temperature and humidity inside the refrigerator.

2. The system of claim 1.

9. The imaging unit is When taking a photo, the location of ingredients is identified using shelf position information within the refrigerator.

2. The system of claim 1.

10. The imaging unit is Estimate the user's emotions and prioritize ingredients to photograph based on the estimated emotions.

2. The system of claim 1.

Images