System

Abstract

To propose an appropriate recipe by efficiently utilizing a food material owned by a user.SOLUTION: A system includes: a reception unit; a generation unit; an automatic generation unit; and a cooperation unit. The reception unit receives an input of a type and a remaining amount of a food material. The generation unit analyzes information received by the reception unit and generates a recipe corresponding to the food ingredient. The automatic generation unit automatically generates a next shopping list based on the recipe generated by the generation unit. The cooperation unit cooperates with mail-order sales service based on the shopping list generated by the automatic generation unit and automatically requests delivery.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have not adequately helped users efficiently utilize ingredients they have at home and suggested appropriate recipes, and there is room for improvement.

[0005] The system according to the embodiment aims to efficiently utilize ingredients owned by the user and to suggest suitable recipes. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, an automatic generation unit, and a linking unit. The reception unit receives input of the type and remaining amount of ingredients. The generation unit analyzes the information received by the reception unit and generates a recipe according to the ingredients. The automatic generation unit automatically generates a shopping list for the next purchase based on the recipe generated by the generation unit. The linking unit links with a mail order service based on the shopping list generated by the automatic generation unit, and automatically requests delivery. Effect of the Invention

[0007] The system according to the embodiment can efficiently utilize ingredients owned by the user and suggest appropriate recipes. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A recipe advice system according to an embodiment of the present invention is a system that advises a user on an appropriate recipe based on information on ingredients that the user has at home. In this recipe advice system, the user inputs the type and remaining amount of ingredients, and the generation AI analyzes the information to provide a recipe that corresponds to the ingredients. Furthermore, this system automatically generates a next shopping list from the user's ingredient information. Since the system also provides a function to automatically request delivery in cooperation with a mail-order service, it brings great convenience to users who are busy at work. For example, a user inputs the type and remaining amount of ingredients that the user has at home into the system. For example, information on vegetables, meat, seasonings, etc. in the refrigerator is input. This information is accepted by the reception unit. Next, the generation AI analyzes the information accepted by the reception unit. The generation AI generates an appropriate recipe based on the input ingredient information. For example, it proposes a recipe for a dish that can be made using ingredients in the refrigerator. This recipe is generated by the generation unit. Based on the generated recipe, the next shopping list is automatically generated. For example, if an ingredient required for a recipe is missing, that ingredient is added to the shopping list. This shopping list is generated by the automatic generation unit. Furthermore, based on the automatically generated shopping list, the system cooperates with a mail-order service to automatically request delivery. For example, a user orders the necessary ingredients based on a shopping list from an online shopping site and requests that they be delivered to his / her home. This linking is performed by the linking unit. This system allows the user to make effective use of ingredients at home and easily obtain appropriate recipes. In addition, the next shopping list is automatically generated and delivery requests are automatically made in cooperation with the online shopping service, providing great convenience for busy users. As a result, the recipe advice system can provide appropriate recipes based on the user's ingredient information, and convenience can be improved by the automatic generation of shopping lists and the linking with the online shopping service.

[0029] The recipe advice system according to the embodiment includes a reception unit, a generation unit, an automatic generation unit, and a linking unit. The reception unit receives input of the type and remaining amount of ingredients held by the user at home. The ingredients input by the user include, but are not limited to, vegetables, meat, fish, seasonings, and the like. The reception unit provides, for example, an interface for the user to input information on ingredients in the refrigerator. The interface supports methods such as text input, voice input, and scan input. The generation unit uses a generation AI to analyze the ingredient information received by the reception unit and generate an appropriate recipe. The generation AI generates a recipe based on the ingredient information, for example, using a text generation AI (for example, LLM). The generation AI analyzes the ingredient information input by the user and suggests an optimal recipe. For example, the generation AI receives a prompt such as "Please suggest a recipe for a dish that can be made using ingredients in the refrigerator" and generates a recipe. The automatic generation unit automatically generates a shopping list for the next time based on the recipe generated by the generation unit. For example, if an ingredient required for a recipe is in short supply, the automatic generation unit adds the ingredient to the shopping list. The automatic generation unit uses a generation AI to generate a shopping list based on the recipe. The linking unit links with a mail order service based on the shopping list generated by the automatic generation unit and automatically requests delivery. The linking unit, for example, orders necessary ingredients from a mail order site based on the shopping list and requests that they be delivered to the home. The linking unit links with the mail order service using the generation AI. In this way, the recipe advice system according to the embodiment can provide appropriate recipes based on the user's ingredient information, and improve convenience through the automatic generation of a shopping list and the linking with the mail order service.

[0030] The reception unit receives input of the type and remaining amount of ingredients that the user has at home. The ingredients input by the user include, but are not limited to, vegetables, meat, fish, and seasonings. The reception unit provides, for example, an interface for the user to input information about ingredients in the refrigerator. The interface supports methods such as text input, voice input, and scan input. Specifically, in text input, the user can input the name of the ingredient and its remaining amount using a keyboard. In voice input, the user speaks the ingredient name and remaining amount into a microphone, and the voice is automatically converted into text using voice recognition technology. In scan input, ingredient information is automatically obtained by scanning a barcode or two-dimensional code (e.g., QR Code (registered trademark)) reader printed on the ingredient package. This allows the user to input ingredient information easily and quickly. In addition, the reception unit stores the input ingredient information in a database so that it can be referenced later. For example, the current inventory status of ingredients can be confirmed based on ingredient information input by the user in the past. Furthermore, the reception unit analyzes the ingredient information input by the user and provides basic data for suggesting appropriate recipes based on the type and remaining amount of the ingredient. This allows the reception unit to improve convenience for the user and increase the efficiency of the entire system.

[0031] The generation unit uses the generation AI to analyze the ingredient information received by the reception unit and generate an appropriate recipe. The generation AI generates a recipe based on the ingredient information, for example, using a text generation AI (e.g., LLM). The generation AI analyzes the ingredient information input by the user and proposes an optimal recipe. Specifically, the generation AI receives the ingredient information input by the user as a prompt and generates a recipe based on that information. For example, when the generation AI receives a prompt such as "Please suggest a recipe for a dish that can be made using ingredients in the refrigerator," the generation AI generates an appropriate recipe while referring to an internal database and past recipe data. The generation AI can propose a recipe that suits the user's preferences by taking into account the combination of ingredients, cooking method, and use of seasonings. Furthermore, the generation AI can also propose a more personalized recipe based on the user's past input history and evaluation. For example, if the user has given a high rating to a recipe in the past or has a tendency to prefer specific ingredients, the generation AI generates a recipe taking that information into consideration. This allows the generation unit to provide an optimal recipe that meets the user's needs and increase the user's satisfaction.

[0032] The automatic generation unit automatically generates the next shopping list based on the recipe generated by the generation unit. For example, if an ingredient required for a recipe is missing, the automatic generation unit adds the ingredient to the shopping list. Specifically, the automatic generation unit lists all ingredients included in the generated recipe and identifies the missing ingredients by comparing them with ingredients already owned by the user. For example, if a recipe requires "tomatoes" and the user already owns tomatoes, the ingredient is not added to the shopping list. On the other hand, if the user does not own "basil," the ingredient is added to the shopping list. The automatic generation unit uses a generation AI to generate a shopping list based on the recipe. The generation AI not only analyzes the contents of the recipe and creates a list of necessary ingredients, but also optimizes the list by taking into account the amount and type of ingredients. For example, if there is an ingredient that is commonly used in multiple recipes, the amount of the ingredient required is added up and reflected in the list. It is also possible to customize the shopping list by taking into account the user's past shopping history and consumption patterns. In this way, the automatic generation unit supports the user in shopping efficiently and reduces unnecessary shopping.

[0033] The linking unit links with the mail-order service based on the shopping list generated by the automatic generation unit and automatically requests delivery. For example, the linking unit orders the necessary ingredients on a mail-order site based on the shopping list and requests that they be delivered to the user's home. Specifically, the linking unit links with the mail-order service using the generation AI. The generation AI analyzes the contents of the shopping list and selects the optimal mail-order site and store. For example, it can select the store where a specific ingredient can be purchased at the lowest price or the mail-order site with the shortest delivery time. The linking unit automatically places an order with the selected mail-order site and arranges for the ingredients to be delivered to the user's home. In addition, the linking unit also has a function to notify the user of the progress of the order and the scheduled delivery time. For example, it sends a notification to the user when the order is confirmed, and sends a reminder when the scheduled delivery time approaches. This allows the user to grasp the order status in real time and wait for the ingredients to be received with peace of mind. The linking unit can also make optimal suggestions for the next order based on the user's past order history and ratings. As a result, the linking unit can greatly improve user convenience and increase the efficiency of the entire system.

[0034] The reception unit may include a freshness determination unit based on the freshness and expiration date of the ingredients. The reception unit may include, for example, a freshness determination unit for taking into account the freshness and expiration date of the ingredients. The freshness determination unit may use a sensor or algorithm for evaluating the freshness of the ingredients. For example, the freshness determination unit may evaluate the freshness based on information such as the color, smell, and hardness of the ingredients. The freshness determination unit may use AI to evaluate the freshness of the ingredients. For example, the freshness determination unit may input image data of the ingredients into AI to evaluate the freshness. This allows for more appropriate recipe suggestions by taking into account the freshness and expiration date of the ingredients.

[0035] The generation unit can include a history analysis unit that suggests a favorite recipe based on the user's past usage history. The generation unit includes, for example, a history analysis unit that suggests a favorite recipe based on the user's past usage history. The history analysis unit analyzes the user's past recipe selections and cooking history to understand the user's preferences. The history analysis unit can analyze the user's usage history using AI. For example, the history analysis unit inputs the user's past recipe selection data into AI to suggest a favorite recipe. This makes it possible to improve user satisfaction by suggesting a favorite recipe based on the user's past usage history.

[0036] The generation unit can include a nutritional analysis unit based on nutritional balance and calories. The generation unit includes, for example, a nutritional analysis unit for taking into account nutritional balance and calories. The nutritional analysis unit can use an algorithm for evaluating the nutritional balance and calories of a recipe. For example, the nutritional analysis unit evaluates a recipe based on the recommended intake amount and balancing method of each nutrient. The nutritional analysis unit can evaluate the nutritional balance and calories of a recipe using AI. For example, the nutritional analysis unit inputs nutritional data of a recipe into AI to evaluate nutritional balance and calories. This makes it possible to propose recipes that take into account nutritional balance and calories.

[0037] The linking unit may include a service selection unit for allowing a plurality of mail-order services to be selected. The linking unit may include, for example, a service selection unit for allowing a plurality of mail-order services to be selected. The service selection unit provides an interface for a user to select an optimal service from a plurality of available mail-order services. The service selection unit may use AI to analyze information on the plurality of mail-order services and select an optimal service. For example, the service selection unit may select a mail-order service based on criteria such as price, delivery time, and user evaluation. This allows a user to select a plurality of mail-order services, thereby improving convenience for the user.

[0038] The reception unit can analyze the user's past ingredient input history and select an appropriate input method. The reception unit, for example, analyzes the user's past ingredient input history and selects the optimal input method. The input method includes, but is not limited to, for example, voice input, touch input, and scan input. The reception unit can use AI to analyze the user's past input history and select the optimal input method. For example, ingredients that the user frequently input in the past are automatically displayed as candidates. In addition, the reception unit preferentially suggests input methods (voice, text, etc.) that the user used in the past. Furthermore, the reception unit predicts and suggests ingredients to be used in a specific time period from the user's past input history. This improves input efficiency by selecting the optimal input method based on the user's past input history.

[0039] The reception unit can filter the food ingredient information based on the user's current meal plan and health condition when the food ingredient information is input. For example, the reception unit filters the food ingredient information based on the user's current meal plan and health condition when the food ingredient information is input. The filtering is performed using AI based on the user's meal plan and health condition. For example, if the user is on a diet, filtering is performed so that low-calorie food ingredients are preferentially input. In addition, if the user needs to ingest a specific nutrient, filtering is performed so that food ingredients containing that nutrient are preferentially input. Furthermore, if the user has a specific allergy, filtering is performed so that food ingredients containing that allergen are excluded. This allows for more appropriate input by filtering food ingredient information based on the user's meal plan and health condition.

[0040] The reception unit can prioritize inputting highly relevant ingredient information in consideration of the geographical location information of the user when inputting ingredient information. For example, the reception unit prioritizes inputting highly relevant ingredient information in consideration of the geographical location information of the user when inputting ingredient information. The geographical location information is analyzed using AI based on the user's current location and regional information. For example, if the user lives in a specific region, ingredients that are easily available in that region are prioritized for input. Also, if the user is traveling, ingredients that are available at the current location are prioritized for input. Furthermore, if the user wants to make a dish from a specific region, ingredients from that region are prioritized for input. In this way, highly relevant ingredient information can be prioritized for input by considering the geographical location information of the user.

[0041] The reception unit can analyze the user's social media activity when inputting ingredient information and input related ingredient information. For example, the reception unit analyzes the user's social media activity when inputting ingredient information and inputs related ingredient information. Social media activity is analyzed using AI to analyze the content of the user's posts and the number of followers. For example, the necessary ingredient information is input based on photos of food shared by the user on social media. Also, related ingredient information is input based on information on cooking accounts the user follows on social media. Furthermore, ingredient information is input based on trends in cooking communities in which the user participates on social media. In this way, related ingredient information can be input by analyzing the user's social media activity.

[0042] The generation unit can adjust the level of detail of the recipe based on the priority of the ingredients when generating the recipe. For example, the generation unit adjusts the level of detail of the recipe based on the priority of the ingredients when generating the recipe. The adjustment of the level of detail is performed using AI based on the importance and frequency of use of the ingredients. For example, detailed cooking steps for main ingredients are provided. Also, concise explanations are provided for supplementary ingredients. Furthermore, details of cooking time and temperature are adjusted according to the importance of the ingredients. In this way, a more appropriate recipe can be provided by adjusting the level of detail of the recipe based on the importance of the ingredients.

[0043] The generation unit can apply different recipe generation algorithms depending on the category of ingredients when generating a recipe. For example, the generation unit applies different recipe generation algorithms depending on the category of ingredients when generating a recipe. The recipe generation algorithm is applied using AI depending on the category of ingredients. For example, a health-oriented algorithm is applied to a recipe whose main ingredient is vegetables. Also, an algorithm that provides a sense of volume is applied to a recipe whose main ingredient is meat. Furthermore, an algorithm that emphasizes sweetness and appearance is applied to a recipe whose main ingredient is dessert. In this way, by applying different recipe generation algorithms depending on the category of ingredients, more appropriate recipes can be provided.

[0044] The generation unit can determine the priority of recipes based on the acquisition time of ingredients when generating recipes. For example, the generation unit determines the priority of recipes based on the acquisition time of ingredients when generating recipes. The acquisition time is evaluated using AI based on the purchase date or harvest date of ingredients. For example, recipes using seasonal ingredients are preferentially generated. Also, recipes using ingredients with an approaching expiration date are preferentially generated. Furthermore, recipes using ingredients recently purchased by the user are preferentially generated. In this way, more appropriate recipes can be provided by determining the priority of recipes based on the acquisition time of ingredients.

[0045] The generation unit can adjust the order of the recipe based on the relevance of ingredients when generating the recipe. For example, the generation unit adjusts the order of the recipe based on the relevance of ingredients when generating the recipe. The evaluation of the relevance is performed using AI based on the combination of ingredients and commonalities in cooking methods. For example, a recipe that uses a main ingredient first is generated. Also, a recipe that uses a supplementary ingredient later is generated. Furthermore, the order of cooking steps is adjusted based on the relevance of ingredients. In this way, a more appropriate recipe can be provided by adjusting the order of the recipe based on the relevance of ingredients.

[0046] The automatic generation unit can generate an optimal list by analyzing the user's past purchase history when generating a shopping list. For example, the automatic generation unit generates an optimal list by analyzing the user's past purchase history when generating a shopping list. The analysis of the purchase history is performed using AI based on the user's past purchases and purchase frequency. For example, an optimal shopping list is generated based on ingredients purchased by the user in the past. Also, frequently purchased ingredients are added to the list with priority from the user's past purchase history. Furthermore, the user's past purchase history is analyzed, and necessary ingredients are predicted and added to the list. In this way, an optimal shopping list can be provided by analyzing the user's past purchase history.

[0047] The automatic generation unit can customize the contents of the shopping list based on the user's current living situation when generating the shopping list. For example, the automatic generation unit customizes the contents of the list based on the user's current living situation when generating the shopping list. The evaluation of the living situation is performed using AI based on the user's family composition, work situation, etc. For example, if the user is busy, ingredients that are easy to cook are preferentially added to the list. Also, if the user is health-conscious, ingredients with a balanced nutritional content are added to the list. Furthermore, if the user is planning a specific event, ingredients necessary for the event are added to the list. In this way, a more appropriate shopping list can be provided by customizing the contents of the list based on the user's current living situation.

[0048] The automatic generation unit can generate an optimal shopping list by taking into consideration the geographical location information of the user when generating the shopping list. For example, the automatic generation unit generates an optimal list by taking into consideration the geographical location information of the user when generating a shopping list. The geographical location information is analyzed based on the user's current location and regional information using AI. For example, if the user lives in a specific region, ingredients that are easily available in that region are added to the list. Also, if the user is traveling, ingredients that are available in the current location are added to the list. Furthermore, if the user wants to cook a dish from a specific region, ingredients from that region are added to the list. In this way, an optimal shopping list can be provided by taking into consideration the geographical location information of the user.

[0049] The automatic generation unit can adjust the contents of the shopping list by analyzing the user's social media activity when generating the shopping list. For example, the automatic generation unit adjusts the contents of the list by analyzing the user's social media activity when generating a shopping list. Social media activity is analyzed using AI to analyze the content of the user's posts and the number of followers. For example, necessary ingredients are added to the list based on photos of dishes shared by the user on social media. Also, related ingredients are added to the list based on information on cooking accounts that the user follows on social media. Furthermore, ingredients are added to the list based on trends in cooking communities that the user participates in on social media. In this way, related ingredients can be added to the list by analyzing the user's social media activity.

[0050] The linking unit can select the optimal service by analyzing the user's past usage history when linking with a mail-order service. For example, when linking with a mail-order service, the linking unit analyzes the user's past usage history and selects the optimal service. The usage history is analyzed using AI based on the user's past purchases and purchase frequency. For example, the optimal service is selected based on the mail-order services the user has used in the past. In addition, the most reliable services are preferentially selected from the user's past usage history. Furthermore, the user's past usage history is analyzed to select the most efficient service. In this way, the optimal mail-order service can be provided by analyzing the user's past usage history.

[0051] The linking unit can customize the selection of services based on the user's current living situation when linking with a mail-order service. For example, when linking with a mail-order service, the linking unit customizes the selection of services based on the user's current living situation. The evaluation of the living situation is performed using AI based on the user's family structure, work situation, etc. For example, if the user is busy, a service that can deliver quickly is selected with priority. Also, if the user is health-conscious, a service that handles organic foods is selected. Furthermore, if the user is planning a specific event, a service that handles products necessary for the event is selected. In this way, by customizing the selection of services based on the user's current living situation, more appropriate services can be provided.

[0052] The linking unit can select the optimal service in consideration of the geographical location information of the user when linking with a mail-order service. For example, the linking unit selects the optimal service in consideration of the geographical location information of the user when linking with a mail-order service. The geographical location information is analyzed using AI based on the user's current location and regional information. For example, if the user lives in a specific region, a service that can deliver quickly in that region is selected. Also, if the user is traveling, a service that can be used in the current location is selected. Furthermore, if the user wants to purchase a specialty product of a specific region, a mail-order service for that region is selected. In this way, the optimal mail-order service can be provided by taking into account the user's geographical location information.

[0053] The linking unit can adjust the selection of a service by analyzing the user's social media activity when linking with a mail-order service. For example, when linking with a mail-order service, the linking unit analyzes the user's social media activity and adjusts the selection of a service. Social media activity is analyzed using AI to analyze the content of the user's posts and the number of followers. For example, a related mail-order service is selected based on products shared by the user on social media. Also, the optimal service is selected based on information about mail-order services the user follows on social media. Furthermore, a service is selected based on trends in communities in which the user participates on social media. In this way, related mail-order services can be provided by analyzing the user's social media activity.

[0054] The freshness determination unit can evaluate the freshness based on the storage method of the food ingredient when determining the freshness. For example, the freshness determination unit evaluates the freshness based on the storage method of the food ingredient when determining the freshness. The evaluation of the storage method is performed using AI based on the storage state and storage period of the food ingredient. For example, the freshness of food ingredients stored in a refrigerator is evaluated. The freshness of food ingredients stored frozen is also evaluated. Furthermore, the freshness of food ingredients stored at room temperature is evaluated. As a result, by evaluating the freshness based on the storage method of the food ingredient, more accurate freshness determination is possible.

[0055] The freshness determination unit can evaluate the freshness based on the purchase date and frequency of use of the ingredients when determining freshness. The freshness determination unit, for example, evaluates the freshness based on the purchase date and frequency of use of the ingredients when determining freshness. The evaluation of the purchase date and frequency of use is performed using AI based on the purchase history and use history of the ingredients. For example, the freshness of ingredients with a recent purchase date is rated high. Also, the freshness of ingredients with a high frequency of use is rated high. Furthermore, the freshness of ingredients with an old purchase date is rated low. This allows for more accurate freshness determination by evaluating the freshness based on the purchase date and frequency of use of the ingredients.

[0056] The freshness determination unit can evaluate freshness taking into account the geographical origin information of the food ingredient when determining freshness. For example, the freshness determination unit evaluates freshness taking into account the geographical origin information of the food ingredient when determining freshness. The evaluation of the geographical origin information is performed using AI based on the food ingredient's place of origin and transportation route. For example, the freshness of locally produced food ingredients is highly rated. In addition, the freshness of imported food ingredients is carefully evaluated. Furthermore, the freshness of specialty products from a specific region is highly rated. This allows for more accurate freshness determination by taking into account the geographical origin information of the food ingredient.

[0057] The history analysis unit can analyze the user's past recipe usage history during history analysis to suggest the optimal recipe. For example, the history analysis unit analyzes the user's past recipe usage history during history analysis to suggest the optimal recipe. The analysis of the recipe usage history is performed using AI based on the user's past recipe selections and cooking history. For example, the optimal recipe is suggested based on recipes the user has used in the past. In addition, the user's favorite recipes are preferentially suggested based on the user's past recipe usage history. Furthermore, the user's past recipe usage history is analyzed to suggest a wide variety of recipes. In this way, the optimal recipe can be provided by analyzing the user's past recipe usage history.

[0058] The history analysis unit can suggest recipes based on the user's current meal plan when analyzing the history. For example, the history analysis unit suggests recipes based on the user's current meal plan when analyzing the history. The meal plan is evaluated using AI based on the user's current meal plan and nutritional balance. For example, if the user is on a diet, low-calorie recipes are suggested. Also, if the user needs to ingest a specific nutrient, recipes containing that nutrient are suggested. Furthermore, if the user is planning a specific event, recipes suitable for that event are suggested. This makes it possible to provide more appropriate recipes by suggesting recipes based on the user's current meal plan.

[0059] The history analysis unit can suggest optimal recipes taking into account the geographical location information of the user when analyzing the history. For example, the history analysis unit suggests optimal recipes taking into account the geographical location information of the user when analyzing the history. The evaluation of the geographical location information is performed using AI based on the user's current location and regional information. For example, if the user lives in a specific region, recipes using ingredients from that region are suggested. Also, if the user is traveling, recipes using ingredients available in the current location are suggested. Furthermore, if the user wants to make a dish from a specific region, recipes from that region are suggested. In this way, optimal recipes can be provided by taking into account the geographical location information of the user.

[0060] The nutritional analysis unit can analyze the user's past meal history during nutritional analysis to suggest an optimal nutritional balance. For example, the nutritional analysis unit analyzes the user's past meal history during nutritional analysis to suggest an optimal nutritional balance. Analysis of the meal history is performed using AI based on the user's past meal contents and ingested nutrients. For example, an optimal nutritional balance is suggested based on the nutrients the user has ingested in the past. In addition, a nutritionally balanced meal is suggested based on the user's past meal history. Furthermore, the user's past meal history is analyzed to suggest a meal that supplements necessary nutrients. In this way, an optimal nutritional balance can be provided by analyzing the user's past meal history.

[0061] The nutritional analysis unit can suggest a nutritional balance based on the user's current health condition during nutritional analysis. The nutritional analysis unit, for example, suggests a nutritional balance based on the user's current health condition during nutritional analysis. The health condition is evaluated using AI based on the user's medical data and self-reporting. For example, if the user is on a diet, a low-calorie meal is suggested. Also, if the user needs to ingest a specific nutrient, a meal containing that nutrient is suggested. Furthermore, if the user is in a specific health condition, a nutritional balance appropriate for that condition is suggested. As a result, a more appropriate nutritional balance can be provided by suggesting a nutritional balance based on the user's current health condition.

[0062] The nutritional analysis unit can propose an optimal nutritional balance in consideration of the user's geographical location information during nutritional analysis. For example, the nutritional analysis unit proposes an optimal nutritional balance in consideration of the user's geographical location information during nutritional analysis. The evaluation of the geographical location information is performed using AI based on the user's current location and regional information. For example, if the user lives in a specific region, a nutritional balance using ingredients from that region is proposed. Also, if the user is traveling, a nutritional balance using ingredients available in the current location is proposed. Furthermore, if the user wants to cook a dish from a specific region, a nutritional balance for that region is proposed. In this way, an optimal nutritional balance can be provided by taking into account the user's geographical location information.

[0063] The service selection unit can select the optimal service when selecting a service by analyzing the user's past usage history. For example, when selecting a service, the service selection unit analyzes the user's past usage history to select the optimal service. The usage history is analyzed using AI based on the user's past purchases and purchase frequency. For example, the optimal service is selected based on services the user has used in the past. In addition, a highly reliable service is preferentially selected from the user's past usage history. Furthermore, the user's past usage history is analyzed to select the most efficient service. In this way, the optimal service can be provided by analyzing the user's past usage history.

[0064] The service selection unit can customize the selection of services based on the user's current living situation when selecting a service. For example, the service selection unit customizes the selection of services based on the user's current living situation when selecting a service. The evaluation of the living situation is performed using AI based on the user's family composition, work situation, etc. For example, if the user is busy, a service that can be quickly responded to is preferentially selected. Also, if the user is health-conscious, a health-related service is selected. Furthermore, if the user has a specific event planned, a service required for the event is selected. In this way, by customizing the selection of services based on the user's current living situation, more appropriate services can be provided.

[0065] The service selection unit can select the optimal service by considering the geographical location information of the user when selecting a service. For example, the service selection unit selects the optimal service by considering the geographical location information of the user when selecting a service. The evaluation of the geographical location information is performed using AI based on the user's current location and regional information. For example, if the user lives in a specific region, a service that can respond quickly in that region is selected. In addition, if the user is traveling, a service that can be used in the current location is selected. Furthermore, if the user wants to purchase a specialty product of a specific region, a service for that region is selected. In this way, the optimal service can be provided by considering the user's geographical location information.

[0066] The service selection unit can adjust the selection of a service by analyzing the social media activity of the user when selecting a service. For example, the service selection unit adjusts the selection of a service by analyzing the social media activity of the user when selecting a service. The analysis of social media activity is performed using AI based on the content of the user's posts and the number of followers. For example, a related service is selected based on products shared by the user on social media. Also, the optimal service is selected based on information on services the user follows on social media. Furthermore, a service is selected based on trends in communities in which the user participates on social media. In this way, related services can be provided by analyzing the user's social media activity.

[0067] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0068] When inputting the user's ingredient information, the reception unit can optimize the input based on the ingredient storage method. For example, refrigerated ingredients are categorized and input by refrigerator shelf. Also, frozen ingredients are categorized and input by freezer drawer. Furthermore, room temperature ingredients are categorized and input by pantry shelf. In this way, by optimizing the input based on the ingredient storage method, the user can manage ingredient information more efficiently.

[0069] The automatic generation unit can analyze the user's past purchasing history and grasp the seasonal food purchasing trends. For example, if there is a tendency to purchase more fresh vegetables in the spring, the spring shopping list will include more vegetables. Also, if there is a tendency to purchase more cold drinks and ice cream in the summer, the summer shopping list will include more of these. Furthermore, if there is a tendency to purchase more hot soups and hot pot ingredients in the winter, the winter shopping list will include more of these. In this way, by grasping the seasonal food purchasing trends, a more appropriate shopping list can be provided.

[0070] The reception unit can preferentially input ingredient information specific to a region, taking into account the geographical location information of the user. For example, if the user lives in Hokkaido, ingredients from Hokkaido are preferentially input. Also, if the user lives in Okinawa, ingredients from Okinawa are preferentially input. Furthermore, if the user wants to make a dish from a specific region, ingredients from that region are preferentially input. In this way, by taking into account the geographical location information of the user, ingredient information specific to a region can be preferentially input.

[0071] The automatic generation unit can customize the contents of the shopping list based on the user's current living situation. For example, if the user is busy, ingredients that are easy to prepare are preferentially added to the list. If the user is health-conscious, ingredients with a balanced nutritional profile are added to the list. Furthermore, if the user is planning a specific event, ingredients needed for the event are added to the list. In this way, a more appropriate list can be provided by customizing the contents of the shopping list based on the user's current living situation.

[0072] The reception unit can analyze the user's social media activity and input related ingredient information. For example, the necessary ingredient information is input based on photos of food shared by the user on social media. Also, related ingredient information is input based on information on cooking accounts the user follows on social media. Furthermore, ingredient information is input based on trends in cooking communities the user participates in on social media. In this way, related ingredient information can be input by analyzing the user's social media activity.

[0073] The process flow of the first embodiment will be briefly described below.

[0074] Step 1: The reception unit receives input of the types and remaining amounts of ingredients that the user has at home. The ingredients input by the user include, for example, vegetables, meat, fish, and seasonings. The reception unit provides an interface for the user to input information about ingredients in the refrigerator, and supports methods such as text input, voice input, and scan input. Step 2: The generation unit uses the generation AI to analyze the ingredient information received by the reception unit and generate an appropriate recipe. The generation AI uses, for example, a text generation AI (e.g., LLM) to generate a recipe based on the ingredient information, and analyzes the ingredient information entered by the user to propose an optimal recipe. Step 3: The automatic generation unit automatically generates a shopping list for the next purchase based on the recipe generated by the generation unit. If an ingredient required for the recipe is missing, the automatic generation unit adds the ingredient to the shopping list. Step 4: The coordinating unit coordinates with the mail-order service based on the shopping list generated by the automatic generation unit and automatically requests delivery. The coordinating unit orders the necessary ingredients on the mail-order site based on the shopping list and requests that they be delivered to the customer's home.

[0075] (Example 2) A recipe advice system according to an embodiment of the present invention is a system that advises a user on an appropriate recipe based on information on ingredients that the user has at home. In this recipe advice system, the user inputs the type and remaining amount of ingredients, and the generation AI analyzes the information to provide a recipe that corresponds to the ingredients. Furthermore, this system automatically generates a next shopping list from the user's ingredient information. Since the system also provides a function to automatically request delivery in cooperation with a mail-order service, it brings great convenience to users who are busy at work. For example, a user inputs the type and remaining amount of ingredients that the user has at home into the system. For example, information on vegetables, meat, seasonings, etc. in the refrigerator is input. This information is accepted by the reception unit. Next, the generation AI analyzes the information accepted by the reception unit. The generation AI generates an appropriate recipe based on the input ingredient information. For example, it proposes a recipe for a dish that can be made using ingredients in the refrigerator. This recipe is generated by the generation unit. Based on the generated recipe, the next shopping list is automatically generated. For example, if an ingredient required for a recipe is missing, that ingredient is added to the shopping list. This shopping list is generated by the automatic generation unit. Furthermore, based on the automatically generated shopping list, the system cooperates with a mail-order service to automatically request delivery. For example, a user orders the necessary ingredients based on a shopping list from an online shopping site and requests that they be delivered to his / her home. This linking is performed by the linking unit. This system allows the user to make effective use of ingredients at home and easily obtain appropriate recipes. In addition, the next shopping list is automatically generated and delivery requests are automatically made in cooperation with the online shopping service, providing great convenience for busy users. As a result, the recipe advice system can provide appropriate recipes based on the user's ingredient information, and convenience can be improved by the automatic generation of shopping lists and the linking with the online shopping service.

[0076] The recipe advice system according to the embodiment includes a reception unit, a generation unit, an automatic generation unit, and a linking unit. The reception unit receives input of the type and remaining amount of ingredients held by the user at home. The ingredients input by the user include, but are not limited to, vegetables, meat, fish, seasonings, and the like. The reception unit provides, for example, an interface for the user to input information on ingredients in the refrigerator. The interface supports methods such as text input, voice input, and scan input. The generation unit uses a generation AI to analyze the ingredient information received by the reception unit and generate an appropriate recipe. The generation AI generates a recipe based on the ingredient information, for example, using a text generation AI (for example, LLM). The generation AI analyzes the ingredient information input by the user and suggests an optimal recipe. For example, the generation AI receives a prompt such as "Please suggest a recipe for a dish that can be made using ingredients in the refrigerator" and generates a recipe. The automatic generation unit automatically generates a shopping list for the next time based on the recipe generated by the generation unit. For example, if an ingredient required for a recipe is in short supply, the automatic generation unit adds the ingredient to the shopping list. The automatic generation unit uses a generation AI to generate a shopping list based on the recipe. The linking unit links with a mail order service based on the shopping list generated by the automatic generation unit and automatically requests delivery. The linking unit, for example, orders necessary ingredients from a mail order site based on the shopping list and requests that they be delivered to the home. The linking unit links with the mail order service using the generation AI. In this way, the recipe advice system according to the embodiment can provide appropriate recipes based on the user's ingredient information, and improve convenience through the automatic generation of a shopping list and the linking with the mail order service.

[0077] The reception unit receives input of the type and remaining amount of ingredients that the user has at home. The ingredients input by the user include, but are not limited to, vegetables, meat, fish, and seasonings. The reception unit provides, for example, an interface for the user to input information about ingredients in the refrigerator. The interface supports methods such as text input, voice input, and scan input. Specifically, in text input, the user can input the name of the ingredient and its remaining amount using a keyboard. In voice input, the user speaks the ingredient name and remaining amount into a microphone, and the voice is automatically converted into text using voice recognition technology. In scan input, the ingredient information is automatically obtained by scanning a barcode or two-dimensional code (e.g., QR code) reader printed on the ingredient package, thereby allowing the user to input ingredient information easily and quickly. In addition, the reception unit stores the input ingredient information in a database so that it can be referenced later. For example, the current inventory status of ingredients can be confirmed based on ingredient information input by the user in the past. Furthermore, the reception unit analyzes the ingredient information input by the user and provides basic data for suggesting appropriate recipes based on the type and remaining amount of the ingredient. This allows the reception unit to improve convenience for the user and increase the efficiency of the entire system.

[0078] The generation unit uses the generation AI to analyze the ingredient information received by the reception unit and generate an appropriate recipe. The generation AI generates a recipe based on the ingredient information, for example, using a text generation AI (e.g., LLM). The generation AI analyzes the ingredient information input by the user and proposes an optimal recipe. Specifically, the generation AI receives the ingredient information input by the user as a prompt and generates a recipe based on that information. For example, when the generation AI receives a prompt such as "Please suggest a recipe for a dish that can be made using ingredients in the refrigerator," the generation AI generates an appropriate recipe while referring to an internal database and past recipe data. The generation AI can propose a recipe that suits the user's preferences by taking into account the combination of ingredients, cooking method, and use of seasonings. Furthermore, the generation AI can also propose a more personalized recipe based on the user's past input history and evaluation. For example, if the user has given a high rating to a recipe in the past or has a tendency to prefer specific ingredients, the generation AI generates a recipe taking that information into consideration. This allows the generation unit to provide an optimal recipe that meets the user's needs and increase the user's satisfaction.

[0079] The automatic generation unit automatically generates the next shopping list based on the recipe generated by the generation unit. For example, if an ingredient required for a recipe is missing, the automatic generation unit adds the ingredient to the shopping list. Specifically, the automatic generation unit lists all ingredients included in the generated recipe and identifies the missing ingredients by comparing them with ingredients already owned by the user. For example, if a recipe requires "tomatoes" and the user already owns tomatoes, the ingredient is not added to the shopping list. On the other hand, if the user does not own "basil," the ingredient is added to the shopping list. The automatic generation unit uses a generation AI to generate a shopping list based on the recipe. The generation AI not only analyzes the contents of the recipe and creates a list of necessary ingredients, but also optimizes the list by taking into account the amount and type of ingredients. For example, if there is an ingredient that is commonly used in multiple recipes, the amount of the ingredient required is added up and reflected in the list. It is also possible to customize the shopping list by taking into account the user's past shopping history and consumption patterns. In this way, the automatic generation unit supports the user in shopping efficiently and reduces unnecessary shopping.

[0080] The linking unit links with the mail-order service based on the shopping list generated by the automatic generation unit and automatically requests delivery. For example, the linking unit orders the necessary ingredients on a mail-order site based on the shopping list and requests that they be delivered to the user's home. Specifically, the linking unit links with the mail-order service using the generation AI. The generation AI analyzes the contents of the shopping list and selects the optimal mail-order site and store. For example, it can select the store where a specific ingredient can be purchased at the lowest price or the mail-order site with the shortest delivery time. The linking unit automatically places an order with the selected mail-order site and arranges for the ingredients to be delivered to the user's home. In addition, the linking unit also has a function to notify the user of the progress of the order and the scheduled delivery time. For example, it sends a notification to the user when the order is confirmed, and sends a reminder when the scheduled delivery time approaches. This allows the user to grasp the order status in real time and wait for the ingredients to be received with peace of mind. The linking unit can also make optimal suggestions for the next order based on the user's past order history and ratings. As a result, the linking unit can greatly improve user convenience and increase the efficiency of the entire system.

[0081] The reception unit may include a freshness determination unit based on the freshness and expiration date of the ingredients. The reception unit may include, for example, a freshness determination unit for taking into account the freshness and expiration date of the ingredients. The freshness determination unit may use a sensor or algorithm for evaluating the freshness of the ingredients. For example, the freshness determination unit may evaluate the freshness based on information such as the color, smell, and hardness of the ingredients. The freshness determination unit may use AI to evaluate the freshness of the ingredients. For example, the freshness determination unit may input image data of the ingredients into AI to evaluate the freshness. This allows for more appropriate recipe suggestions by taking into account the freshness and expiration date of the ingredients.

[0082] The generation unit can include a history analysis unit that suggests a favorite recipe based on the user's past usage history. The generation unit includes, for example, a history analysis unit that suggests a favorite recipe based on the user's past usage history. The history analysis unit analyzes the user's past recipe selections and cooking history to understand the user's preferences. The history analysis unit can analyze the user's usage history using AI. For example, the history analysis unit inputs the user's past recipe selection data into AI to suggest a favorite recipe. This makes it possible to improve user satisfaction by suggesting a favorite recipe based on the user's past usage history.

[0083] The generation unit can include a nutritional analysis unit based on nutritional balance and calories. The generation unit includes, for example, a nutritional analysis unit for taking into account nutritional balance and calories. The nutritional analysis unit can use an algorithm for evaluating the nutritional balance and calories of a recipe. For example, the nutritional analysis unit evaluates a recipe based on the recommended intake amount and balancing method of each nutrient. The nutritional analysis unit can evaluate the nutritional balance and calories of a recipe using AI. For example, the nutritional analysis unit inputs nutritional data of a recipe into AI to evaluate nutritional balance and calories. This makes it possible to propose recipes that take into account nutritional balance and calories.

[0084] The linking unit may include a service selection unit for allowing a plurality of mail-order services to be selected. The linking unit may include, for example, a service selection unit for allowing a plurality of mail-order services to be selected. The service selection unit provides an interface for a user to select an optimal service from a plurality of available mail-order services. The service selection unit may use AI to analyze information on the plurality of mail-order services and select an optimal service. For example, the service selection unit may select a mail-order service based on criteria such as price, delivery time, and user evaluation. This allows a user to select a plurality of mail-order services, thereby improving convenience for the user.

[0085] The reception unit can estimate the user's emotion and adjust the timing of inputting the ingredient information based on the estimated emotion of the user. The reception unit, for example, estimates the user's emotion and adjusts the timing of inputting the ingredient information based on the estimated emotion of the user. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, the system simplifies the input of the ingredient information so that it can be completed in a short time. Also, when the user is relaxed, detailed input options are provided so that the user can input while enjoying it. Furthermore, when the user is in a hurry, voice input is prioritized so that the ingredient information can be input quickly. This allows more appropriate input by adjusting the timing of inputting the ingredient information according to the user's emotion.

[0086] The reception unit can analyze the user's past ingredient input history and select an appropriate input method. The reception unit, for example, analyzes the user's past ingredient input history and selects the optimal input method. The input method includes, but is not limited to, for example, voice input, touch input, and scan input. The reception unit can use AI to analyze the user's past input history and select the optimal input method. For example, ingredients that the user frequently input in the past are automatically displayed as candidates. In addition, the reception unit preferentially suggests input methods (voice, text, etc.) that the user used in the past. Furthermore, the reception unit predicts and suggests ingredients to be used in a specific time period from the user's past input history. This improves input efficiency by selecting the optimal input method based on the user's past input history.

[0087] The reception unit can filter the food ingredient information based on the user's current meal plan and health condition when the food ingredient information is input. For example, the reception unit filters the food ingredient information based on the user's current meal plan and health condition when the food ingredient information is input. The filtering is performed using AI based on the user's meal plan and health condition. For example, if the user is on a diet, filtering is performed so that low-calorie food ingredients are preferentially input. In addition, if the user needs to ingest a specific nutrient, filtering is performed so that food ingredients containing that nutrient are preferentially input. Furthermore, if the user has a specific allergy, filtering is performed so that food ingredients containing that allergen are excluded. This allows for more appropriate input by filtering food ingredient information based on the user's meal plan and health condition.

[0088] The reception unit can estimate the user's emotion and determine the priority of the ingredient information to be input based on the estimated user's emotion. The reception unit, for example, estimates the user's emotion and determines the priority of the ingredient information to be input based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, the system prioritizes input of important ingredient information. Also, when the user is relaxed, the system prompts the user to input detailed ingredient information. Furthermore, when the user is in a hurry, the system prioritizes input of the minimum necessary ingredient information. This allows more appropriate input by determining the priority of ingredient information according to the user's emotion.

[0089] The reception unit can prioritize inputting highly relevant ingredient information in consideration of the geographical location information of the user when inputting ingredient information. For example, the reception unit prioritizes inputting highly relevant ingredient information in consideration of the geographical location information of the user when inputting ingredient information. The geographical location information is analyzed using AI based on the user's current location and regional information. For example, if the user lives in a specific region, ingredients that are easily available in that region are prioritized for input. Also, if the user is traveling, ingredients that are available at the current location are prioritized for input. Furthermore, if the user wants to make a dish from a specific region, ingredients from that region are prioritized for input. In this way, highly relevant ingredient information can be prioritized for input by considering the geographical location information of the user.

[0090] The reception unit can analyze the user's social media activity when inputting ingredient information and input related ingredient information. For example, the reception unit analyzes the user's social media activity when inputting ingredient information and inputs related ingredient information. Social media activity is analyzed using AI to analyze the content of the user's posts and the number of followers. For example, the necessary ingredient information is input based on photos of food shared by the user on social media. Also, related ingredient information is input based on information on cooking accounts the user follows on social media. Furthermore, ingredient information is input based on trends in cooking communities in which the user participates on social media. In this way, related ingredient information can be input by analyzing the user's social media activity.

[0091] The generation unit can estimate the user's emotion and adjust the way of expressing the recipe based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the way of expressing the recipe based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is relaxed, a recipe including detailed steps and explanations is generated. Also, when the user is in a hurry, a concise and to the point recipe is generated. Furthermore, when the user is excited, a visually attractive recipe is generated. This allows a more appropriate recipe to be provided by adjusting the way of expressing the recipe according to the user's emotion.

[0092] The generation unit can adjust the level of detail of the recipe based on the priority of the ingredients when generating the recipe. For example, the generation unit adjusts the level of detail of the recipe based on the priority of the ingredients when generating the recipe. The adjustment of the level of detail is performed using AI based on the importance and frequency of use of the ingredients. For example, detailed cooking steps for main ingredients are provided. Also, concise explanations are provided for supplementary ingredients. Furthermore, details of cooking time and temperature are adjusted according to the importance of the ingredients. In this way, a more appropriate recipe can be provided by adjusting the level of detail of the recipe based on the importance of the ingredients.

[0093] The generation unit can apply different recipe generation algorithms depending on the category of ingredients when generating a recipe. For example, the generation unit applies different recipe generation algorithms depending on the category of ingredients when generating a recipe. The recipe generation algorithm is applied using AI depending on the category of ingredients. For example, a health-oriented algorithm is applied to a recipe whose main ingredient is vegetables. Also, an algorithm that provides a sense of volume is applied to a recipe whose main ingredient is meat. Furthermore, an algorithm that emphasizes sweetness and appearance is applied to a recipe whose main ingredient is dessert. In this way, by applying different recipe generation algorithms depending on the category of ingredients, more appropriate recipes can be provided.

[0094] The generation unit can estimate the user's emotion and adjust the length of the recipe based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the length of the recipe based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is in a hurry, a short and to the point recipe is generated. Also, when the user is relaxed, a longer recipe including detailed explanations is generated. Furthermore, when the user is excited, a recipe with a visually stimulating effect is generated. In this way, a more appropriate recipe can be provided by adjusting the length of the recipe according to the user's emotion.

[0095] The generation unit can determine the priority of recipes based on the acquisition time of ingredients when generating recipes. For example, the generation unit determines the priority of recipes based on the acquisition time of ingredients when generating recipes. The acquisition time is evaluated using AI based on the purchase date or harvest date of ingredients. For example, recipes using seasonal ingredients are preferentially generated. Also, recipes using ingredients with an approaching expiration date are preferentially generated. Furthermore, recipes using ingredients recently purchased by the user are preferentially generated. In this way, more appropriate recipes can be provided by determining the priority of recipes based on the acquisition time of ingredients.

[0096] The generation unit can adjust the order of the recipe based on the relevance of ingredients when generating the recipe. For example, the generation unit adjusts the order of the recipe based on the relevance of ingredients when generating the recipe. The evaluation of the relevance is performed using AI based on the combination of ingredients and commonalities in cooking methods. For example, a recipe that uses a main ingredient first is generated. Also, a recipe that uses a supplementary ingredient later is generated. Furthermore, the order of cooking steps is adjusted based on the relevance of ingredients. In this way, a more appropriate recipe can be provided by adjusting the order of the recipe based on the relevance of ingredients.

[0097] The automatic generation unit can estimate the user's emotions and adjust the generation method of the shopping list based on the estimated user's emotions. The automatic generation unit, for example, estimates the user's emotions and adjusts the generation method of the shopping list based on the estimated user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is relaxed, a detailed shopping list is generated. Also, when the user is in a hurry, a minimum necessary shopping list is generated. Furthermore, when the user is excited, a visually attractive shopping list is generated. As a result, a more appropriate list can be provided by adjusting the generation method of the shopping list according to the user's emotions.

[0098] The automatic generation unit can generate an optimal list by analyzing the user's past purchase history when generating a shopping list. For example, the automatic generation unit generates an optimal list by analyzing the user's past purchase history when generating a shopping list. The analysis of the purchase history is performed using AI based on the user's past purchases and purchase frequency. For example, an optimal shopping list is generated based on ingredients purchased by the user in the past. Also, frequently purchased ingredients are added to the list with priority from the user's past purchase history. Furthermore, the user's past purchase history is analyzed, and necessary ingredients are predicted and added to the list. In this way, an optimal shopping list can be provided by analyzing the user's past purchase history.

[0099] The automatic generation unit can customize the contents of the shopping list based on the user's current living situation when generating the shopping list. For example, the automatic generation unit customizes the contents of the list based on the user's current living situation when generating the shopping list. The evaluation of the living situation is performed using AI based on the user's family composition, work situation, etc. For example, if the user is busy, ingredients that are easy to cook are preferentially added to the list. Also, if the user is health-conscious, ingredients with a balanced nutritional content are added to the list. Furthermore, if the user is planning a specific event, ingredients necessary for the event are added to the list. In this way, a more appropriate shopping list can be provided by customizing the contents of the list based on the user's current living situation.

[0100] The automatic generation unit can estimate the user's emotions and determine the priority of the shopping list based on the estimated user's emotions. The automatic generation unit, for example, estimates the user's emotions and determines the priority of the shopping list based on the estimated user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is feeling stressed, important ingredients are preferentially added to the list. Also, when the user is relaxed, a detailed shopping list is generated. Furthermore, when the user is in a hurry, the minimum necessary ingredients are preferentially added to the list. In this way, a more appropriate list can be provided by determining the priority of the shopping list according to the user's emotions.

[0101] The automatic generation unit can generate an optimal shopping list by taking into consideration the geographical location information of the user when generating the shopping list. For example, the automatic generation unit generates an optimal list by taking into consideration the geographical location information of the user when generating a shopping list. The geographical location information is analyzed based on the user's current location and regional information using AI. For example, if the user lives in a specific region, ingredients that are easily available in that region are added to the list. Also, if the user is traveling, ingredients that are available in the current location are added to the list. Furthermore, if the user wants to cook a dish from a specific region, ingredients from that region are added to the list. In this way, an optimal shopping list can be provided by taking into consideration the geographical location information of the user.

[0102] The automatic generation unit can adjust the contents of the shopping list by analyzing the user's social media activity when generating the shopping list. For example, the automatic generation unit adjusts the contents of the list by analyzing the user's social media activity when generating a shopping list. Social media activity is analyzed using AI to analyze the content of the user's posts and the number of followers. For example, necessary ingredients are added to the list based on photos of dishes shared by the user on social media. Also, related ingredients are added to the list based on information on cooking accounts that the user follows on social media. Furthermore, ingredients are added to the list based on trends in cooking communities that the user participates in on social media. In this way, related ingredients can be added to the list by analyzing the user's social media activity.

[0103] The linking unit can estimate the user's emotions and adjust the selection method of the mail-order service based on the estimated user's emotions. The linking unit, for example, estimates the user's emotions and adjusts the selection method of the mail-order service based on the estimated user's emotions. The estimation of emotions is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, a reliable mail-order service is preferentially selected. Also, when the user is relaxed, the most suitable mail-order service is selected by comparing prices and service contents. Furthermore, when the user is in a hurry, a mail-order service that can deliver quickly is preferentially selected. In this way, a more appropriate service can be provided by adjusting the selection method of the mail-order service according to the user's emotions.

[0104] The linking unit can select the optimal service by analyzing the user's past usage history when linking with a mail-order service. For example, when linking with a mail-order service, the linking unit analyzes the user's past usage history and selects the optimal service. The usage history is analyzed using AI based on the user's past purchases and purchase frequency. For example, the optimal service is selected based on the mail-order services the user has used in the past. In addition, the most reliable services are preferentially selected from the user's past usage history. Furthermore, the user's past usage history is analyzed to select the most efficient service. In this way, the optimal mail-order service can be provided by analyzing the user's past usage history.

[0105] The linking unit can customize the selection of services based on the user's current living situation when linking with a mail-order service. For example, when linking with a mail-order service, the linking unit customizes the selection of services based on the user's current living situation. The evaluation of the living situation is performed using AI based on the user's family structure, work situation, etc. For example, if the user is busy, a service that can deliver quickly is selected with priority. Also, if the user is health-conscious, a service that handles organic foods is selected. Furthermore, if the user is planning a specific event, a service that handles products necessary for the event is selected. In this way, by customizing the selection of services based on the user's current living situation, more appropriate services can be provided.

[0106] The linking unit can estimate the user's emotion and determine the priority of mail-order services based on the estimated user's emotion. The linking unit, for example, estimates the user's emotion and determines the priority of mail-order services based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, a highly reliable service is selected with priority. Also, when the user is relaxed, the price and service content are compared to select the optimal service. Furthermore, when the user is in a hurry, a service that can be delivered quickly is selected with priority. In this way, a more appropriate service can be provided by determining the priority of mail-order services according to the user's emotion.

[0107] The linking unit can select the optimal service in consideration of the geographical location information of the user when linking with a mail-order service. For example, the linking unit selects the optimal service in consideration of the geographical location information of the user when linking with a mail-order service. The geographical location information is analyzed using AI based on the user's current location and regional information. For example, if the user lives in a specific region, a service that can deliver quickly in that region is selected. Also, if the user is traveling, a service that can be used in the current location is selected. Furthermore, if the user wants to purchase a specialty product of a specific region, a mail-order service for that region is selected. In this way, the optimal mail-order service can be provided by taking into account the user's geographical location information.

[0108] The linking unit can adjust the selection of a service by analyzing the user's social media activity when linking with a mail-order service. For example, when linking with a mail-order service, the linking unit analyzes the user's social media activity and adjusts the selection of a service. Social media activity is analyzed using AI to analyze the content of the user's posts and the number of followers. For example, a related mail-order service is selected based on products shared by the user on social media. Also, the optimal service is selected based on information about mail-order services the user follows on social media. Furthermore, a service is selected based on trends in communities in which the user participates on social media. In this way, related mail-order services can be provided by analyzing the user's social media activity.

[0109] The freshness determination unit can estimate the user's emotions and adjust the freshness determination criteria for ingredients based on the estimated user's emotions. The freshness determination unit, for example, estimates the user's emotions and adjusts the freshness determination criteria for ingredients based on the estimated user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, a strict freshness determination criterion is applied. Also, when the user is relaxed, a flexible freshness determination criterion is applied. Furthermore, when the user is in a hurry, a criterion for quickly determining freshness is applied. This allows for more appropriate freshness determination by adjusting the freshness determination criterion according to the user's emotions.

[0110] The freshness determination unit can evaluate the freshness based on the storage method of the food ingredient when determining the freshness. For example, the freshness determination unit evaluates the freshness based on the storage method of the food ingredient when determining the freshness. The evaluation of the storage method is performed using AI based on the storage state and storage period of the food ingredient. For example, the freshness of food ingredients stored in a refrigerator is evaluated. The freshness of food ingredients stored frozen is also evaluated. Furthermore, the freshness of food ingredients stored at room temperature is evaluated. As a result, by evaluating the freshness based on the storage method of the food ingredient, more accurate freshness determination is possible.

[0111] The freshness determination unit can evaluate the freshness based on the purchase date and frequency of use of the ingredients when determining freshness. The freshness determination unit, for example, evaluates the freshness based on the purchase date and frequency of use of the ingredients when determining freshness. The evaluation of the purchase date and frequency of use is performed using AI based on the purchase history and use history of the ingredients. For example, the freshness of ingredients with a recent purchase date is rated high. Also, the freshness of ingredients with a high frequency of use is rated high. Furthermore, the freshness of ingredients with an old purchase date is rated low. This allows for more accurate freshness determination by evaluating the freshness based on the purchase date and frequency of use of the ingredients.

[0112] The freshness determination unit can estimate the user's emotion and determine the priority of freshness determination based on the estimated user's emotion. The freshness determination unit, for example, estimates the user's emotion and determines the priority of freshness determination based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, the freshness of important ingredients is determined with priority. Also, when the user is relaxed, a detailed freshness determination is performed. Furthermore, when the user is in a hurry, the freshness is quickly determined. As a result, by determining the priority of freshness determination according to the user's emotion, more appropriate freshness determination is possible.

[0113] The freshness determination unit can evaluate freshness taking into account the geographical origin information of the food ingredient when determining freshness. For example, the freshness determination unit evaluates freshness taking into account the geographical origin information of the food ingredient when determining freshness. The evaluation of the geographical origin information is performed using AI based on the food ingredient's place of origin and transportation route. For example, the freshness of locally produced food ingredients is highly rated. In addition, the freshness of imported food ingredients is carefully evaluated. Furthermore, the freshness of specialty products from a specific region is highly rated. This allows for more accurate freshness determination by taking into account the geographical origin information of the food ingredient.

[0114] The history analysis unit can estimate the user's emotion and adjust the method of history analysis based on the estimated user's emotion. The history analysis unit, for example, estimates the user's emotion and adjusts the method of history analysis based on the estimated user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, a concise analysis result is provided. Also, when the user is relaxed, a detailed analysis result is provided. Furthermore, when the user is in a hurry, an analysis result is provided quickly. In this way, by adjusting the method of history analysis according to the user's emotion, a more appropriate analysis result can be provided.

[0115] The history analysis unit can analyze the user's past recipe usage history during history analysis to suggest the optimal recipe. For example, the history analysis unit analyzes the user's past recipe usage history during history analysis to suggest the optimal recipe. The analysis of the recipe usage history is performed using AI based on the user's past recipe selections and cooking history. For example, the optimal recipe is suggested based on recipes the user has used in the past. In addition, the user's favorite recipes are preferentially suggested based on the user's past recipe usage history. Furthermore, the user's past recipe usage history is analyzed to suggest a wide variety of recipes. In this way, the optimal recipe can be provided by analyzing the user's past recipe usage history.

[0116] The history analysis unit can suggest recipes based on the user's current meal plan when analyzing the history. For example, the history analysis unit suggests recipes based on the user's current meal plan when analyzing the history. The meal plan is evaluated using AI based on the user's current meal plan and nutritional balance. For example, if the user is on a diet, low-calorie recipes are suggested. Also, if the user needs to ingest a specific nutrient, recipes containing that nutrient are suggested. Furthermore, if the user is planning a specific event, recipes suitable for that event are suggested. This makes it possible to provide more appropriate recipes by suggesting recipes based on the user's current meal plan.

[0117] The history analysis unit can estimate the user's emotions and determine the priority of history analysis based on the estimated user's emotions. The history analysis unit, for example, estimates the user's emotions and determines the priority of history analysis based on the estimated user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, important history is analyzed preferentially. Also, when the user is relaxed, detailed history analysis is performed. Furthermore, when the user is in a hurry, history analysis is performed quickly. In this way, by determining the priority of history analysis according to the user's emotions, more appropriate analysis results can be provided.

[0118] The history analysis unit can suggest optimal recipes taking into account the geographical location information of the user when analyzing the history. For example, the history analysis unit suggests optimal recipes taking into account the geographical location information of the user when analyzing the history. The evaluation of the geographical location information is performed using AI based on the user's current location and regional information. For example, if the user lives in a specific region, recipes using ingredients from that region are suggested. Also, if the user is traveling, recipes using ingredients available in the current location are suggested. Furthermore, if the user wants to make a dish from a specific region, recipes from that region are suggested. In this way, optimal recipes can be provided by taking into account the geographical location information of the user.

[0119] The nutritional analysis unit can estimate the user's emotions and adjust the method of nutritional analysis based on the estimated user's emotions. The nutritional analysis unit, for example, estimates the user's emotions and adjusts the method of nutritional analysis based on the estimated user's emotions. The estimation of emotions is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, a concise nutritional analysis result is provided. Also, when the user is relaxed, a detailed nutritional analysis result is provided. Furthermore, when the user is in a hurry, a quick nutritional analysis result is provided. This allows a more appropriate analysis result to be provided by adjusting the method of nutritional analysis according to the user's emotions.

[0120] The nutritional analysis unit can analyze the user's past meal history during nutritional analysis to suggest an optimal nutritional balance. For example, the nutritional analysis unit analyzes the user's past meal history during nutritional analysis to suggest an optimal nutritional balance. Analysis of the meal history is performed using AI based on the user's past meal contents and ingested nutrients. For example, an optimal nutritional balance is suggested based on the nutrients the user has ingested in the past. In addition, a nutritionally balanced meal is suggested based on the user's past meal history. Furthermore, the user's past meal history is analyzed to suggest a meal that supplements necessary nutrients. In this way, an optimal nutritional balance can be provided by analyzing the user's past meal history.

[0121] The nutritional analysis unit can suggest a nutritional balance based on the user's current health condition during nutritional analysis. The nutritional analysis unit, for example, suggests a nutritional balance based on the user's current health condition during nutritional analysis. The health condition is evaluated using AI based on the user's medical data and self-reporting. For example, if the user is on a diet, a low-calorie meal is suggested. Also, if the user needs to ingest a specific nutrient, a meal containing that nutrient is suggested. Furthermore, if the user is in a specific health condition, a nutritional balance appropriate for that condition is suggested. As a result, a more appropriate nutritional balance can be provided by suggesting a nutritional balance based on the user's current health condition.

[0122] The nutritional analysis unit can estimate the user's emotions and determine the priority of nutritional analysis based on the estimated user's emotions. The nutritional analysis unit, for example, estimates the user's emotions and determines the priority of nutritional analysis based on the estimated user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, important nutrients are analyzed preferentially. Also, when the user is relaxed, detailed nutritional analysis is performed. Furthermore, when the user is in a hurry, nutritional analysis is performed quickly. In this way, by determining the priority of nutritional analysis according to the user's emotions, more appropriate analysis results can be provided.

[0123] The nutritional analysis unit can propose an optimal nutritional balance in consideration of the user's geographical location information during nutritional analysis. For example, the nutritional analysis unit proposes an optimal nutritional balance in consideration of the user's geographical location information during nutritional analysis. The evaluation of the geographical location information is performed using AI based on the user's current location and regional information. For example, if the user lives in a specific region, a nutritional balance using ingredients from that region is proposed. Also, if the user is traveling, a nutritional balance using ingredients available in the current location is proposed. Furthermore, if the user wants to cook a dish from a specific region, a nutritional balance for that region is proposed. In this way, an optimal nutritional balance can be provided by taking into account the user's geographical location information.

[0124] The service selection unit can estimate the user's emotion and adjust the service selection method based on the estimated user's emotion. The service selection unit, for example, estimates the user's emotion and adjusts the service selection method based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, a highly reliable service is preferentially selected. Also, when the user is relaxed, the price and service content are compared to select the optimal service. Furthermore, when the user is in a hurry, a service that can be quickly responded to is preferentially selected. In this way, a more appropriate service can be provided by adjusting the service selection method according to the user's emotion.

[0125] The service selection unit can select the optimal service when selecting a service by analyzing the user's past usage history. For example, when selecting a service, the service selection unit analyzes the user's past usage history to select the optimal service. The usage history is analyzed using AI based on the user's past purchases and purchase frequency. For example, the optimal service is selected based on services the user has used in the past. In addition, a highly reliable service is preferentially selected from the user's past usage history. Furthermore, the user's past usage history is analyzed to select the most efficient service. In this way, the optimal service can be provided by analyzing the user's past usage history.

[0126] The service selection unit can customize the selection of services based on the user's current living situation when selecting a service. For example, the service selection unit customizes the selection of services based on the user's current living situation when selecting a service. The evaluation of the living situation is performed using AI based on the user's family composition, work situation, etc. For example, if the user is busy, a service that can be quickly responded to is preferentially selected. Also, if the user is health-conscious, a health-related service is selected. Furthermore, if the user has a specific event planned, a service required for the event is selected. In this way, by customizing the selection of services based on the user's current living situation, more appropriate services can be provided.

[0127] The service selection unit can estimate the user's emotion and determine the priority order of service selection based on the estimated user's emotion. The service selection unit, for example, estimates the user's emotion and determines the priority order of service selection based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is stressed, a highly reliable service is preferentially selected. Also, when the user is relaxed, the price and service content are compared to select the optimal service. Furthermore, when the user is in a hurry, a service that can be quickly responded to is preferentially selected. In this way, a more appropriate service can be provided by determining the priority order of service selection according to the user's emotion.

[0128] The service selection unit can select the optimal service by considering the geographical location information of the user when selecting a service. For example, the service selection unit selects the optimal service by considering the geographical location information of the user when selecting a service. The evaluation of the geographical location information is performed using AI based on the user's current location and regional information. For example, if the user lives in a specific region, a service that can respond quickly in that region is selected. In addition, if the user is traveling, a service that can be used in the current location is selected. Furthermore, if the user wants to purchase a specialty product of a specific region, a service for that region is selected. In this way, the optimal service can be provided by considering the user's geographical location information.

[0129] The service selection unit can adjust the selection of a service by analyzing the social media activity of the user when selecting a service. For example, the service selection unit adjusts the selection of a service by analyzing the social media activity of the user when selecting a service. The analysis of social media activity is performed using AI based on the content of the user's posts and the number of followers. For example, a related service is selected based on products shared by the user on social media. Also, the optimal service is selected based on information on services the user follows on social media. Furthermore, a service is selected based on trends in communities in which the user participates on social media. In this way, related services can be provided by analyzing the user's social media activity.

[0130] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0131] When inputting the user's ingredient information, the reception unit can optimize the input based on the ingredient storage method. For example, refrigerated ingredients are categorized and input by refrigerator shelf. Also, frozen ingredients are categorized and input by freezer drawer. Furthermore, room temperature ingredients are categorized and input by pantry shelf. In this way, by optimizing the input based on the ingredient storage method, the user can manage ingredient information more efficiently.

[0132] The generation unit can estimate the user's emotions and adjust the difficulty of the recipe based on the estimated user's emotions. For example, if the user is stressed, a simple and easy recipe is suggested. If the user is relaxed, a slightly more time-consuming recipe is suggested. If the user is excited, a challenging recipe is suggested. In this way, the difficulty of the recipe can be adjusted according to the user's emotions, making it possible to provide more appropriate recipes.

[0133] The automatic generation unit can analyze the user's past purchasing history and grasp the seasonal food purchasing trends. For example, if there is a tendency to purchase more fresh vegetables in the spring, the spring shopping list will include more vegetables. Also, if there is a tendency to purchase more cold drinks and ice cream in the summer, the summer shopping list will include more of these. Furthermore, if there is a tendency to purchase more hot soups and hot pot ingredients in the winter, the winter shopping list will include more of these. In this way, by grasping the seasonal food purchasing trends, a more appropriate shopping list can be provided.

[0134] The linking unit can estimate the user's emotions and adjust the selection criteria for mail-order services based on the estimated user's emotions. For example, if the user is stressed, a highly reliable mail-order service is preferentially selected. If the user is relaxed, the optimal mail-order service is selected by comparing prices and service contents. Furthermore, if the user is in a hurry, a mail-order service that can deliver quickly is preferentially selected. In this way, by adjusting the selection criteria for mail-order services according to the user's emotions, more appropriate services can be provided.

[0135] The reception unit can preferentially input ingredient information specific to a region, taking into account the geographical location information of the user. For example, if the user lives in Hokkaido, ingredients from Hokkaido are preferentially input. Also, if the user lives in Okinawa, ingredients from Okinawa are preferentially input. Furthermore, if the user wants to make a dish from a specific region, ingredients from that region are preferentially input. In this way, by taking into account the geographical location information of the user, ingredient information specific to a region can be preferentially input.

[0136] The generator can estimate the user's emotions and adjust the way in which the recipe is presented based on the estimated user's emotions. For example, if the user is relaxed, a recipe including detailed steps and instructions is generated. If the user is in a hurry, a concise recipe that is to the point is generated. If the user is excited, a visually appealing recipe is generated. In this way, a more appropriate recipe can be provided by adjusting the way in which the recipe is presented depending on the user's emotions.

[0137] The automatic generation unit can customize the contents of the shopping list based on the user's current living situation. For example, if the user is busy, ingredients that are easy to prepare are preferentially added to the list. If the user is health-conscious, ingredients with a balanced nutritional profile are added to the list. Furthermore, if the user is planning a specific event, ingredients needed for the event are added to the list. In this way, a more appropriate list can be provided by customizing the contents of the shopping list based on the user's current living situation.

[0138] The linking unit can estimate the user's emotions and determine the priority order of mail order services based on the estimated user's emotions. For example, if the user is feeling stressed, a highly reliable service is selected with priority. If the user is relaxed, the optimal service is selected by comparing prices and service contents. Furthermore, if the user is in a hurry, a service that can deliver quickly is selected with priority. In this way, by determining the priority order of mail order services according to the user's emotions, more appropriate services can be provided.

[0139] The reception unit can analyze the user's social media activity and input related ingredient information. For example, the necessary ingredient information is input based on photos of food shared by the user on social media. Also, related ingredient information is input based on information on cooking accounts the user follows on social media. Furthermore, ingredient information is input based on trends in cooking communities the user participates in on social media. In this way, related ingredient information can be input by analyzing the user's social media activity.

[0140] The generation unit can estimate the user's emotions and adjust the length of the recipe based on the estimated user's emotions. For example, if the user is in a hurry, a short recipe that gets to the point is generated. If the user is relaxed, a longer recipe with detailed explanations is generated. If the user is excited, a recipe with visually stimulating effects is generated. In this way, a more appropriate recipe can be provided by adjusting the length of the recipe according to the user's emotions.

[0141] The process flow of the second embodiment will be briefly described below.

[0142] Step 1: The reception unit receives input of the types and remaining amounts of ingredients that the user has at home. The ingredients input by the user include, for example, vegetables, meat, fish, and seasonings. The reception unit provides an interface for the user to input information about ingredients in the refrigerator, and supports methods such as text input, voice input, and scan input. Step 2: The generation unit uses the generation AI to analyze the ingredient information received by the reception unit and generate an appropriate recipe. The generation AI uses, for example, a text generation AI (e.g., LLM) to generate a recipe based on the ingredient information, and analyzes the ingredient information entered by the user to propose an optimal recipe. Step 3: The automatic generation unit automatically generates a shopping list for the next shopping trip based on the recipe generated by the generation unit. If an ingredient required for the recipe is missing, the automatic generation unit adds the ingredient to the shopping list. Step 4: The coordinating unit coordinates with the mail-order service based on the shopping list generated by the automatic generation unit and automatically requests delivery. The coordinating unit orders the necessary ingredients on the mail-order site based on the shopping list and requests that they be delivered to the customer's home.

[0143] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0145] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0146] For example, the reception unit is realized by the reception device 38 of the smart device 14. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the automatic generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the link unit is realized by the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0147] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0148] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] The 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.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0154] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0157] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0159] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0161] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0162] For example, the reception unit is realized by the microphone 238 of the smart glasses 214. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the automatic generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the cooperation unit is realized by the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0163] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0164] 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.

[0165] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0166] The 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.

[0167] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

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

[0169] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0170] 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.

[0171] 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.

[0172] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0173] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0174] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0175] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0176] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0177] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0178] For example, the reception unit is realized by the microphone 238 of the headset type terminal 314. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the automatic generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the cooperation unit is realized by the control unit 46A of the headset type terminal 314. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0179] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0180] 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.

[0181] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0182] 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.

[0183] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0184] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0185] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0186] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0187] 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.

[0188] 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.

[0189] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0190] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0191] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0192] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0193] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0194] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0195] For example, the reception unit is realized by the microphone 238 of the robot 414. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the automatic generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the collaboration unit is realized by the control unit 46A of the robot 414. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0196] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0197] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0198] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0199] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0200] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0201] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0202] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0203] 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.

[0204] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0205] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0206] 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.

[0207] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0208] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0209] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0210] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0211] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0212] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0213] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0214] (Appendix 1) A reception unit that receives input of the type and remaining amount of ingredients; A generation unit that analyzes the information received by the reception unit and generates a recipe according to ingredients; an automatic generation unit that automatically generates a next shopping list based on the recipes generated by the generation unit; a linking unit that links with a mail-order service based on the shopping list generated by the automatic generation unit and automatically requests delivery. A system characterized by: (Appendix 2) The reception unit is Equipped with a freshness determination unit based on the freshness and expiration date of ingredients 2. The system of claim 1, (Appendix 3) The generation unit is Equipped with a history analysis unit that suggests recipes based on the user's past usage history 2. The system of claim 1, (Appendix 4) The generation unit is Equipped with a nutritional analysis section based on nutritional balance and calories 2. The system of claim 1, (Appendix 5) The linking portion is A service selection section is provided to allow a user to select from a number of mail order services. 2. The system of claim 1, (Appendix 6) The reception unit is The system estimates the user's emotions and adjusts the timing of inputting ingredient information based on the estimated user's emotions. 2. The system of claim 1, (Appendix 7) The reception unit is Analyze the user's past ingredient input history and select the appropriate input method 2. The system of claim 1, (Appendix 8) The reception unit is Filtering ingredient information based on the user's current diet plan and health status when entering ingredients 2. The system of claim 1, (Appendix 9) The reception unit is The system estimates the user's emotions and determines the priority of the food information to be input based on the estimated user's emotions. 2. The system of claim 1, (Appendix 10) The reception unit is When inputting ingredient information, the system takes into consideration the user's geographic location information and inputs ingredient information with high relevance. 2. The system of claim 1, (Appendix 11) The reception unit is When entering ingredient information, analyze the user's social media activity and enter related ingredient information 2. The system of claim 1, (Appendix 12) The generation unit is Infer user emotions and adjust recipe presentation based on the inferred user emotions 2. The system of claim 1, (Appendix 13) The generation unit is When generating recipes, adjust the recipe detail level based on the priority of ingredients 2. The system of claim 1, (Appendix 14) The generation unit is When generating recipes, apply different recipe generation algorithms depending on the ingredient category. 2. The system of claim 1, (Appendix 15) The generation unit is Infer user sentiment and adjust recipe length based on the inferred sentiment 2. The system of claim 1, (Appendix 16) The generation unit is When generating recipes, prioritize recipes based on when ingredients were acquired 2. The system of claim 1, (Appendix 17) The generation unit is When generating recipes, adjust the order of recipes based on ingredient associations 2. The system of claim 1, (Appendix 18) The automatic generation unit Inferring user emotions and adjusting the way a shopping list is generated based on the estimated user emotions 2. The system of claim 1, (Appendix 19) The automatic generation unit When generating a shopping list, the system analyzes the user's past purchase history to generate an optimal list. 2. The system of claim 1, (Appendix 20) The automatic generation unit When generating a shopping list, customize the list contents based on the user's current life situation 2. The system of claim 1, (Appendix 21) The automatic generation unit Infer user emotions and prioritize shopping lists based on the inferred user emotions 2. The system of claim 1, (Appendix 22) The automatic generation unit When generating a shopping list, the system considers the user's geographic location to generate the optimal list. 2. The system of claim 1, (Appendix 23) The automatic generation unit When generating a shopping list, analyze the user's social media activity to tailor the list 2. The system of claim 1, (Appendix 24) The linking portion is To estimate a user's emotion and adjust a method for selecting a mail-order service based on the estimated user's emotion. 2. The system of claim 1, (Appendix 25) The linking portion is When linking with online shopping services, analyze the user's past usage history to select the most suitable service. 2. The system of claim 1, (Appendix 26) The linking portion is When connecting with online shopping services, customize the service selection based on the user's current living situation 2. The system of claim 1, (Appendix 27) The linking portion is To estimate a user's emotion and determine the priority of mail-order services based on the estimated user's emotion. 2. The system of claim 1, (Appendix 28) The linking portion is When linking online shopping services, select the most suitable service by taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 29) The linking portion is When linking with online shopping services, analyze users' social media activity to adjust service selection 2. The system of claim 1, (Appendix 30) The freshness determination unit is To estimate a user's emotion and adjust a criterion for determining the freshness of ingredients based on the estimated user's emotion. 3. The system of claim 2, (Appendix 31) The freshness determination unit is When assessing freshness, evaluate the freshness of the food based on how it was stored. 3. The system of claim 2, (Appendix 32) The freshness determination unit is When determining freshness, evaluate the freshness of ingredients based on the purchase date and frequency of use. 3. The system of claim 2, (Appendix 33) The freshness determination unit is A user's emotion is estimated, and a priority order for freshness determination is determined based on the estimated user's emotion. 3. The system of claim 2, (Appendix 34) The freshness determination unit is When assessing freshness, the geographic origin of the food is taken into account. 3. The system of claim 2, (Appendix 35) The history analysis unit To estimate a user's emotion and adjust a method of history analysis based on the estimated user's emotion. 4. The system of claim 3. (Appendix 36) The history analysis unit During history analysis, the system analyzes the user's past recipe usage history and suggests optimal recipes. 4. The system of claim 3. (Appendix 37) The history analysis unit When analyzing history, it suggests recipes based on the user's current meal plan 4. The system of claim 3. (Appendix 38) The history analysis unit To estimate a user's emotion and determine a priority of history analysis based on the estimated user's emotion. 4. The system of claim 3. (Appendix 39) The history analysis unit When analyzing history, the system considers the user's geographic location to suggest optimal recipes. 4. The system of claim 3. (Appendix 40) The nutritional analysis unit includes: To estimate a user's emotion and adjust a nutrition analysis method based on the estimated user's emotion. 5. The system of claim 4. (Appendix 41) The nutritional analysis unit includes: During nutritional analysis, the system analyzes the user's past meal history to suggest optimal nutritional balance. 5. The system of claim 4. (Appendix 42) The nutritional analysis unit includes: During nutritional analysis, nutritional balance is suggested based on the user's current health condition. 5. The system of claim 4. (Appendix 43) The nutritional analysis unit includes: Estimate user's emotions and determine priority of nutrition analysis based on the estimated user's emotions 5. The system of claim 4. (Appendix 44) The nutritional analysis unit includes: When analyzing nutrition, the system takes into account the user's geographic location to suggest optimal nutritional balance. 5. The system of claim 4. (Appendix 45) The service selection unit To estimate a user's emotion and adjust a service selection method based on the estimated user's emotion. 6. The system of claim 5, (Appendix 46) The service selection unit When selecting a service, the system analyzes the user's past usage history to select the most suitable service. 6. The system of claim 5, (Appendix 47) The service selection unit When selecting a service, customize the service selection based on the user's current living situation 6. The system of claim 5, (Appendix 48) The service selection unit To estimate a user's emotion and determine a priority order for service selection based on the estimated user's emotion. 6. The system of claim 5, (Appendix 49) The service selection unit When selecting a service, the optimal service is selected taking into account the user's geographic location information. 6. The system of claim 5, (Appendix 50) The service selection unit When selecting services, analyze users' social media activity to tailor service selection 6. The system of claim 5, [Explanation of symbols]

[0215] 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 reception unit that receives input of the type and remaining amount of ingredients; A generation unit that analyzes the information received by the reception unit and generates a recipe according to ingredients; an automatic generation unit that automatically generates a next shopping list based on the recipes generated by the generation unit; a linking unit that links with a mail-order service based on the shopping list generated by the automatic generation unit and automatically requests delivery. A system characterized by:

2. The reception unit is Equipped with a freshness determination unit based on the freshness and expiration date of ingredients 2. The system of claim 1 .

3. The generation unit is Equipped with a history analysis unit that suggests recipes based on the user's past usage history 2. The system of claim 1 .

4. The generation unit is Equipped with a nutritional analysis section based on nutritional balance and calories 2. The system of claim 1 .

5. The linking portion is A service selection section is provided to allow a user to select from a number of mail order services.

2. The system of claim 1 .

6. The reception unit is The system estimates the user's emotions and adjusts the timing of inputting ingredient information based on the estimated user's emotions.

2. The system of claim 1 .

7. The reception unit is Analyze the user's past ingredient input history and select the appropriate input method 2. The system of claim 1 .

8. The reception unit is Filtering ingredient information based on the user's current diet plan and health status when entering ingredients 2. The system of claim 1 .

9. The reception unit is The system estimates the user's emotions and determines the priority of the food information to be input based on the estimated user's emotions.

2. The system of claim 1 .

10. The reception unit is When inputting ingredient information, the system takes into consideration the user's geographic location information and inputs ingredient information with high relevance.

2. The system of claim 1 .

Images