system

Abstract

The system according to the embodiment aims to generate appropriate cooking recipes based on the user's preferences and conditions. [Solution] The system according to the embodiment includes a condition input unit, an ingredient input unit, an ingredient recognition unit, a recipe generation unit, and a recipe provision unit. The condition input unit inputs various conditions including the user's preferences, age, and place of origin. The ingredient input unit takes photos of remaining ingredients based on the information input by the condition input unit and inputs the photos to the generation AI. The ingredient recognition unit analyzes the ingredient information input by the ingredient input unit. The recipe generation unit generates a cooking recipe suitable for the user based on the information analyzed by the ingredient recognition unit. The recipe provision unit provides the recipe generated by the recipe generation unit to the user.

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem of making it difficult to efficiently generate cooking recipes based on a user's preferences and conditions.

[0005] The system according to the embodiment aims to generate appropriate cooking recipes based on the user's preferences and conditions. [Means for solving the problem]

[0006] The system according to the embodiment includes a condition input unit, an ingredient input unit, an ingredient recognition unit, a recipe generation unit, and a recipe provision unit. The condition input unit inputs various conditions including the user's preferences, age, and place of origin. The ingredient input unit takes photos of remaining ingredients based on the information input by the condition input unit and inputs the photos to the generation AI. The ingredient recognition unit analyzes the ingredient information input by the ingredient input unit. The recipe generation unit generates a cooking recipe suitable for the user based on the information analyzed by the ingredient recognition unit. The recipe provision unit provides the recipe generated by the recipe generation unit to the user. [Effects of the Invention]

[0007] The system according to the embodiment can generate appropriate cooking recipes based on the user's preferences and conditions. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A cooking recipe generation system according to an embodiment of the present invention provides a user with a cooking recipe optimized for that user by inputting various conditions, such as the user's preferences, age, and hometown, and taking photos of remaining ingredients. The cooking recipe generation system generates and provides a cooking recipe optimized for the user by inputting various conditions, such as the user's preferences, age, and hometown, taking photos of remaining ingredients, and inputting the photos into a generation AI. For example, the cooking recipe generation system inputs various conditions, such as the user's preferences, age, and hometown. For example, if the user likes Japanese food and has no allergies, the user inputs this information. Next, the cooking recipe generation system has the user take photos of remaining ingredients and input them into the generation AI. The generation AI recognizes the ingredients from the photos and analyzes the information. For example, the user takes photos of leftover vegetables and meat in the refrigerator and inputs them into the generation AI. Next, the cooking recipe generation system uses the generation AI to analyze the input conditions and ingredient information and generate a cooking recipe optimized for the user. For example, if the user likes Japanese food and wants a dish using leftover vegetables and meat in the refrigerator, the generation AI generates a Japanese recipe based on that information. This allows the cooking recipe generation system to provide cooking recipes customized based on the user's preferences, age, and place of origin. For example, if a user is busy and looking for a dish that can be easily made using leftover ingredients in the refrigerator, the generation AI can provide a recipe that meets that need. Also, by providing recipes tailored to the user's preferences and health status, meal satisfaction can be improved. Furthermore, the generation AI can learn the user's input information and reflect it in subsequent recipe suggestions. This makes it possible to provide recipes that are more suited to the user's preferences and needs. For example, if a user prefers a particular dish, the generation AI can learn that information and reflect it in subsequent suggestions, thereby providing more satisfying recipes.

[0029] A cooking recipe generation system according to an embodiment includes a condition input unit, an ingredient input unit, an ingredient recognition unit, a recipe generation unit, and a recipe provision unit. The condition input unit inputs various conditions, including the user's preferences, age, and hometown. For example, the user can input their favorite types of cuisine, allergy information, and health status. The ingredient input unit inputs photos of ingredients taken by the user to the generation AI. For example, the user may take photos of leftover vegetables and meat in the refrigerator and input them to the generation AI. The ingredient recognition unit uses the generation AI to recognize ingredients from the photos and analyze the information. For example, the generation AI recognizes ingredients from the photos and analyzes the information. The recipe generation unit uses the generation AI to generate a customized cooking recipe based on the user's preferences, age, and hometown. For example, if a user likes Japanese food and wants a dish using leftover vegetables and meat in the refrigerator, the generation AI generates a Japanese recipe based on that information. The recipe provision unit provides the generated cooking recipe to the user. For example, the generated cooking recipe is displayed on the user's smartphone or tablet. As a result, the recipe generation system according to the embodiment can provide optimal recipes based on various conditions such as the user's preferences, age, and place of origin.

[0030] The condition input unit can input information including the user's preferences, age, hometown, allergy information, and health condition. The condition input unit inputs, for example, the user's preferences, age, hometown, allergy information, and health condition. For example, the user can input the type of food they like, allergy information, and health condition. By inputting detailed information about the user, more customized recipes can be provided. Some or all of the above-described processing in the condition input unit may be performed, for example, using AI, or may be performed without using AI. For example, the condition input unit can input the user's input information to a generation AI and have the generation AI analyze it.

[0031] The ingredient input unit can input photos of ingredients taken by the user to the generation AI. The ingredient input unit, for example, inputs photos of ingredients taken by the user to the generation AI. For example, the user takes photos of vegetables or meat that are left over in the refrigerator and inputs the photos to the generation AI. In this way, by inputting photos of ingredients taken by the user, accurate information about the ingredients can be obtained. Some or all of the above-mentioned processing in the ingredient input unit may be performed, for example, using AI, or may be performed without using AI. For example, the ingredient input unit can input photos of ingredients taken by the user to the generation AI, and have the generation AI analyze the photos.

[0032] The ingredient recognition unit can use the generation AI to recognize ingredients from a photo and analyze the information. The ingredient recognition unit, for example, uses the generation AI to recognize ingredients from a photo and analyze the information. For example, the generation AI recognizes ingredients from a photo and analyzes the information. By using the generation AI, the accuracy of ingredient recognition and analysis is improved. Some or all of the above-mentioned processing in the ingredient recognition unit may be performed using AI, for example, or may be performed without using AI. For example, the ingredient recognition unit can input photos of ingredients taken by the user into the generation AI and have the generation AI analyze the photos.

[0033] The recipe generation unit can use the generation AI to generate a cooking recipe customized based on the user's preferences, age, and hometown. The recipe generation unit, for example, uses the generation AI to generate a cooking recipe customized based on the user's preferences, age, and hometown. For example, if a user likes Japanese food and wants to make a dish using leftover vegetables and meat in the refrigerator, the generation AI generates a Japanese recipe based on that information. In this way, by using the generation AI, it is possible to generate a cooking recipe that is optimal for the user. Some or all of the above-mentioned processes in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input information about the user's preferences, age, and hometown into the generation AI and have it analyzed by the generation AI.

[0034] The recipe providing unit can provide the generated cooking recipe to the user. The recipe providing unit, for example, provides the generated cooking recipe to the user. For example, the generated cooking recipe is displayed on the user's smartphone or tablet. By providing the generated cooking recipe to the user, the user can easily obtain the recipe. Some or all of the above-mentioned processing in the recipe providing unit may be performed using AI, for example, or may be performed without using AI. For example, the recipe providing unit can generate the generated cooking recipe using a generation AI and provide it to the user.

[0035] The recipe generation unit can learn the user's input information and reflect it in subsequent recipe suggestions. The recipe generation unit, for example, learns the user's input information and reflects it in subsequent recipe suggestions. For example, if a user likes a particular dish, the recipe generation unit can learn that information and reflect it in subsequent suggestions, thereby providing more satisfying recipes. By learning the user's input information, the accuracy of subsequent recipe suggestions is improved. Some or all of the above-described processing in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input the user's input information into a generation AI and have the generation AI learn the information.

[0036] The condition input unit can analyze the user's past input history and suggest the optimal input method. For example, the condition input unit automatically displays preferences and allergy information that the user has frequently input in the past as candidates. The condition input unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. The condition input unit can also predict and suggest information to be input during a specific time period based on the user's past input history. In this way, by analyzing the past input history, the optimal input method can be suggested to the user. Some or all of the above-mentioned processing in the condition input unit may be performed using, for example, AI, or may be performed without using AI. For example, the condition input unit can have a generation AI analyze the user's past input history and suggest the optimal input method.

[0037] When inputting conditions, the condition input unit can filter the input content based on the user's current health condition and dietary restrictions. For example, if the user has diabetes, the condition input unit automatically excludes ingredients and recipes with high sugar content. Furthermore, if the user is on a diet, the condition input unit can also prioritize displaying low-calorie ingredients and recipes. Furthermore, if the user has a specific allergy, the condition input unit can automatically exclude ingredients and recipes containing that allergen. By filtering the input content based on the user's health condition and dietary restrictions, appropriate recipes can be provided. Some or all of the above-described processing in the condition input unit may be performed, for example, using AI, or may be performed without using AI. For example, the condition input unit can input information about the user's health condition and dietary restrictions to the generation AI, which can then filter the information.

[0038] The condition input unit can select the optimal input means depending on the user's input method when inputting conditions. For example, if the user selects voice input, the condition input unit converts the input content into text using voice recognition technology. Furthermore, if the user selects text input, the condition input unit can also input using a keyboard or touch screen. Furthermore, if the user selects image input, the condition input unit can also analyze the input content using image recognition technology. This improves input convenience by selecting the optimal input means depending on the user's input method. Some or all of the above-described processing in the condition input unit may be performed using, for example, AI, or may be performed without using AI. For example, the condition input unit can have a generation AI analyze the user's input method and select the optimal input means.

[0039] When inputting conditions, the condition input unit can prioritize inputting highly relevant information by taking into account the user's geographical location information. For example, if the user lives in a specific area, the condition input unit can prioritize displaying ingredients that are easily available in that area. Furthermore, if the user is traveling, the condition input unit can also suggest local ingredients and recipes based on the user's current location. Furthermore, if the user prefers cuisine from a specific area, the condition input unit can prioritize displaying recipes from that area. In this way, highly relevant information can be prioritized by taking the user's geographical location information into account. Some or all of the above-described processing in the condition input unit may be performed using, for example, AI, or may be performed without using AI. For example, the condition input unit can have a generation AI analyze the user's geographical location information and prioritize inputting highly relevant information.

[0040] The condition input unit can analyze the user's social media activity when inputting conditions and input related information. The condition input unit can, for example, suggest a favorite dish based on information about dishes shared by the user on social media. The condition input unit can also analyze the content of the user's social media posts and suggest related ingredients and recipes. The condition input unit can also suggest related dishes by referring to the activities of the user's friends on social media. In this way, related information can be input by analyzing the user's social media activity. Some or all of the above-mentioned processing in the condition input unit may be performed using, for example, AI, or may be performed without using AI. For example, the condition input unit can have a generation AI analyze the user's social media activity and input related information.

[0041] The condition input unit can customize the input method by reflecting the user's past feedback when inputting conditions. The condition input unit can, for example, suggest an optimal input method based on feedback provided by the user in the past. The condition input unit can also preferentially display a specific input method based on the user's past feedback. The condition input unit can also analyze the user's feedback and customize the input interface. This allows the input method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the condition input unit can be performed using, for example, AI, or can be performed without using AI. For example, the condition input unit can customize the input method by having a generation AI analyze the user's past feedback.

[0042] The ingredient input unit can analyze the user's past ingredient input history and select the optimal input method. For example, the ingredient input unit can automatically display ingredients that the user has frequently input in the past as candidates. The ingredient input unit can also prioritize and suggest input methods (voice, text, etc.) that the user has used in the past. The ingredient input unit can also predict and suggest ingredients to be used in a specific time period based on the user's past ingredient input history. In this way, by analyzing the past ingredient input history, the optimal input method for the user can be selected. Some or all of the above-mentioned processing in the ingredient input unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient input unit can have a generation AI analyze the user's past ingredient input history and select the optimal input method.

[0043] The ingredient input unit can filter ingredients based on the user's current ingredient inventory when inputting ingredients. For example, if the user inputs ingredients in the refrigerator, the ingredient input unit can suggest recipes based on the inventory. Furthermore, if the user does not have a specific ingredient, the ingredient input unit can suggest a recipe that excludes that ingredient. Furthermore, the ingredient input unit can prioritize suggesting ingredients that should be used soon, taking into account the expiration dates of ingredients the user has. In this way, filtering based on the user's ingredient inventory can provide an appropriate recipe. Some or all of the above-mentioned processing in the ingredient input unit may be performed using, for example, AI, or may be performed without AI. For example, the ingredient input unit can have a generation AI analyze the user's ingredient inventory and perform filtering.

[0044] When inputting ingredients, the ingredient input unit can select the optimal input means depending on the user's input method. For example, if the user selects voice input, the ingredient input unit converts the input content into text using voice recognition technology. Furthermore, if the user selects text input, the ingredient input unit can also input using a keyboard or touch screen. Furthermore, if the user selects image input, the ingredient input unit can also analyze the input content using image recognition technology. This improves input convenience by selecting the optimal input means depending on the user's input method. Some or all of the above-mentioned processing in the ingredient input unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient input unit can have a generation AI analyze the user's input method and select the optimal input means.

[0045] When inputting ingredients, the ingredient input unit can prioritize inputting highly relevant ingredients by taking into account the user's geographical location information. For example, if the user lives in a specific area, the ingredient input unit can prioritize displaying ingredients that are easily available in that area. Furthermore, if the user is traveling, the ingredient input unit can also suggest local ingredients based on the user's current location. Furthermore, if the user prefers cuisine from a specific area, the ingredient input unit can prioritize displaying ingredients from that area. In this way, highly relevant ingredients can be prioritized by taking the user's geographical location information into account. Some or all of the above-described processing in the ingredient input unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient input unit can have a generation AI analyze the user's geographical location information and prioritize inputting highly relevant ingredients.

[0046] The ingredient input unit can analyze the user's social media activity when inputting ingredients and input related ingredients. The ingredient input unit can suggest related ingredients based on, for example, information about dishes shared by the user on social media. The ingredient input unit can also analyze the content of the user's social media posts and suggest related ingredients. The ingredient input unit can also suggest related ingredients by referring to the activity of the user's friends on social media. In this way, related ingredients can be input by analyzing the user's social media activity. Some or all of the above-mentioned processing in the ingredient input unit may be performed, for example, using AI, or may be performed without using AI. For example, the ingredient input unit can have a generation AI analyze the user's social media activity and input related ingredients.

[0047] The ingredient input unit can customize the input method by reflecting the user's past feedback when inputting ingredients. For example, the ingredient input unit can suggest the optimal input method based on feedback provided by the user in the past. The ingredient input unit can also preferentially display a specific input method based on the user's past feedback. The ingredient input unit can also analyze the user's feedback and customize the input interface. This allows the input method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the ingredient input unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient input unit can customize the input method by having a generation AI analyze the user's past feedback.

[0048] When recognizing ingredients, the ingredient recognition unit can optimize the recognition results by taking into account the freshness and quality of the ingredients. For example, the ingredient recognition unit evaluates the freshness of the ingredients and prioritizes recognition of fresh ingredients. The ingredient recognition unit can also evaluate the quality of the ingredients and prioritize recognition of high-quality ingredients. The ingredient recognition unit can also take into account the expiration date of the ingredients and prioritize recognition of ingredients that should be used soon. In this way, by taking into account the freshness and quality of the ingredients, the accuracy of the recognition results is improved. Some or all of the above-mentioned processing in the ingredient recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient recognition unit can input information on the freshness and quality of the ingredients into the generation AI, which can then analyze it.

[0049] When recognizing ingredients, the ingredient recognition unit can apply different recognition algorithms depending on the ingredient category. For example, the ingredient recognition unit can apply different algorithms to recognize vegetables and fruits to improve accuracy. The ingredient recognition unit can also apply different algorithms to recognize meat and fish to improve accuracy. The ingredient recognition unit can also apply different algorithms to recognize processed foods and fresh foods to improve accuracy. In this way, by applying different recognition algorithms depending on the ingredient category, recognition accuracy is improved. Some or all of the above-mentioned processing in the ingredient recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient recognition unit can input ingredient category information to a generation AI and have the generation AI analyze it.

[0050] When recognizing ingredients, the ingredient recognition unit can improve the accuracy of the recognition by referring to the user's past recognition results. For example, the ingredient recognition unit improves the recognition accuracy based on information about ingredients that the user has previously recognized. The ingredient recognition unit can also improve the recognition algorithm based on information about ingredients that the user has previously misrecognized. The ingredient recognition unit can also analyze the user's past recognition results to improve the recognition accuracy of specific ingredients. In this way, by referring to the user's past recognition results, the recognition accuracy is improved. Some or all of the above-mentioned processing in the ingredient recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient recognition unit can improve the recognition accuracy by having a generation AI analyze the user's past recognition results.

[0051] The ingredient recognition unit can recognize ingredients while taking into account the geographical distribution of ingredients. For example, the ingredient recognition unit prioritizes the recognition of ingredients that are commonly used in a specific region. The ingredient recognition unit can also recognize ingredients from a specific region based on their geographical distribution. The ingredient recognition unit can also improve the recognition accuracy of ingredients from a specific region by taking into account their geographical distribution. This improves the recognition accuracy by taking into account the geographical distribution of ingredients. Some or all of the above-described processing in the ingredient recognition unit can be performed using, for example, AI, or without AI. For example, the ingredient recognition unit can input information about the geographical distribution of ingredients into a generation AI, which can then analyze the information.

[0052] When recognizing ingredients, the ingredient recognition unit can improve the accuracy of the recognition by referring to literature related to ingredients. For example, the ingredient recognition unit can refer to literature related to ingredients to improve the recognition algorithm. The ingredient recognition unit can also improve the recognition accuracy of specific ingredients based on literature related to ingredients. The ingredient recognition unit can also develop new ingredient recognition algorithms by referring to literature related to ingredients. In this way, by referring to literature related to ingredients, the recognition accuracy is improved. Some or all of the above-mentioned processing in the ingredient recognition unit can be performed using, for example, AI, or can be performed without using AI. For example, the ingredient recognition unit can input literature related to ingredients into a generation AI and have the generation AI analyze it.

[0053] The ingredient recognition unit can take into account the market value of the ingredient when recognizing ingredients. For example, the ingredient recognition unit prioritizes the recognition of ingredients with high market value. The ingredient recognition unit can also improve the recognition accuracy of specific ingredients by taking market value into account. The ingredient recognition unit can also improve the recognition algorithm for specific ingredients based on market value. In this way, taking the market value of ingredients into account improves recognition accuracy. Some or all of the above-mentioned processing in the ingredient recognition unit can be performed, for example, using AI or without AI. For example, the ingredient recognition unit can input market value information of ingredients into a generation AI and have the generation AI analyze it.

[0054] When generating a recipe, the recipe generation unit can adjust the level of detail of the recipe based on the importance of the ingredients. For example, the recipe generation unit provides detailed instructions for main ingredients and simplified instructions for secondary ingredients. The recipe generation unit can also provide detailed instructions for cooking main ingredients and simplified instructions for cooking other ingredients. The recipe generation unit can also provide detailed instructions for cooking times and temperatures for main ingredients and simplified information for secondary ingredients. In this way, adjusting the level of detail of the recipe based on the importance of the ingredients improves understanding of the recipe. Some or all of the above-mentioned processes in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input ingredient importance information into the generation AI and have the generation AI analyze it.

[0055] When generating a recipe, the recipe generation unit can apply different generation algorithms depending on the category of the dish. For example, the recipe generation unit can apply different algorithms to generate recipes for Japanese cuisine and Western cuisine, thereby improving accuracy. The recipe generation unit can also apply different algorithms to generate recipes for desserts and main dishes, thereby improving accuracy. The recipe generation unit can also apply different algorithms to generate recipes for vegetarian cuisine and meat dishes, thereby improving accuracy. In this way, by applying different generation algorithms depending on the category of the dish, the accuracy of the recipe is improved. Some or all of the above-mentioned processing in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input dish category information into the generation AI and have it analyzed by the generation AI.

[0056] When generating a recipe, the recipe generation unit can improve the accuracy of generation by referring to the user's past recipe results. The recipe generation unit, for example, improves the generation algorithm based on the results of recipes created by the user in the past. The recipe generation unit can also reflect information about the user's favorite recipes in the next recipe generation. The recipe generation unit can also analyze the user's past recipe results to improve the accuracy of generation of specific dishes. In this way, the accuracy of generation is improved by referring to the user's past recipe results. Some or all of the above-mentioned processing in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can have the generation AI analyze the user's past recipe results to improve the accuracy of generation.

[0057] When generating a recipe, the recipe generation unit can determine the priority of recipes based on the time when ingredients were submitted. For example, the recipe generation unit provides recipes that prioritize the use of ingredients that are close to their expiration date. The recipe generation unit can also provide recipes that prioritize the use of seasonal ingredients. The recipe generation unit can also provide recipes that prioritize the use of ingredients that the user recently purchased. This enables effective use of ingredients by determining the priority of recipes based on the time when ingredients were submitted. Some or all of the above-mentioned processing in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input information on the time when ingredients were submitted to the generation AI, which can then analyze the information.

[0058] The recipe generation unit can adjust the order of the recipe based on the relevance of ingredients when generating a recipe. For example, the recipe generation unit determines the order of the recipe based on the main ingredients. The recipe generation unit can also provide an optimal order of the recipe by taking into account the combination of ingredients. The recipe generation unit can also adjust the order of the recipe by taking into account the cooking time and temperature of the ingredients. In this way, adjusting the order of the recipe based on the relevance of ingredients improves cooking efficiency. Some or all of the above-mentioned processing in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input information on the relevance of ingredients into the generation AI and have it analyzed by the generation AI.

[0059] When generating a recipe, the recipe generation unit can adjust the use of technical terms in the recipe according to the user's level of expertise. For example, the recipe generation unit can provide a recipe explained in simple terms for beginners. The recipe generation unit can also provide a recipe including slightly more technical terms for intermediate users. The recipe generation unit can also provide a detailed recipe using a lot of technical terms for advanced users. In this way, adjusting the use of technical terms in the recipe according to the user's level of expertise improves understanding of the recipe. Some or all of the above-described processing in the recipe generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the recipe generation unit can input the user's level of expertise information into the generation AI and have the generation AI analyze it.

[0060] When providing a recipe, the recipe providing unit can select the optimal serving method by referring to the user's past recipe history. For example, the recipe providing unit selects the optimal serving method based on the user's past preferred recipe serving methods. The recipe providing unit can also preferentially display specific serving methods from the user's past recipe history. The recipe providing unit can also analyze the user's past recipe history and improve the serving method for a specific dish. In this way, the optimal serving method can be selected by referring to the user's past recipe history. Some or all of the above-described processing in the recipe providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe providing unit can have a generation AI analyze the user's past recipe history to select the optimal serving method.

[0061] When providing a recipe, the recipe providing unit can customize the provided content based on the user's current living situation. For example, if the user is busy, the recipe providing unit can provide a recipe that can be made in a short time. Furthermore, if the user is relaxed, the recipe providing unit can also provide a recipe that includes detailed steps. Furthermore, if the user does not have a specific ingredient, the recipe providing unit can also provide a recipe that excludes that ingredient. This improves the applicability of the recipe by customizing the provided content based on the user's current living situation. Some or all of the above-mentioned processing in the recipe providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the recipe providing unit can input the user's living situation information into a generation AI and have the generation AI analyze it.

[0062] When providing a recipe, the recipe providing unit can improve the providing method by reflecting user feedback. For example, the recipe providing unit selects the optimal providing method based on feedback provided by the user. The recipe providing unit can also preferentially display a specific providing method based on user feedback. The recipe providing unit can also analyze user feedback and customize the providing interface. In this way, the providing method can be improved by reflecting user feedback. Some or all of the above-described processing in the recipe providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe providing unit can have a generation AI analyze user feedback and improve the providing method.

[0063] When providing a recipe, the recipe providing unit can select the optimal delivery method by taking into account the user's geographical location information. For example, if the user lives in a specific area, the recipe providing unit can provide recipes using ingredients that are easily available in that area. Furthermore, if the user is traveling, the recipe providing unit can also provide recipes using local ingredients based on the user's current location. Furthermore, if the user prefers cuisine from a specific area, the recipe providing unit can also preferentially provide recipes from that area. In this way, the optimal delivery method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the recipe providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe providing unit can have a generation AI analyze the user's geographical location information and select the optimal delivery method.

[0064] When providing a recipe, the recipe providing unit can analyze the user's social media activity and customize the content to be provided. For example, the recipe providing unit can provide related recipes based on information about dishes shared by the user on social media. The recipe providing unit can also analyze the content posted by the user on social media and provide related recipes. The recipe providing unit can also provide related recipes by referring to the activity of the user's friends on social media. In this way, the content to be provided can be customized by analyzing the user's social media activity. Some or all of the above-described processing in the recipe providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe providing unit can customize the content to be provided by having a generation AI analyze the user's social media activity.

[0065] When providing a recipe, the recipe providing unit can customize the serving method by reflecting the user's past feedback. For example, the recipe providing unit selects the optimal serving method based on feedback provided by the user in the past. The recipe providing unit can also preferentially display a specific serving method based on the user's past feedback. The recipe providing unit can also analyze the user's feedback and customize the serving interface. This allows the serving method to be customized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the recipe providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe providing unit can customize the serving method by having a generation AI analyze the user's past feedback.

[0066] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0067] The ingredient input unit can input ingredient information by scanning the barcode of an ingredient in addition to a photo of the ingredient taken by the user. For example, when a user scans the barcode of an ingredient in the refrigerator, detailed information about the ingredient (such as expiration date and nutritional information) is automatically obtained. Also, by scanning the receipt of the purchased ingredient, the user can input information about the purchased ingredient all at once. Furthermore, the user can input ingredient information using voice input; for example, by inputting "three tomatoes" by voice, ingredient information can be easily added. This makes the input of ingredient information more convenient and efficient.

[0068] When recognizing ingredients from a photo, the ingredient recognition unit can also evaluate the freshness and quality of the ingredients. For example, it can analyze the color and shape of the ingredients from the photo to determine whether they are fresh. It can also detect scratches and discoloration on the surface of the ingredients to evaluate their quality. Furthermore, it can prioritize the recognition of ingredients that should be used soon, taking into account their expiration dates. This allows users to be recommended recipes that use fresh and high-quality ingredients.

[0069] The recipe generation unit can also take into account the user's past recipe history when generating a cooking recipe customized based on the user's preferences, age, and place of origin. For example, the next recipe suggestion can be based on the user's ratings and feedback on recipes they have created in the past. Also, if a user frequently uses a particular ingredient, it can prioritize recipes that use that ingredient. Furthermore, it can also suggest more suitable recipes by taking into account the success rate and cooking time of recipes the user has created in the past. This makes it possible to provide recipes that are more suited to the user's preferences and needs.

[0070] When providing the generated cooking recipe to the user, the recipe providing unit can provide it in the optimal format depending on the user's device and platform. For example, if the user is using a smartphone, the recipe can be displayed in a mobile-friendly format. Also, if the user is using a tablet, the recipe can be provided in a layout suitable for a large screen. Furthermore, if the user is using a smart speaker, the recipe can be read aloud. This allows the user to obtain the recipe in the optimal format for their device and platform.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The condition input section allows users to input various conditions, including their preferences, age, and hometown. For example, users can input their favorite types of cuisine, allergy information, and health conditions. Step 2: The ingredient input unit inputs photos of ingredients taken by the user into the generation AI. For example, the user can take photos of leftover vegetables or meat in the refrigerator and input them into the generation AI. Step 3: The ingredient recognition unit uses the generation AI to recognize ingredients from the photo and analyze the information. For example, the generation AI recognizes ingredients from the photo and analyzes the information. Step 4: The recipe generation unit uses the generation AI to generate customized cooking recipes based on the user's preferences, age, and place of origin. For example, if the user likes Japanese food and wants to make a dish using leftover vegetables and meat in the refrigerator, the generation AI will use that information to generate a Japanese recipe. Step 5: The recipe provider provides the generated cooking recipe to the user. For example, the generated cooking recipe is displayed on the user's smartphone or tablet.

[0073] (Example 2) A cooking recipe generation system according to an embodiment of the present invention provides a user with a cooking recipe optimized for that user by inputting various conditions, such as the user's preferences, age, and hometown, and taking photos of remaining ingredients. The cooking recipe generation system generates and provides a cooking recipe optimized for the user by inputting various conditions, such as the user's preferences, age, and hometown, taking photos of remaining ingredients, and inputting the photos into a generation AI. For example, the cooking recipe generation system inputs various conditions, such as the user's preferences, age, and hometown. For example, if the user likes Japanese food and has no allergies, the user inputs this information. Next, the cooking recipe generation system has the user take photos of remaining ingredients and input them into the generation AI. The generation AI recognizes the ingredients from the photos and analyzes the information. For example, the user takes photos of leftover vegetables and meat in the refrigerator and inputs them into the generation AI. Next, the cooking recipe generation system uses the generation AI to analyze the input conditions and ingredient information and generate a cooking recipe optimized for the user. For example, if the user likes Japanese food and wants a dish using leftover vegetables and meat in the refrigerator, the generation AI generates a Japanese recipe based on that information. This allows the cooking recipe generation system to provide cooking recipes customized based on the user's preferences, age, and place of origin. For example, if a user is busy and looking for a dish that can be easily made using leftover ingredients in the refrigerator, the generation AI can provide a recipe that meets that need. Also, by providing recipes tailored to the user's preferences and health status, meal satisfaction can be improved. Furthermore, the generation AI can learn the user's input information and reflect it in subsequent recipe suggestions. This makes it possible to provide recipes that are more suited to the user's preferences and needs. For example, if a user prefers a particular dish, the generation AI can learn that information and reflect it in subsequent suggestions, thereby providing more satisfying recipes.

[0074] A cooking recipe generation system according to an embodiment includes a condition input unit, an ingredient input unit, an ingredient recognition unit, a recipe generation unit, and a recipe provision unit. The condition input unit inputs various conditions, including the user's preferences, age, and hometown. For example, the user can input their favorite types of cuisine, allergy information, and health status. The ingredient input unit inputs photos of ingredients taken by the user to the generation AI. For example, the user may take photos of leftover vegetables and meat in the refrigerator and input them to the generation AI. The ingredient recognition unit uses the generation AI to recognize ingredients from the photos and analyze the information. For example, the generation AI recognizes ingredients from the photos and analyzes the information. The recipe generation unit uses the generation AI to generate a customized cooking recipe based on the user's preferences, age, and hometown. For example, if a user likes Japanese food and wants a dish using leftover vegetables and meat in the refrigerator, the generation AI generates a Japanese recipe based on that information. The recipe provision unit provides the generated cooking recipe to the user. For example, the generated cooking recipe is displayed on the user's smartphone or tablet. As a result, the recipe generation system according to the embodiment can provide optimal recipes based on various conditions such as the user's preferences, age, and place of origin.

[0075] The condition input unit can input information including the user's preferences, age, hometown, allergy information, and health condition. The condition input unit inputs, for example, the user's preferences, age, hometown, allergy information, and health condition. For example, the user can input the type of food they like, allergy information, and health condition. By inputting detailed information about the user, more customized recipes can be provided. Some or all of the above-described processing in the condition input unit may be performed, for example, using AI, or may be performed without using AI. For example, the condition input unit can input the user's input information to a generation AI and have the generation AI analyze it.

[0076] The ingredient input unit can input photos of ingredients taken by the user to the generation AI. The ingredient input unit, for example, inputs photos of ingredients taken by the user to the generation AI. For example, the user takes photos of vegetables or meat that are left over in the refrigerator and inputs the photos to the generation AI. In this way, by inputting photos of ingredients taken by the user, accurate information about the ingredients can be obtained. Some or all of the above-mentioned processing in the ingredient input unit may be performed, for example, using AI, or may be performed without using AI. For example, the ingredient input unit can input photos of ingredients taken by the user to the generation AI, and have the generation AI analyze the photos.

[0077] The ingredient recognition unit can use the generation AI to recognize ingredients from a photo and analyze the information. The ingredient recognition unit, for example, uses the generation AI to recognize ingredients from a photo and analyze the information. For example, the generation AI recognizes ingredients from a photo and analyzes the information. By using the generation AI, the accuracy of ingredient recognition and analysis is improved. Some or all of the above-mentioned processing in the ingredient recognition unit may be performed using AI, for example, or may be performed without using AI. For example, the ingredient recognition unit can input photos of ingredients taken by the user into the generation AI and have the generation AI analyze the photos.

[0078] The recipe generation unit can use the generation AI to generate a cooking recipe customized based on the user's preferences, age, and hometown. The recipe generation unit, for example, uses the generation AI to generate a cooking recipe customized based on the user's preferences, age, and hometown. For example, if a user likes Japanese food and wants to make a dish using leftover vegetables and meat in the refrigerator, the generation AI generates a Japanese recipe based on that information. In this way, by using the generation AI, it is possible to generate a cooking recipe that is optimal for the user. Some or all of the above-mentioned processes in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input information about the user's preferences, age, and hometown into the generation AI and have it analyzed by the generation AI.

[0079] The recipe providing unit can provide the generated cooking recipe to the user. The recipe providing unit, for example, provides the generated cooking recipe to the user. For example, the generated cooking recipe is displayed on the user's smartphone or tablet. By providing the generated cooking recipe to the user, the user can easily obtain the recipe. Some or all of the above-mentioned processing in the recipe providing unit may be performed using AI, for example, or may be performed without using AI. For example, the recipe providing unit can generate the generated cooking recipe using a generation AI and provide it to the user.

[0080] The recipe generation unit can learn the user's input information and reflect it in subsequent recipe suggestions. The recipe generation unit, for example, learns the user's input information and reflects it in subsequent recipe suggestions. For example, if a user likes a particular dish, the recipe generation unit can learn that information and reflect it in subsequent suggestions, thereby providing more satisfying recipes. By learning the user's input information, the accuracy of subsequent recipe suggestions is improved. Some or all of the above-described processing in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input the user's input information into a generation AI and have the generation AI learn the information.

[0081] The condition input unit can estimate the user's emotions and prioritize the information to be input based on the estimated user emotions. For example, if the user is feeling stressed, the condition input unit can prioritize displaying simple input items and deferring detailed information. Furthermore, if the user is relaxed, the condition input unit can prioritize displaying detailed input items and provide customizable options. Furthermore, if the user is in a hurry, the condition input unit can prompt the user to enter only the most important information and allow other information to be added later. This reduces the burden on the user by prioritizing the input information based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the condition input unit can be performed using, for example, an AI, or without an AI. For example, the condition input unit can have a generative AI estimate the user's emotions and prioritize the input information based on the estimation result.

[0082] The condition input unit can analyze the user's past input history and suggest the optimal input method. For example, the condition input unit automatically displays preferences and allergy information that the user has frequently input in the past as candidates. The condition input unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. The condition input unit can also predict and suggest information to be input during a specific time period based on the user's past input history. In this way, by analyzing the past input history, the optimal input method can be suggested to the user. Some or all of the above-mentioned processing in the condition input unit may be performed using, for example, AI, or may be performed without using AI. For example, the condition input unit can have a generation AI analyze the user's past input history and suggest the optimal input method.

[0083] When inputting conditions, the condition input unit can filter the input content based on the user's current health condition and dietary restrictions. For example, if the user has diabetes, the condition input unit automatically excludes ingredients and recipes with high sugar content. Furthermore, if the user is on a diet, the condition input unit can also prioritize displaying low-calorie ingredients and recipes. Furthermore, if the user has a specific allergy, the condition input unit can automatically exclude ingredients and recipes containing that allergen. By filtering the input content based on the user's health condition and dietary restrictions, appropriate recipes can be provided. Some or all of the above-described processing in the condition input unit may be performed, for example, using AI, or may be performed without using AI. For example, the condition input unit can input information about the user's health condition and dietary restrictions to the generation AI, which can then filter the information.

[0084] The condition input unit can select the optimal input means depending on the user's input method when inputting conditions. For example, if the user selects voice input, the condition input unit converts the input content into text using voice recognition technology. Furthermore, if the user selects text input, the condition input unit can also input using a keyboard or touch screen. Furthermore, if the user selects image input, the condition input unit can also analyze the input content using image recognition technology. This improves input convenience by selecting the optimal input means depending on the user's input method. Some or all of the above-described processing in the condition input unit may be performed using, for example, AI, or may be performed without using AI. For example, the condition input unit can have a generation AI analyze the user's input method and select the optimal input means.

[0085] The condition input unit can estimate the user's emotions and adjust the level of detail of the information to be input based on the estimated user emotions. For example, if the user is feeling stressed, the condition input unit can display only simple input items and postpone detailed information. Alternatively, if the user is relaxed, the condition input unit can display detailed input items and provide customizable options. Alternatively, if the user is in a hurry, the condition input unit can prompt the user to enter only the most important information and allow other information to be added later. This reduces the burden on the user by adjusting the level of detail of the input information based on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the condition input unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the condition input unit can estimate the user's emotions using a generative AI and adjust the level of detail of the input information based on the estimation result.

[0086] When inputting conditions, the condition input unit can prioritize inputting highly relevant information by taking into account the user's geographical location information. For example, if the user lives in a specific area, the condition input unit can prioritize displaying ingredients that are easily available in that area. Furthermore, if the user is traveling, the condition input unit can also suggest local ingredients and recipes based on the user's current location. Furthermore, if the user prefers cuisine from a specific area, the condition input unit can prioritize displaying recipes from that area. In this way, highly relevant information can be prioritized by taking the user's geographical location information into account. Some or all of the above-described processing in the condition input unit may be performed using, for example, AI, or may be performed without using AI. For example, the condition input unit can have a generation AI analyze the user's geographical location information and prioritize inputting highly relevant information.

[0087] The condition input unit can analyze the user's social media activity when inputting conditions and input related information. The condition input unit can, for example, suggest a favorite dish based on information about dishes shared by the user on social media. The condition input unit can also analyze the content of the user's social media posts and suggest related ingredients and recipes. The condition input unit can also suggest related dishes by referring to the activities of the user's friends on social media. In this way, related information can be input by analyzing the user's social media activity. Some or all of the above-mentioned processing in the condition input unit may be performed using, for example, AI, or may be performed without using AI. For example, the condition input unit can have a generation AI analyze the user's social media activity and input related information.

[0088] The condition input unit can customize the input method by reflecting the user's past feedback when inputting conditions. The condition input unit can, for example, suggest an optimal input method based on feedback provided by the user in the past. The condition input unit can also preferentially display a specific input method based on the user's past feedback. The condition input unit can also analyze the user's feedback and customize the input interface. This allows the input method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the condition input unit can be performed using, for example, AI, or can be performed without using AI. For example, the condition input unit can customize the input method by having a generation AI analyze the user's past feedback.

[0089] The ingredient input unit can estimate the user's emotions and adjust the timing of ingredient input based on the estimated user emotions. For example, if the user is feeling stressed, the ingredient input unit can simplify the ingredient input and allow the user to add details later. The ingredient input unit can also prompt the user to enter detailed ingredient information when the user is relaxed. If the user is in a hurry, the ingredient input unit can also prompt the user to enter only the most important ingredients and allow the user to add other information later. This improves input convenience by adjusting the timing of ingredient input based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the ingredient input unit can be performed using, for example, AI, or without AI. For example, the ingredient input unit can estimate the user's emotions using a generative AI and adjust the timing of ingredient input based on the estimation result.

[0090] The ingredient input unit can analyze the user's past ingredient input history and select the optimal input method. For example, the ingredient input unit can automatically display ingredients that the user has frequently input in the past as candidates. The ingredient input unit can also prioritize and suggest input methods (voice, text, etc.) that the user has used in the past. The ingredient input unit can also predict and suggest ingredients to be used in a specific time period based on the user's past ingredient input history. In this way, by analyzing the past ingredient input history, the optimal input method for the user can be selected. Some or all of the above-mentioned processing in the ingredient input unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient input unit can have a generation AI analyze the user's past ingredient input history and select the optimal input method.

[0091] The ingredient input unit can filter ingredients based on the user's current ingredient inventory when inputting ingredients. For example, if the user inputs ingredients in the refrigerator, the ingredient input unit can suggest recipes based on the inventory. Furthermore, if the user does not have a specific ingredient, the ingredient input unit can suggest a recipe that excludes that ingredient. Furthermore, the ingredient input unit can prioritize suggesting ingredients that should be used soon, taking into account the expiration dates of ingredients the user has. In this way, filtering based on the user's ingredient inventory can provide an appropriate recipe. Some or all of the above-mentioned processing in the ingredient input unit may be performed using, for example, AI, or may be performed without AI. For example, the ingredient input unit can have a generation AI analyze the user's ingredient inventory and perform filtering.

[0092] When inputting ingredients, the ingredient input unit can select the optimal input means depending on the user's input method. For example, if the user selects voice input, the ingredient input unit converts the input content into text using voice recognition technology. Furthermore, if the user selects text input, the ingredient input unit can also input using a keyboard or touch screen. Furthermore, if the user selects image input, the ingredient input unit can also analyze the input content using image recognition technology. This improves input convenience by selecting the optimal input means depending on the user's input method. Some or all of the above-mentioned processing in the ingredient input unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient input unit can have a generation AI analyze the user's input method and select the optimal input means.

[0093] The ingredient input unit can estimate the user's emotions and determine the priority of ingredients to be input based on the estimated user emotions. For example, when the user is stressed, the ingredient input unit can prioritize the input of ingredients that are easy to prepare. Furthermore, when the user is relaxed, the ingredient input unit can also prioritize the input of ingredients that take a long time to prepare. Furthermore, when the user is in a hurry, the ingredient input unit can prioritize the input of ingredients that can be quickly prepared. This improves the efficiency of input by determining the priority of ingredients based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the ingredient input unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the ingredient input unit can estimate the user's emotions using a generative AI and determine the priority of ingredients to be input based on the estimation result.

[0094] When inputting ingredients, the ingredient input unit can prioritize inputting highly relevant ingredients by taking into account the user's geographical location information. For example, if the user lives in a specific area, the ingredient input unit can prioritize displaying ingredients that are easily available in that area. Furthermore, if the user is traveling, the ingredient input unit can also suggest local ingredients based on the user's current location. Furthermore, if the user prefers cuisine from a specific area, the ingredient input unit can prioritize displaying ingredients from that area. In this way, highly relevant ingredients can be prioritized by taking the user's geographical location information into account. Some or all of the above-described processing in the ingredient input unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient input unit can have a generation AI analyze the user's geographical location information and prioritize inputting highly relevant ingredients.

[0095] The ingredient input unit can analyze the user's social media activity when inputting ingredients and input related ingredients. The ingredient input unit can suggest related ingredients based on, for example, information about dishes shared by the user on social media. The ingredient input unit can also analyze the content of the user's social media posts and suggest related ingredients. The ingredient input unit can also suggest related ingredients by referring to the activity of the user's friends on social media. In this way, related ingredients can be input by analyzing the user's social media activity. Some or all of the above-mentioned processing in the ingredient input unit may be performed, for example, using AI, or may be performed without using AI. For example, the ingredient input unit can have a generation AI analyze the user's social media activity and input related ingredients.

[0096] The ingredient input unit can customize the input method by reflecting the user's past feedback when inputting ingredients. For example, the ingredient input unit can suggest the optimal input method based on feedback provided by the user in the past. The ingredient input unit can also preferentially display a specific input method based on the user's past feedback. The ingredient input unit can also analyze the user's feedback and customize the input interface. This allows the input method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the ingredient input unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient input unit can customize the input method by having a generation AI analyze the user's past feedback.

[0097] The ingredient recognition unit can estimate the user's emotions and adjust the accuracy of ingredient recognition based on the estimated user emotions. For example, if the user is stressed, the ingredient recognition unit can prioritize simple ingredient recognition and postpone detailed recognition. Alternatively, if the user is relaxed, the ingredient recognition unit can perform detailed ingredient recognition and provide customizable options. Alternatively, if the user is in a hurry, the ingredient recognition unit can recognize only the most important ingredients and allow other information to be added later. This improves the accuracy of ingredient recognition by adjusting the accuracy of ingredient recognition based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processing in the ingredient recognition unit may be performed using AI, or without AI. For example, the ingredient recognition unit can estimate the user's emotions using a generative AI and adjust the accuracy of ingredient recognition based on the estimation results.

[0098] When recognizing ingredients, the ingredient recognition unit can optimize the recognition results by taking into account the freshness and quality of the ingredients. For example, the ingredient recognition unit evaluates the freshness of the ingredients and prioritizes recognition of fresh ingredients. The ingredient recognition unit can also evaluate the quality of the ingredients and prioritize recognition of high-quality ingredients. The ingredient recognition unit can also take into account the expiration date of the ingredients and prioritize recognition of ingredients that should be used soon. In this way, by taking into account the freshness and quality of the ingredients, the accuracy of the recognition results is improved. Some or all of the above-mentioned processing in the ingredient recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient recognition unit can input information on the freshness and quality of the ingredients into the generation AI, which can then analyze it.

[0099] When recognizing ingredients, the ingredient recognition unit can apply different recognition algorithms depending on the ingredient category. For example, the ingredient recognition unit can apply different algorithms to recognize vegetables and fruits to improve accuracy. The ingredient recognition unit can also apply different algorithms to recognize meat and fish to improve accuracy. The ingredient recognition unit can also apply different algorithms to recognize processed foods and fresh foods to improve accuracy. In this way, by applying different recognition algorithms depending on the ingredient category, recognition accuracy is improved. Some or all of the above-mentioned processing in the ingredient recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient recognition unit can input ingredient category information to a generation AI and have the generation AI analyze it.

[0100] When recognizing ingredients, the ingredient recognition unit can improve the accuracy of the recognition by referring to the user's past recognition results. For example, the ingredient recognition unit improves the recognition accuracy based on information about ingredients that the user has previously recognized. The ingredient recognition unit can also improve the recognition algorithm based on information about ingredients that the user has previously misrecognized. The ingredient recognition unit can also analyze the user's past recognition results to improve the recognition accuracy of specific ingredients. In this way, by referring to the user's past recognition results, the recognition accuracy is improved. Some or all of the above-mentioned processing in the ingredient recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the ingredient recognition unit can improve the recognition accuracy by having a generation AI analyze the user's past recognition results.

[0101] The ingredient recognition unit can estimate the user's emotions and adjust the display method of the recognition results based on the estimated user emotions. For example, if the user is nervous, the ingredient recognition unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the ingredient recognition unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the ingredient recognition unit can also provide a display method that focuses on the main points. By adjusting the display method of the recognition results based on the user's emotions, the convenience of the display is improved. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the ingredient recognition unit can be performed using, for example, AI, or without AI. For example, the ingredient recognition unit can have a generation AI estimate the user's emotions and adjust the display method of the recognition results based on the estimation result.

[0102] The ingredient recognition unit can recognize ingredients while taking into account the geographical distribution of ingredients. For example, the ingredient recognition unit prioritizes the recognition of ingredients that are commonly used in a specific region. The ingredient recognition unit can also recognize ingredients from a specific region based on their geographical distribution. The ingredient recognition unit can also improve the recognition accuracy of ingredients from a specific region by taking into account their geographical distribution. This improves the recognition accuracy by taking into account the geographical distribution of ingredients. Some or all of the above-described processing in the ingredient recognition unit can be performed using, for example, AI, or without AI. For example, the ingredient recognition unit can input information about the geographical distribution of ingredients into a generation AI, which can then analyze the information.

[0103] When recognizing ingredients, the ingredient recognition unit can improve the accuracy of the recognition by referring to literature related to ingredients. For example, the ingredient recognition unit can refer to literature related to ingredients to improve the recognition algorithm. The ingredient recognition unit can also improve the recognition accuracy of specific ingredients based on literature related to ingredients. The ingredient recognition unit can also develop new ingredient recognition algorithms by referring to literature related to ingredients. In this way, by referring to literature related to ingredients, the recognition accuracy is improved. Some or all of the above-mentioned processing in the ingredient recognition unit can be performed using, for example, AI, or can be performed without using AI. For example, the ingredient recognition unit can input literature related to ingredients into a generation AI and have the generation AI analyze it.

[0104] The ingredient recognition unit can take into account the market value of the ingredient when recognizing ingredients. For example, the ingredient recognition unit prioritizes the recognition of ingredients with high market value. The ingredient recognition unit can also improve the recognition accuracy of specific ingredients by taking market value into account. The ingredient recognition unit can also improve the recognition algorithm for specific ingredients based on market value. In this way, taking the market value of ingredients into account improves recognition accuracy. Some or all of the above-mentioned processing in the ingredient recognition unit can be performed, for example, using AI or without AI. For example, the ingredient recognition unit can input market value information of ingredients into a generation AI and have the generation AI analyze it.

[0105] The recipe generation unit can estimate a user's emotions and adjust the way a recipe is presented based on the estimated user emotions. For example, if a user is feeling stressed, the recipe generation unit can provide a simple and easy-to-understand recipe. Furthermore, if a user is relaxed, the recipe generation unit can provide detailed instructions and customizable options. Furthermore, if a user is in a hurry, the recipe generation unit can provide a recipe that can be made in a short time. By adjusting the way a recipe is presented based on the user's emotions, understanding of the recipe is improved. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the recipe generation unit can be performed using, for example, AI, or without AI. For example, the recipe generation unit can have a generation AI estimate the user's emotions and adjust the way a recipe is presented based on the estimation result.

[0106] When generating a recipe, the recipe generation unit can adjust the level of detail of the recipe based on the importance of the ingredients. For example, the recipe generation unit provides detailed instructions for main ingredients and simplified instructions for secondary ingredients. The recipe generation unit can also provide detailed instructions for cooking main ingredients and simplified instructions for cooking other ingredients. The recipe generation unit can also provide detailed instructions for cooking times and temperatures for main ingredients and simplified information for secondary ingredients. In this way, adjusting the level of detail of the recipe based on the importance of the ingredients improves understanding of the recipe. Some or all of the above-mentioned processes in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input ingredient importance information into the generation AI and have the generation AI analyze it.

[0107] When generating a recipe, the recipe generation unit can apply different generation algorithms depending on the category of the dish. For example, the recipe generation unit can apply different algorithms to generate recipes for Japanese cuisine and Western cuisine, thereby improving accuracy. The recipe generation unit can also apply different algorithms to generate recipes for desserts and main dishes, thereby improving accuracy. The recipe generation unit can also apply different algorithms to generate recipes for vegetarian cuisine and meat dishes, thereby improving accuracy. In this way, by applying different generation algorithms depending on the category of the dish, the accuracy of the recipe is improved. Some or all of the above-mentioned processing in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input dish category information into the generation AI and have it analyzed by the generation AI.

[0108] When generating a recipe, the recipe generation unit can improve the accuracy of generation by referring to the user's past recipe results. The recipe generation unit, for example, improves the generation algorithm based on the results of recipes created by the user in the past. The recipe generation unit can also reflect information about the user's favorite recipes in the next recipe generation. The recipe generation unit can also analyze the user's past recipe results to improve the accuracy of generation of specific dishes. In this way, the accuracy of generation is improved by referring to the user's past recipe results. Some or all of the above-mentioned processing in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can have the generation AI analyze the user's past recipe results to improve the accuracy of generation.

[0109] The recipe generation unit can estimate the user's emotions and adjust the length of the recipe based on the estimated user emotions. For example, if the user is in a hurry, the recipe generation unit can provide a short, concise recipe. If the user is relaxed, the recipe generation unit can also provide a longer recipe with detailed steps. If the user is excited, the recipe generation unit can also provide a recipe with visually stimulating effects. By adjusting the length of the recipe based on the user's emotions, the recipe can be more easily understood. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the recipe generation unit can be performed using, for example, AI, or without AI. For example, the recipe generation unit can have the generation AI estimate the user's emotions and adjust the length of the recipe based on the estimation result.

[0110] When generating a recipe, the recipe generation unit can determine the priority of recipes based on the time when ingredients were submitted. For example, the recipe generation unit provides recipes that prioritize the use of ingredients that are close to their expiration date. The recipe generation unit can also provide recipes that prioritize the use of seasonal ingredients. The recipe generation unit can also provide recipes that prioritize the use of ingredients that the user recently purchased. This enables effective use of ingredients by determining the priority of recipes based on the time when ingredients were submitted. Some or all of the above-mentioned processing in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input information on the time when ingredients were submitted to the generation AI, which can then analyze the information.

[0111] The recipe generation unit can adjust the order of the recipe based on the relevance of ingredients when generating a recipe. For example, the recipe generation unit determines the order of the recipe based on the main ingredients. The recipe generation unit can also provide an optimal order of the recipe by taking into account the combination of ingredients. The recipe generation unit can also adjust the order of the recipe by taking into account the cooking time and temperature of the ingredients. In this way, adjusting the order of the recipe based on the relevance of ingredients improves cooking efficiency. Some or all of the above-mentioned processing in the recipe generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe generation unit can input information on the relevance of ingredients into the generation AI and have it analyzed by the generation AI.

[0112] When generating a recipe, the recipe generation unit can adjust the use of technical terms in the recipe according to the user's level of expertise. For example, the recipe generation unit can provide a recipe explained in simple terms for beginners. The recipe generation unit can also provide a recipe including slightly more technical terms for intermediate users. The recipe generation unit can also provide a detailed recipe using a lot of technical terms for advanced users. In this way, adjusting the use of technical terms in the recipe according to the user's level of expertise improves understanding of the recipe. Some or all of the above-described processing in the recipe generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the recipe generation unit can input the user's level of expertise information into the generation AI and have the generation AI analyze it.

[0113] The recipe providing unit can estimate a user's emotions and adjust the recipe presentation method based on the estimated user emotions. For example, if the user is feeling stressed, the recipe providing unit can provide a simple and easy-to-understand recipe. Furthermore, if the user is relaxed, the recipe providing unit can also provide detailed instructions and customizable options. Furthermore, if the user is in a hurry, the recipe providing unit can also provide a recipe that can be made in a short time. This improves the user's understanding of the recipe by adjusting the recipe presentation method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the recipe providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe providing unit can have a generative AI estimate the user's emotions and adjust the recipe presentation method based on the estimation result.

[0114] When providing a recipe, the recipe providing unit can select the optimal serving method by referring to the user's past recipe history. For example, the recipe providing unit selects the optimal serving method based on the user's past preferred recipe serving methods. The recipe providing unit can also preferentially display specific serving methods from the user's past recipe history. The recipe providing unit can also analyze the user's past recipe history and improve the serving method for a specific dish. In this way, the optimal serving method can be selected by referring to the user's past recipe history. Some or all of the above-described processing in the recipe providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe providing unit can have a generation AI analyze the user's past recipe history to select the optimal serving method.

[0115] When providing a recipe, the recipe providing unit can customize the provided content based on the user's current living situation. For example, if the user is busy, the recipe providing unit can provide a recipe that can be made in a short time. Furthermore, if the user is relaxed, the recipe providing unit can also provide a recipe that includes detailed steps. Furthermore, if the user does not have a specific ingredient, the recipe providing unit can also provide a recipe that excludes that ingredient. This improves the applicability of the recipe by customizing the provided content based on the user's current living situation. Some or all of the above-mentioned processing in the recipe providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the recipe providing unit can input the user's living situation information into a generation AI and have the generation AI analyze it.

[0116] When providing a recipe, the recipe providing unit can improve the providing method by reflecting user feedback. For example, the recipe providing unit selects the optimal providing method based on feedback provided by the user. The recipe providing unit can also preferentially display a specific providing method based on user feedback. The recipe providing unit can also analyze user feedback and customize the providing interface. In this way, the providing method can be improved by reflecting user feedback. Some or all of the above-described processing in the recipe providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe providing unit can have a generation AI analyze user feedback and improve the providing method.

[0117] The recipe providing unit can estimate a user's emotions and determine the order in which recipes are provided based on the estimated user emotions. For example, if a user is feeling stressed, the recipe providing unit can prioritize providing recipes that are easy to make. Furthermore, if a user is relaxed, the recipe providing unit can prioritize providing recipes that include detailed instructions. Furthermore, if a user is in a hurry, the recipe providing unit can prioritize providing recipes that can be made in a short time. This improves the applicability of recipes by determining the order in which recipes are provided based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the recipe providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the recipe providing unit can have a generative AI estimate a user's emotions and determine the order in which recipes are provided based on the estimation results.

[0118] When providing a recipe, the recipe providing unit can select the optimal delivery method by taking into account the user's geographical location information. For example, if the user lives in a specific area, the recipe providing unit can provide recipes using ingredients that are easily available in that area. Furthermore, if the user is traveling, the recipe providing unit can also provide recipes using local ingredients based on the user's current location. Furthermore, if the user prefers cuisine from a specific area, the recipe providing unit can also preferentially provide recipes from that area. In this way, the optimal delivery method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the recipe providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe providing unit can have a generation AI analyze the user's geographical location information and select the optimal delivery method.

[0119] When providing a recipe, the recipe providing unit can analyze the user's social media activity and customize the content to be provided. For example, the recipe providing unit can provide related recipes based on information about dishes shared by the user on social media. The recipe providing unit can also analyze the content posted by the user on social media and provide related recipes. The recipe providing unit can also provide related recipes by referring to the activity of the user's friends on social media. In this way, the content to be provided can be customized by analyzing the user's social media activity. Some or all of the above-described processing in the recipe providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe providing unit can customize the content to be provided by having a generation AI analyze the user's social media activity.

[0120] When providing a recipe, the recipe providing unit can customize the serving method by reflecting the user's past feedback. For example, the recipe providing unit selects the optimal serving method based on feedback provided by the user in the past. The recipe providing unit can also preferentially display a specific serving method based on the user's past feedback. The recipe providing unit can also analyze the user's feedback and customize the serving interface. This allows the serving method to be customized by reflecting the user's past feedback. Some or all of the above-mentioned processing in the recipe providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the recipe providing unit can customize the serving method by having a generation AI analyze the user's past feedback. === Hard Collateral 1-1 === Each of the multiple elements, including the condition input unit, ingredient input unit, ingredient recognition unit, recipe generation unit, and recipe providing unit, described above, is realized by at least one of the smart device 14 and the data processing device 12. For example, the condition input unit is realized by the control unit 46A of the smart device 14 and inputs various conditions such as the user's preferences, age, and hometown. The ingredient input unit takes photos of ingredients using the camera 42 of the smart device 14 and inputs them into the generation AI. The ingredient recognition unit is realized by the specific processing unit 290 of the data processing device 12 and recognizes ingredients from the photos and analyzes the information. The recipe generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a cooking recipe customized based on the user's preferences, age, and hometown. The recipe providing unit provides the user with the cooking recipe generated using the output device 40 of the smart device 14. The condition input unit can estimate the user's emotions and determine the priority of information to be input based on the estimated user emotions. === Hard Collateral 1-2 === Each of the multiple elements, including the condition input unit, ingredient input unit, ingredient recognition unit, recipe generation unit, and recipe providing unit, described above, is realized by, for example, at least one of the smart glasses 214 and the data processing device 12. For example, the condition input unit is realized by the control unit 46A of the smart glasses 214 and inputs various conditions such as the user's preferences, age, and hometown. The ingredient input unit takes photos of ingredients using the camera 42 of the smart glasses 214 and inputs them to the generation AI. The ingredient recognition unit is realized by the specific processing unit 290 of the data processing device 12 and recognizes ingredients from the photos and analyzes the information. The recipe generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a cooking recipe customized based on the user's preferences, age, and hometown. The recipe providing unit provides the generated cooking recipe to the user using the speaker 240 of the smart glasses 214. The condition input unit can estimate the user's emotions and determine the priority of information to be input based on the estimated user emotions. === Hard Collateral 1-3 === Each of the multiple elements, including the condition input unit, ingredient input unit, ingredient recognition unit, recipe generation unit, and recipe providing unit, described above, is realized by, for example, at least one of the headset terminal 314 and the data processing device 12. For example, the condition input unit is realized by the control unit 46A of the headset terminal 314 and inputs various conditions such as the user's preferences, age, and hometown. The ingredient input unit takes photos of ingredients using the camera 42 of the headset terminal 314 and inputs them to the generation AI. The ingredient recognition unit is realized by the specific processing unit 290 of the data processing device 12 and recognizes ingredients from the photos and analyzes the information. The recipe generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a cooking recipe customized based on the user's preferences, age, and hometown. The recipe providing unit provides the generated cooking recipe to the user using the display 343 of the headset terminal 314. The condition input unit can estimate the user's emotions and determine the priority of information to be input based on the estimated user emotions. === Hard Collateral 1-4 === Each of the multiple elements, including the condition input unit, ingredient input unit, ingredient recognition unit, recipe generation unit, and recipe providing unit, described above, is realized by, for example, at least one of the robot 414 and the data processing device 12. For example, the condition input unit is realized by the control unit 46A of the robot 414 and inputs various conditions such as the user's preferences, age, and hometown. The ingredient input unit takes photos of ingredients using the camera 42 of the robot 414 and inputs them into the generation AI. The ingredient recognition unit is realized by the specific processing unit 290 of the data processing device 12 and recognizes ingredients from the photos and analyzes the information. The recipe generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a cooking recipe customized based on the user's preferences, age, and hometown. The recipe providing unit provides the user with the cooking recipe generated using the speaker 240 of the robot 414. The condition input unit can estimate the user's emotions and determine the priority of the information to be input based on the estimated user emotions.

[0121] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0122] The condition input unit can input the user's current mood and physical condition in addition to the user's preferences, age, and hometown. For example, if the user is tired, easy-to-make recipes will be preferentially suggested. Also, if the user wants to consume specific nutrients, nutritionally balanced recipes can be provided by inputting that information. Furthermore, if the user wants a recipe for a specific event (e.g., a birthday or anniversary), recipes suitable for the event can be suggested by inputting that information. This makes it possible to provide recipes that meet the diverse needs of users.

[0123] The ingredient input unit can input ingredient information by scanning the barcode of an ingredient in addition to a photo of the ingredient taken by the user. For example, when a user scans the barcode of an ingredient in the refrigerator, detailed information about the ingredient (such as expiration date and nutritional information) is automatically obtained. Also, by scanning the receipt of the purchased ingredient, the user can input information about the purchased ingredient all at once. Furthermore, the user can input ingredient information using voice input; for example, by inputting "three tomatoes" by voice, ingredient information can be easily added. This makes the input of ingredient information more convenient and efficient.

[0124] When recognizing ingredients from a photo, the ingredient recognition unit can also evaluate the freshness and quality of the ingredients. For example, it can analyze the color and shape of the ingredients from the photo to determine whether they are fresh. It can also detect scratches and discoloration on the surface of the ingredients to evaluate their quality. Furthermore, it can prioritize the recognition of ingredients that should be used soon, taking into account their expiration dates. This allows users to be recommended recipes that use fresh and high-quality ingredients.

[0125] The recipe generation unit can also take into account the user's past recipe history when generating a cooking recipe customized based on the user's preferences, age, and place of origin. For example, the next recipe suggestion can be based on the user's ratings and feedback on recipes they have created in the past. Also, if a user frequently uses a particular ingredient, it can prioritize recipes that use that ingredient. Furthermore, it can also suggest more suitable recipes by taking into account the success rate and cooking time of recipes the user has created in the past. This makes it possible to provide recipes that are more suited to the user's preferences and needs.

[0126] When providing the generated cooking recipe to the user, the recipe providing unit can provide it in the optimal format depending on the user's device and platform. For example, if the user is using a smartphone, the recipe can be displayed in a mobile-friendly format. Also, if the user is using a tablet, the recipe can be provided in a layout suitable for a large screen. Furthermore, if the user is using a smart speaker, the recipe can be read aloud. This allows the user to obtain the recipe in the optimal format for their device and platform.

[0127] The condition input unit can estimate the user's emotions and prioritize the information to be input based on the estimated user emotions. For example, if the user is feeling stressed, simple input items can be displayed preferentially, and detailed information can be displayed later. The condition input unit can also display detailed input items preferentially and provide customizable options when the user is relaxed. The condition input unit can also allow the user to enter only the most important information when the user is in a hurry, and allow other information to be added later. In this way, prioritizing input information based on the user's emotions reduces the burden on the user.

[0128] The ingredient input unit can estimate the user's emotions and adjust the timing of ingredient input based on the estimated user emotions. For example, if the user is feeling stressed, the ingredient input can be simplified and more details can be added later. The ingredient input unit can also prompt the user to enter detailed ingredient information if the user is relaxed. The ingredient input unit can also prompt the user to enter only the most important ingredients if the user is in a hurry and allow other information to be added later. This improves the convenience of input by adjusting the timing of ingredient input based on the user's emotions.

[0129] The ingredient recognition unit can estimate the user's emotions and adjust the accuracy of ingredient recognition based on the estimated user emotions. For example, if the user is stressed, simple ingredient recognition can be prioritized and detailed recognition can be postponed. Alternatively, if the user is relaxed, the ingredient recognition unit can perform detailed ingredient recognition and provide customizable options. Alternatively, if the user is in a hurry, the ingredient recognition unit can recognize only the most important ingredients and allow other information to be added later. This improves the accuracy of recognition by adjusting the accuracy of ingredient recognition based on the user's emotions.

[0130] The recipe generation unit can estimate the user's emotions and adjust the way the recipe is presented based on the estimated user's emotions. For example, if the user is feeling stressed, the recipe generation unit can provide a simple and easy-to-understand recipe. If the user is feeling relaxed, the recipe generation unit can also provide detailed instructions and customizable options. If the user is in a hurry, the recipe generation unit can also provide a recipe that can be made in a short time. In this way, adjusting the way the recipe is presented based on the user's emotions improves the user's understanding of the recipe.

[0131] The recipe providing unit 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 feeling stressed, the recipe providing unit can provide a simple and easy-to-understand recipe. If the user is feeling relaxed, the recipe providing unit can also provide detailed instructions and customizable options. If the user is in a hurry, the recipe providing unit can also provide a recipe that can be made in a short time. In this way, adjusting the way in which the recipe is presented based on the user's emotions improves the user's understanding of the recipe.

[0132] The processing flow of the second embodiment will be briefly explained below.

[0133] Step 1: The condition input section allows users to input various conditions, including their preferences, age, and hometown. For example, users can input their favorite types of cuisine, allergy information, and health conditions. Step 2: The ingredient input unit inputs photos of ingredients taken by the user into the generation AI. For example, the user can take photos of leftover vegetables or meat in the refrigerator and input them into the generation AI. Step 3: The ingredient recognition unit uses the generation AI to recognize ingredients from the photo and analyze the information. For example, the generation AI recognizes ingredients from the photo and analyzes the information. Step 4: The recipe generation unit uses the generation AI to generate customized cooking recipes based on the user's preferences, age, and place of origin. For example, if the user likes Japanese food and wants to make a dish using leftover vegetables and meat in the refrigerator, the generation AI will use that information to generate a Japanese recipe. Step 5: The recipe provider provides the generated cooking recipe to the user. For example, the generated cooking recipe is displayed on the user's smartphone or tablet.

[0134] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0139] 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.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] 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.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] 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.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0155] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0156] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0157] 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.

[0158] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0160] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0161] 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.

[0162] 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.

[0163] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0164] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0165] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0166] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0171] 7, the 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.

[0172] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0173] 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.

[0174] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0175] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0176] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0177] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0178] 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.

[0179] 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.

[0180] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0181] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0182] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0183] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0184] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0185] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0186] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0187] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0188] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0189] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0190] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0191] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0192] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0193] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0194] 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.

[0195] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0196] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0197] 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.

[0198] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0199] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0200] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0201] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0202] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0203] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0204] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0205] [Explanation of symbols]

[0206] 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 condition input section for inputting various conditions including the user's preferences, age, and place of origin; an ingredient input unit that takes a photo of the remaining ingredients based on the information input by the condition input unit and inputs the photo to the generation AI; an ingredient recognition unit that analyzes the ingredient information input by the ingredient input unit; a recipe generation unit that generates a cooking recipe suitable for the user based on the information analyzed by the ingredient recognition unit; a recipe providing unit that provides a user with the recipe generated by the recipe generating unit. A system characterized by:

2. The condition input unit Enter information including user preferences, age, hometown, allergy information, and health conditions 2. The system of claim 1.

3. The ingredient input unit The user takes a photo of the food and inputs it into the AI ​​generator.

2. The system of claim 1.

4. The ingredient recognition unit Using generative AI to recognize ingredients from photos and analyze their information 2. The system of claim 1.

5. The recipe generation unit Use generative AI to generate customized cooking recipes based on the user's preferences, age, and place of origin.

2. The system of claim 1.

6. The recipe providing unit Providing the generated recipe to the user 2. The system of claim 1.

7. The recipe generation unit Learns user input information and reflects it in future recipe suggestions 2. The system of claim 1.

8. The condition input unit Estimate the user's emotions and prioritize the information to be input based on the estimated user emotions.

2. The system of claim 1.

Images