system

Abstract

The system according to this embodiment aims to learn secret recipes and assist in cooking. [Solution] The system according to the embodiment comprises a learning unit, an assist unit, a suggestion unit, and a creation unit. The learning unit learns secret recipes. The assist unit assists cooking based on the recipes learned by the learning unit. The suggestion unit makes suggestions for improving the recipes based on the cooking results obtained by the assist unit. The creation unit creates new variations based on the suggestions obtained by the suggestion unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there was a problem that it was difficult to inherit, reproduce, improve, and create new variations of secret recipe techniques.

[0005] The system according to the embodiment aims to learn a secret recipe and assist in cooking.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a learning unit, an assist unit, a suggestion unit, and a creation unit. The learning unit learns a secret recipe. The assist unit assists cooking based on the recipe learned by the learning unit. The suggestion unit makes suggestions for improving the recipe based on the cooking results obtained by the assist unit. The creation unit creates new variations based on the suggestions obtained by the suggestion unit. [Effects of the Invention]

[0007] The system according to this embodiment can learn secret recipes and assist in cooking. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The cooking assistance system according to an embodiment of the present invention is a system in which AI learns a secret recipe and assists in cooking. By learning the secret recipe and assisting in cooking, this cooking assistance system facilitates the transfer of techniques and enables accurate reproduction of the recipe. The cooking assistance system also suggests improvements to the recipe and creates new variations. For example, the cooking assistance system uses image and voice recognition to analyze the cooking process in detail, and the generating AI suggests improvements to the recipe. This mechanism allows chefs to gain new cooking ideas and stimulate their inspiration. First, the cooking assistance system's AI learns the secret recipe. During this process, detailed recipe input and recording and analysis of the cooking process are performed. For example, the cooking assistance system films the chef cooking with a camera, and the AI ​​analyzes the video to learn the cooking procedures and techniques. Next, the cooking assistance system's AI assists in cooking based on the learned recipe. For example, the cooking assistance system instructs the chef on the cooking procedure through an interactive touchscreen interface. This allows the chef to cook according to the exact recipe. Furthermore, the cooking assistance system also suggests improvements to recipes and creates new variations. For example, based on recipes learned by the generating AI, it suggests new cooking methods and ingredient combinations. This allows chefs to gain new culinary ideas. This system facilitates the transfer of techniques and enables accurate reproduction of recipes. In addition, the AI's suggestions generate new culinary ideas, promoting innovation in the culinary industry. For example, home cooking experts and restaurant owners can train the AI ​​with their secret recipes and reproduce or improve them, solving the challenge of technique transfer. This also streamlines new menu development and improves the productivity of the entire culinary industry. In summary, the cooking assistance system learns secret recipes, assists in cooking, and can suggest improvements to recipes and create new variations.

[0029] The cooking assistance system according to this embodiment comprises a learning unit, an assistance unit, a suggestion unit, and a creation unit. The learning unit learns secret recipes. The learning unit performs tasks such as detailed recipe input and recording and analyzing the cooking process. The learning unit can learn cooking procedures and techniques by having a camera film the chef cooking and an AI analyze the footage. The assistance unit assists cooking based on the recipes learned by the learning unit. The assistance unit instructs the chef on cooking procedures, for example, through an interactive touchscreen interface. The assistance unit can also instruct the chef on cooking procedures using voice guidance or visual guidance. The suggestion unit makes suggestions for improving the recipe based on the cooking results obtained by the assistance unit. The suggestion unit analyzes the cooking process in detail using image or voice recognition, for example, and the generating AI makes suggestions for improving the recipe. The suggestion unit can also propose new cooking methods and ingredient combinations based on the recipes learned by the generating AI. The creation unit creates new variations based on the suggestions obtained by the suggestion unit. The creation unit, for example, uses a generation AI to propose new cooking methods and ingredient combinations. Based on the new cooking methods and ingredient combinations proposed by the generation AI, the creation unit can create new variations. As a result, the cooking assistance system according to this embodiment can learn secret recipes, assist in cooking, suggest improvements to recipes, and create new variations.

[0030] The learning unit learns secret recipes. For example, the learning unit inputs detailed recipes and records and analyzes the cooking process. Specifically, it films the chef cooking with a camera, and the AI ​​analyzes the footage to learn cooking procedures and techniques. The camera has high resolution, allowing it to accurately capture even the smallest movements and procedures of cooking. The AI ​​uses video analysis technology to analyze in detail the chef's hand movements, the tools used, and how ingredients are handled. For example, it can learn the chef's techniques step by step, such as how to use a knife, adjust the heat, and add seasonings. The learning unit can also use speech recognition technology to record the cooking procedures and tips that the chef explains verbally as text data. This allows it to acquire cooking information from both video and audio, and build more accurate recipe data. Furthermore, the learning unit can refer to past cooking data and recipe databases, and integrate existing knowledge with newly learned information to gain a deeper understanding of secret recipes. This allows the learning unit to faithfully reproduce the chef's techniques and know-how and build a foundation for providing it to other departments.

[0031] The assist unit assists in cooking based on recipes learned by the learning unit. For example, the assist unit guides the cook through cooking steps via an interactive touchscreen interface. The touchscreen is designed for intuitive operation, allowing the cook to easily review cooking steps. The assist unit can also guide the cook using voice and visual guides. Voice guides provide detailed explanations of each cooking step, improving efficiency during cooking as the cook receives instructions hands-free. Visual guides use images and videos to show cooking steps, making them easy for the cook to understand visually. For example, videos demonstrating how to cut ingredients or use cooking utensils help the cook accurately reproduce the steps. The assist unit can also monitor the cooking status in real time and provide advice and warnings as needed. For example, it can display alerts prompting appropriate adjustments if the heat is too high or the cooking time is too long. This allows the assist unit to support the cook in cooking accurately and efficiently, improving the quality of the food.

[0032] The suggestion unit makes recipe improvement suggestions based on the cooking results obtained by the assistance unit. For example, the suggestion unit analyzes the cooking process in detail using image and voice recognition, and the generative AI makes recipe improvement suggestions. Specifically, it analyzes images taken and audio data recorded during cooking to identify problems and areas for improvement at each step of cooking. Based on this data, the generative AI optimizes the cooking procedure and suggests new cooking methods. For example, it can suggest detailed improvements such as how ingredients are cut, adjusting cooking times, and mixing seasonings. The suggestion unit can also suggest new cooking methods and ingredient combinations based on recipes learned by the generative AI. For example, it can suggest changing the taste or texture by substituting certain ingredients with others. Furthermore, the suggestion unit can collect feedback from users and continuously improve the accuracy and effectiveness of its suggestions. As a result, the suggestion unit can always provide highly accurate recipe improvement suggestions based on the latest information, improving the quality and variety of dishes.

[0033] The Creation Department creates new variations based on proposals received from the Proposal Department. For example, the Creation Department uses a Generative AI to suggest new cooking methods and ingredient combinations. Specifically, the Generative AI generates original recipes based on improvements and new ideas provided by the Proposal Department. The Generative AI refers to past recipe and cooking data to provide ideas for creating completely new dishes. For example, it can create various variations such as new recipes that fuse dishes from different cultures or recipes that use health-conscious ingredients. The Creation Department can create new variations based on the new cooking methods and ingredient combinations suggested by the Generative AI. This allows the Creation Department to constantly incorporate new ideas and enrich the variety of dishes. In addition, the Creation Department can collect feedback from users and evaluate and improve new variations. This allows the Creation Department to provide new dishes that meet user needs and preferences, improving the enjoyment and satisfaction of cooking.

[0034] The learning unit can perform detailed recipe input and record and analyze the cooking process. For example, the learning unit can input detailed recipe information such as the type and quantity of ingredients and the procedure. To record and analyze the cooking process, the learning unit can film the cooking process with a camera and have the AI ​​analyze the video. To record and analyze the cooking process, the learning unit can also record the cooking process with sensors and have the AI ​​analyze the data. This improves the accuracy of learning by performing detailed recipe input and recording and analyzing the cooking process. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input video data of the cooking process filmed with a camera into a generating AI and have the generating AI perform the learning of cooking procedures and techniques.

[0035] The assist unit can provide instructions for cooking procedures through an interactive touchscreen interface. For example, the assist unit can use the touchscreen interface to instruct the cook on cooking procedures. The assist unit can use the touchscreen interface to visually display the cooking procedures to the cook. The assist unit can also use the touchscreen interface to provide voice instructions for cooking procedures to the cook. This makes cooking assistance easier by providing instructions for cooking procedures through an interactive touchscreen interface. Some or all of the above-described processes in the assist unit may be performed using AI, for example, or without AI. For example, the assist unit can use the touchscreen interface to have a generating AI execute instructions for cooking procedures.

[0036] The suggestion unit can analyze the cooking process in detail using image and voice recognition, and the generating AI can suggest improvements to the recipe. For example, the suggestion unit can photograph the cooking process with a camera and analyze the cooking procedure using image recognition technology. The suggestion unit can also record the cooking process with voice and analyze the cooking procedure using voice recognition technology. The suggestion unit can combine image recognition technology and voice recognition technology to analyze the cooking process in detail. This makes it easier to improve recipes by analyzing the cooking process in detail using image and voice recognition and having the generating AI suggest improvements to the recipe. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input image data and voice data of the cooking process into the generating AI and have the generating AI execute recipe improvement suggestions.

[0037] The creation unit allows the generative AI to propose new cooking methods and ingredient combinations. For example, the creation unit can propose new cooking methods based on recipes learned by the generative AI. The creation unit can also propose new ingredient combinations based on recipes learned by the generative AI. The creation unit can propose new cooking methods and ingredient combinations based on recipes learned by the generative AI. This makes it easier to create new variations by having the generative AI propose new cooking methods and ingredient combinations. Some or all of the above processing in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can create new variations based on new cooking methods and ingredient combinations proposed by the generative AI.

[0038] The learning unit can optimize its learning algorithm by referring to past cooking data. For example, the learning unit can prioritize learning recipes with high success rates from past cooking data. The learning unit can also analyze past cooking data to identify the causes of failures and adjust the learning algorithm accordingly. Based on past cooking data, the learning unit can optimize cooking time and procedures. This improves the accuracy of learning by optimizing the learning algorithm by referring to past cooking data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past cooking data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0039] The learning unit can perform learning while taking into account fluctuations in the cooking environment. For example, the learning unit can learn the optimal cooking procedure by taking into account temperature fluctuations in the cooking environment. The learning unit can also learn how to store ingredients by taking into account humidity fluctuations in the cooking environment. Based on fluctuations in the cooking environment, the learning unit can optimize cooking time and heat level. As a result, the accuracy of learning is improved by performing learning while taking fluctuations in the cooking environment into account. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input cooking environment data into a generating AI and have the generating AI perform the learning.

[0040] The learning unit can learn region-specific recipes by taking into account the geographical location of the chef. For example, if the chef is in Japan, the learning unit can learn region-specific recipes for Japan. If the chef is in Italy, the learning unit can also learn region-specific recipes for Italy. If the chef is in India, the learning unit can learn region-specific recipes for India. This improves the accuracy of learning by taking into account the geographical location of the chef when learning region-specific recipes. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the chef's geographical location information into a generating AI and have the generating AI perform the learning of region-specific recipes.

[0041] The learning unit can analyze a chef's social media activity and learn related recipes. For example, the learning unit can learn recipes that a chef has shared on social media. The learning unit can also learn recipes from chefs that a chef follows. The learning unit can learn recipes that a chef has "liked". By analyzing a chef's social media activity and learning related recipes, the accuracy of the learning is improved. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input a chef's social media activity data into a generating AI and have the generating AI perform the task of learning related recipes.

[0042] The assist unit can monitor the usage status of cooking appliances in real time and issue instructions at the optimal time. For example, the assist unit can monitor the temperature of cooking appliances in real time and issue instructions for adjusting the heat at the optimal time. The assist unit can also monitor the usage status of cooking appliances and issue instructions for the next step. The assist unit can monitor the condition of cooking appliances and issue instructions for necessary maintenance. This improves cooking efficiency by monitoring the usage status of cooking appliances in real time and issuing instructions at the optimal time. Some or all of the above processes in the assist unit may be performed using AI, for example, or without AI. For example, the assist unit can input cooking appliance usage data into a generating AI and have the generating AI execute instructions at the optimal time.

[0043] The assist unit can issue instructions while taking into account fluctuations in the cooking environment. For example, the assist unit can issue instructions for the optimal cooking procedure while taking into account temperature fluctuations in the cooking environment. The assist unit can also issue instructions on how to store ingredients while taking into account humidity fluctuations in the cooking environment. Based on fluctuations in the cooking environment, the assist unit can issue instructions on cooking time and heat level. As a result, the accuracy of cooking is improved by issuing instructions while taking into account fluctuations in the cooking environment. Some or all of the above processing in the assist unit may be performed using AI, for example, or without using AI. For example, the assist unit can input cooking environment data into a generating AI and have the generating AI execute the instructions.

[0044] The assistance unit can instruct region-specific cooking procedures while considering the chef's geographical location. For example, if the chef is in Japan, the assistance unit will instruct region-specific cooking procedures for Japan. If the chef is in Italy, the assistance unit can also instruct region-specific cooking procedures for Italy. If the chef is in India, the assistance unit can instruct region-specific cooking procedures for India. This improves cooking accuracy by instructing region-specific cooking procedures while considering the chef's geographical location. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the chef's geographical location information into a generating AI and have the generating AI execute region-specific cooking procedure instructions.

[0045] The assistance unit can analyze a chef's social media activity and provide relevant cooking instructions. For example, the assistance unit can provide instructions for cooking procedures shared by the chef on social media. The assistance unit can also provide instructions for cooking procedures from chefs the chef follows. The assistance unit can provide instructions for cooking procedures that the chef has "liked". By analyzing the chef's social media activity and providing relevant cooking instructions, the accuracy of the cooking is improved. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the chef's social media activity data into a generating AI and have the generating AI execute instructions for relevant cooking procedures.

[0046] The suggestion unit can make optimal improvement suggestions by referring to past cooking data. For example, the suggestion unit can make improvement suggestions with a high success rate based on past cooking data. The suggestion unit can also analyze past cooking data, identify the causes of failures, and make improvement suggestions. Based on past cooking data, the suggestion unit can make improvement suggestions that optimize cooking time and procedures. This makes it easier to improve recipes by making optimal improvement suggestions by referring to past cooking data. Some or all of the above processes in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input past cooking data into a generating AI and have the generating AI execute optimal improvement suggestions.

[0047] The suggestion unit can make improvement suggestions by taking into account fluctuations in the cooking environment. For example, the suggestion unit can make optimal improvement suggestions by taking into account temperature fluctuations in the cooking environment. The suggestion unit can also make improvement suggestions for food storage methods by taking into account humidity fluctuations in the cooking environment. Based on fluctuations in the cooking environment, the suggestion unit can make improvement suggestions that optimize cooking time and heat level. This makes it easier to improve recipes by making improvement suggestions while taking into account fluctuations in the cooking environment. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without using AI. For example, the suggestion unit can input cooking environment data into a generating AI and have the generating AI execute improvement suggestions.

[0048] The suggestion unit can make region-specific improvement suggestions by taking into account the geographical location of the chef. For example, if the chef is in Japan, the suggestion unit can make region-specific improvement suggestions for Japan. If the chef is in Italy, the suggestion unit can also make region-specific improvement suggestions for Italy. If the chef is in India, the suggestion unit can make region-specific improvement suggestions for India. This makes it easier to improve recipes by making region-specific improvement suggestions by taking into account the geographical location of the chef. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the chef's geographical location information into a generating AI and have the generating AI execute region-specific improvement suggestions.

[0049] The suggestion unit can analyze a chef's social media activity and make relevant improvement suggestions. For example, the suggestion unit can make improvement suggestions based on recipes shared by the chef on social media. The suggestion unit can also make improvement suggestions based on recipes from chefs followed by the chef. The suggestion unit can also make improvement suggestions based on recipes that the chef has "liked". This makes it easier to improve recipes by analyzing the chef's social media activity and making relevant improvement suggestions. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit can input the chef's social media activity data into a generating AI and have the generating AI execute relevant improvement suggestions.

[0050] The creation unit can create optimal new variations by referring to past cooking data. For example, the creation unit can create new variations with a high success rate from past cooking data. The creation unit can also analyze past cooking data, identify the causes of failures, and create new variations. Based on past cooking data, the creation unit can create new variations that optimize cooking time and procedures. In this way, new culinary ideas can be obtained by creating optimal new variations by referring to past cooking data. Some or all of the above processes in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input past cooking data into a generation AI and have the generation AI perform the creation of new variations.

[0051] The creation unit can create new variations by taking into account fluctuations in the cooking environment. For example, the creation unit can create an optimal new variation by taking into account temperature fluctuations in the cooking environment. The creation unit can also incorporate food preservation methods into the new variations by taking into account humidity fluctuations in the cooking environment. Based on fluctuations in the cooking environment, the creation unit can create new variations with optimized cooking time and heat levels. In this way, new cooking ideas can be obtained by creating new variations while taking into account fluctuations in the cooking environment. Some or all of the above processes in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input cooking environment data into a generation AI and have the generation AI perform the creation of new variations.

[0052] The creation unit can create new regional variations by taking into account the geographical location of the chef. For example, if the chef is in Japan, the creation unit can create new regional variations specific to Japan. If the chef is in Italy, the creation unit can also create new regional variations specific to Italy. If the chef is in India, the creation unit can create new regional variations specific to India. In this way, new culinary ideas can be obtained by creating new regional variations by taking into account the geographical location of the chef. Some or all of the above processing in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input the chef's geographical location information into a generation AI and have the generation AI perform the creation of new regional variations.

[0053] The creation unit can analyze a chef's social media activity and create related new variations. For example, the creation unit can create new variations based on recipes shared by the chef on social media. The creation unit can also create new variations based on recipes from chefs that the chef follows. The creation unit can also create new variations based on recipes that the chef "likes". In this way, new culinary ideas can be obtained by analyzing a chef's social media activity and creating related new variations. Some or all of the above processes in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input the chef's social media activity data into a generation AI and have the generation AI create related new variations.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The cooking assistance system can also include a health management unit that monitors the user's health condition and suggests recipes based on that condition. For example, the health management unit can monitor the user's blood pressure and blood sugar levels and suggest low-salt and low-sugar recipes based on this data. The health management unit can also consider the user's allergy information and suggest recipes that do not contain allergens. Furthermore, the health management unit can monitor the user's weight and BMI and suggest recipes suitable for dieting and weight management. This makes it possible to suggest recipes that are tailored to the user's health condition, making health management easier.

[0056] The cooking assistance system can also include a history management unit that records the user's meal history and suggests recipes based on that history. For example, the history management unit records dishes the user has made and eaten in the past and suggests new recipes based on this data. The history management unit can also learn the user's preferences and eating habits and suggest recipes that suit the user's tastes. Furthermore, the history management unit can record the user's ratings of dishes they have made in the past and prioritize suggesting highly-rated dishes. This enables recipe suggestions based on the user's meal history, improving meal satisfaction.

[0057] The cooking assistance system can also include an inventory management unit that manages the user's food inventory and suggests recipes based on that inventory. For example, the inventory management unit monitors the food inventory in the refrigerator and pantry and suggests recipes based on this data. The inventory management unit can also suggest recipes that prioritize the use of ingredients nearing their expiration date. Furthermore, the inventory management unit can record the history of ingredients purchased by the user and suggest recipes based on this. This reduces food waste and enables efficient food management.

[0058] The cooking assistance system can also include a nutrition management unit that suggests recipes considering the nutritional balance of the user's diet. For example, the nutrition management unit monitors the user's daily nutrient intake and suggests balanced recipes based on this. If a specific nutrient is deficient, the nutrition management unit can also suggest recipes that supplement that nutrient. Furthermore, the nutrition management unit can suggest recipes tailored to the user's health goals (e.g., muscle building or weight loss). This enables recipe suggestions that consider the user's nutritional balance, promoting a healthy diet.

[0059] The cooking assistance system can also be equipped with a preference learning unit that learns the user's dietary preferences and suggests recipes based on those preferences. For example, the preference learning unit can learn the user's favorite ingredients and types of dishes and suggest recipes based on that. The preference learning unit can also prioritize suggesting dishes that the user has previously given high ratings to. Furthermore, the preference learning unit can analyze the user's eating patterns and suggest recipes based on that. This makes it possible to suggest recipes that match the user's preferences, improving meal satisfaction.

[0060] The cooking assistance system can also include a cultural consideration unit that suggests recipes taking into account the user's cultural background. For example, the cultural consideration unit can suggest traditional dishes or regionally specific recipes based on the user's place of origin and cultural background. The cultural consideration unit can also suggest appropriate recipes considering the user's religious dietary restrictions. Furthermore, the cultural consideration unit can suggest recipes that the whole family can enjoy, taking into account the eating habits of the user's family. This enables recipe suggestions that are tailored to the user's cultural background, thereby improving meal satisfaction.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The learning unit learns the secret recipe. The learning unit inputs detailed recipes and records and analyzes the cooking process. For example, by filming a chef cooking with a camera and having the AI ​​analyze the footage, the AI ​​can learn cooking procedures and techniques. Step 2: The assist unit assists with cooking based on the recipe learned by the learning unit. The assist unit guides the cook through the cooking procedure via an interactive touchscreen interface. It can also guide the cook through the cooking procedure using voice and visual guides. Step 3: The suggestion unit makes recipe improvement suggestions based on the cooking results obtained by the assistance unit. The suggestion unit analyzes the cooking process in detail using image and voice recognition, and the generating AI makes recipe improvement suggestions. Based on the recipes that the generating AI has learned, it can also suggest new cooking methods and ingredient combinations. Step 4: The creation unit creates new variations based on the proposals received from the suggestion unit. The creation unit can create new variations based on the new cooking methods and ingredient combinations suggested by the generation AI.

[0063] (Example of form 2) The cooking assistance system according to an embodiment of the present invention is a system in which AI learns a secret recipe and assists in cooking. By learning the secret recipe and assisting in cooking, this cooking assistance system facilitates the transfer of techniques and enables accurate reproduction of the recipe. The cooking assistance system also suggests improvements to the recipe and creates new variations. For example, the cooking assistance system uses image and voice recognition to analyze the cooking process in detail, and the generating AI suggests improvements to the recipe. This mechanism allows chefs to gain new cooking ideas and stimulate their inspiration. First, the cooking assistance system's AI learns the secret recipe. During this process, detailed recipe input and recording and analysis of the cooking process are performed. For example, the cooking assistance system films the chef cooking with a camera, and the AI ​​analyzes the video to learn the cooking procedures and techniques. Next, the cooking assistance system's AI assists in cooking based on the learned recipe. For example, the cooking assistance system instructs the chef on the cooking procedure through an interactive touchscreen interface. This allows the chef to cook according to the exact recipe. Furthermore, the cooking assistance system also suggests improvements to recipes and creates new variations. For example, based on recipes learned by the generating AI, it suggests new cooking methods and ingredient combinations. This allows chefs to gain new culinary ideas. This system facilitates the transfer of techniques and enables accurate reproduction of recipes. In addition, the AI's suggestions generate new culinary ideas, promoting innovation in the culinary industry. For example, home cooking experts and restaurant owners can train the AI ​​with their secret recipes and reproduce or improve them, solving the challenge of technique transfer. This also streamlines new menu development and improves the productivity of the entire culinary industry. In summary, the cooking assistance system learns secret recipes, assists in cooking, and can suggest improvements to recipes and create new variations.

[0064] The cooking assistance system according to this embodiment comprises a learning unit, an assistance unit, a suggestion unit, and a creation unit. The learning unit learns secret recipes. The learning unit performs tasks such as detailed recipe input and recording and analyzing the cooking process. The learning unit can learn cooking procedures and techniques by having a camera film the chef cooking and an AI analyze the footage. The assistance unit assists cooking based on the recipes learned by the learning unit. The assistance unit instructs the chef on cooking procedures, for example, through an interactive touchscreen interface. The assistance unit can also instruct the chef on cooking procedures using voice guidance or visual guidance. The suggestion unit makes suggestions for improving the recipe based on the cooking results obtained by the assistance unit. The suggestion unit analyzes the cooking process in detail using image or voice recognition, for example, and the generating AI makes suggestions for improving the recipe. The suggestion unit can also propose new cooking methods and ingredient combinations based on the recipes learned by the generating AI. The creation unit creates new variations based on the suggestions obtained by the suggestion unit. The creation unit, for example, uses a generation AI to propose new cooking methods and ingredient combinations. Based on the new cooking methods and ingredient combinations proposed by the generation AI, the creation unit can create new variations. As a result, the cooking assistance system according to this embodiment can learn secret recipes, assist in cooking, suggest improvements to recipes, and create new variations.

[0065] The learning unit learns secret recipes. For example, the learning unit inputs detailed recipes and records and analyzes the cooking process. Specifically, it films the chef cooking with a camera, and the AI ​​analyzes the footage to learn cooking procedures and techniques. The camera has high resolution, allowing it to accurately capture even the smallest movements and procedures of cooking. The AI ​​uses video analysis technology to analyze in detail the chef's hand movements, the tools used, and how ingredients are handled. For example, it can learn the chef's techniques step by step, such as how to use a knife, adjust the heat, and add seasonings. The learning unit can also use speech recognition technology to record the cooking procedures and tips that the chef explains verbally as text data. This allows it to acquire cooking information from both video and audio, and build more accurate recipe data. Furthermore, the learning unit can refer to past cooking data and recipe databases, and integrate existing knowledge with newly learned information to gain a deeper understanding of secret recipes. This allows the learning unit to faithfully reproduce the chef's techniques and know-how and build a foundation for providing it to other departments.

[0066] The assist unit assists in cooking based on recipes learned by the learning unit. For example, the assist unit guides the cook through cooking steps via an interactive touchscreen interface. The touchscreen is designed for intuitive operation, allowing the cook to easily review cooking steps. The assist unit can also guide the cook using voice and visual guides. Voice guides provide detailed explanations of each cooking step, improving efficiency during cooking as the cook receives instructions hands-free. Visual guides use images and videos to show cooking steps, making them easy for the cook to understand visually. For example, videos demonstrating how to cut ingredients or use cooking utensils help the cook accurately reproduce the steps. The assist unit can also monitor the cooking status in real time and provide advice and warnings as needed. For example, it can display alerts prompting appropriate adjustments if the heat is too high or the cooking time is too long. This allows the assist unit to support the cook in cooking accurately and efficiently, improving the quality of the food.

[0067] The suggestion unit makes recipe improvement suggestions based on the cooking results obtained by the assistance unit. For example, the suggestion unit analyzes the cooking process in detail using image and voice recognition, and the generative AI makes recipe improvement suggestions. Specifically, it analyzes images taken and audio data recorded during cooking to identify problems and areas for improvement at each step of cooking. Based on this data, the generative AI optimizes the cooking procedure and suggests new cooking methods. For example, it can suggest detailed improvements such as how ingredients are cut, adjusting cooking times, and mixing seasonings. The suggestion unit can also suggest new cooking methods and ingredient combinations based on recipes learned by the generative AI. For example, it can suggest changing the taste or texture by substituting certain ingredients with others. Furthermore, the suggestion unit can collect feedback from users and continuously improve the accuracy and effectiveness of its suggestions. As a result, the suggestion unit can always provide highly accurate recipe improvement suggestions based on the latest information, improving the quality and variety of dishes.

[0068] The Creation Department creates new variations based on proposals received from the Proposal Department. For example, the Creation Department uses a Generative AI to suggest new cooking methods and ingredient combinations. Specifically, the Generative AI generates original recipes based on improvements and new ideas provided by the Proposal Department. The Generative AI refers to past recipe and cooking data to provide ideas for creating completely new dishes. For example, it can create various variations such as new recipes that fuse dishes from different cultures or recipes that use health-conscious ingredients. The Creation Department can create new variations based on the new cooking methods and ingredient combinations suggested by the Generative AI. This allows the Creation Department to constantly incorporate new ideas and enrich the variety of dishes. In addition, the Creation Department can collect feedback from users and evaluate and improve new variations. This allows the Creation Department to provide new dishes that meet user needs and preferences, improving the enjoyment and satisfaction of cooking.

[0069] The learning unit can perform detailed recipe input and record and analyze the cooking process. For example, the learning unit can input detailed recipe information such as the type and quantity of ingredients and the procedure. To record and analyze the cooking process, the learning unit can film the cooking process with a camera and have the AI ​​analyze the video. To record and analyze the cooking process, the learning unit can also record the cooking process with sensors and have the AI ​​analyze the data. This improves the accuracy of learning by performing detailed recipe input and recording and analyzing the cooking process. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input video data of the cooking process filmed with a camera into a generating AI and have the generating AI perform the learning of cooking procedures and techniques.

[0070] The assist unit can provide instructions for cooking procedures through an interactive touchscreen interface. For example, the assist unit can use the touchscreen interface to instruct the cook on cooking procedures. The assist unit can use the touchscreen interface to visually display the cooking procedures to the cook. The assist unit can also use the touchscreen interface to provide voice instructions for cooking procedures to the cook. This makes cooking assistance easier by providing instructions for cooking procedures through an interactive touchscreen interface. Some or all of the above-described processes in the assist unit may be performed using AI, for example, or without AI. For example, the assist unit can use the touchscreen interface to have a generating AI execute instructions for cooking procedures.

[0071] The suggestion unit can analyze the cooking process in detail using image and voice recognition, and the generating AI can suggest improvements to the recipe. For example, the suggestion unit can photograph the cooking process with a camera and analyze the cooking procedure using image recognition technology. The suggestion unit can also record the cooking process with voice and analyze the cooking procedure using voice recognition technology. The suggestion unit can combine image recognition technology and voice recognition technology to analyze the cooking process in detail. This makes it easier to improve recipes by analyzing the cooking process in detail using image and voice recognition and having the generating AI suggest improvements to the recipe. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input image data and voice data of the cooking process into the generating AI and have the generating AI execute recipe improvement suggestions.

[0072] The creation unit allows the generative AI to propose new cooking methods and ingredient combinations. For example, the creation unit can propose new cooking methods based on recipes learned by the generative AI. The creation unit can also propose new ingredient combinations based on recipes learned by the generative AI. The creation unit can propose new cooking methods and ingredient combinations based on recipes learned by the generative AI. This makes it easier to create new variations by having the generative AI propose new cooking methods and ingredient combinations. Some or all of the above processing in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can create new variations based on new cooking methods and ingredient combinations proposed by the generative AI.

[0073] The learning unit can estimate the chef's emotions and select training data based on the estimated emotions. For example, if the chef is relaxed, the learning unit may select complex recipes as training data. If the chef is stressed, the learning unit may select simple recipes as training data. If the chef is excited, the learning unit may select challenging recipes as training data. This improves the efficiency of learning by selecting training data based on the chef's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input chef emotion data into a generative AI and have the generative AI perform the selection of training data.

[0074] The learning unit can optimize its learning algorithm by referring to past cooking data. For example, the learning unit can prioritize learning recipes with high success rates from past cooking data. The learning unit can also analyze past cooking data to identify the causes of failures and adjust the learning algorithm accordingly. Based on past cooking data, the learning unit can optimize cooking time and procedures. This improves the accuracy of learning by optimizing the learning algorithm by referring to past cooking data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input past cooking data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0075] The learning unit can perform learning while taking into account fluctuations in the cooking environment. For example, the learning unit can learn the optimal cooking procedure by taking into account temperature fluctuations in the cooking environment. The learning unit can also learn how to store ingredients by taking into account humidity fluctuations in the cooking environment. Based on fluctuations in the cooking environment, the learning unit can optimize cooking time and heat level. As a result, the accuracy of learning is improved by performing learning while taking fluctuations in the cooking environment into account. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input cooking environment data into a generating AI and have the generating AI perform the learning.

[0076] The learning unit can estimate the chef's emotions and adjust the learning frequency based on the estimated emotions. For example, the learning unit can increase the learning frequency if the chef is relaxed. It can also decrease the learning frequency if the chef is stressed. If the chef is excited, it can adjust the learning frequency to a moderate level. This improves the efficiency of learning by adjusting the learning frequency based on the chef's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not using AI. For example, the learning unit can input chef emotion data into a generative AI and have the generative AI adjust the learning frequency.

[0077] The learning unit can learn region-specific recipes by taking into account the geographical location of the chef. For example, if the chef is in Japan, the learning unit can learn region-specific recipes for Japan. If the chef is in Italy, the learning unit can also learn region-specific recipes for Italy. If the chef is in India, the learning unit can learn region-specific recipes for India. This improves the accuracy of learning by taking into account the geographical location of the chef when learning region-specific recipes. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the chef's geographical location information into a generating AI and have the generating AI perform the learning of region-specific recipes.

[0078] The learning unit can analyze a chef's social media activity and learn related recipes. For example, the learning unit can learn recipes that a chef has shared on social media. The learning unit can also learn recipes from chefs that a chef follows. The learning unit can learn recipes that a chef has "liked". By analyzing a chef's social media activity and learning related recipes, the accuracy of the learning is improved. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input a chef's social media activity data into a generating AI and have the generating AI perform the task of learning related recipes.

[0079] The assist unit can estimate the chef's emotions and adjust the cooking procedure instructions based on the estimated emotions. For example, if the chef is relaxed, the assist unit may provide detailed instructions. If the chef is stressed, the assist unit may provide concise instructions. If the chef is excited, the assist unit may provide challenging instructions. This improves cooking efficiency by adjusting the cooking procedure instructions based on the chef's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the assist unit may be performed using AI or not using AI. For example, the assist unit can input the chef's emotion data into the generative AI and have the generative AI adjust the cooking procedure instructions.

[0080] The assist unit can monitor the usage status of cooking appliances in real time and issue instructions at the optimal time. For example, the assist unit can monitor the temperature of cooking appliances in real time and issue instructions for adjusting the heat at the optimal time. The assist unit can also monitor the usage status of cooking appliances and issue instructions for the next step. The assist unit can monitor the condition of cooking appliances and issue instructions for necessary maintenance. This improves cooking efficiency by monitoring the usage status of cooking appliances in real time and issuing instructions at the optimal time. Some or all of the above processes in the assist unit may be performed using AI, for example, or without AI. For example, the assist unit can input cooking appliance usage data into a generating AI and have the generating AI execute instructions at the optimal time.

[0081] The assist unit can issue instructions while taking into account fluctuations in the cooking environment. For example, the assist unit can issue instructions for the optimal cooking procedure while taking into account temperature fluctuations in the cooking environment. The assist unit can also issue instructions on how to store ingredients while taking into account humidity fluctuations in the cooking environment. Based on fluctuations in the cooking environment, the assist unit can issue instructions on cooking time and heat level. As a result, the accuracy of cooking is improved by issuing instructions while taking into account fluctuations in the cooking environment. Some or all of the above processing in the assist unit may be performed using AI, for example, or without using AI. For example, the assist unit can input cooking environment data into a generating AI and have the generating AI execute the instructions.

[0082] The assistance unit can estimate the chef's emotions and determine the priority of cooking procedures based on the estimated emotions. For example, if the chef is relaxed, the assistance unit will prioritize complex procedures. If the chef is stressed, the assistance unit may also prioritize simple procedures. If the chef is excited, the assistance unit may prioritize challenging procedures. This improves cooking efficiency by prioritizing cooking procedures based on the chef's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the assistance unit may be performed using AI or not using AI. For example, the assistance unit can input the chef's emotion data into a generative AI and have the generative AI determine the priority of cooking procedures.

[0083] The assistance unit can instruct region-specific cooking procedures while considering the chef's geographical location. For example, if the chef is in Japan, the assistance unit will instruct region-specific cooking procedures for Japan. If the chef is in Italy, the assistance unit can also instruct region-specific cooking procedures for Italy. If the chef is in India, the assistance unit can instruct region-specific cooking procedures for India. This improves cooking accuracy by instructing region-specific cooking procedures while considering the chef's geographical location. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the chef's geographical location information into a generating AI and have the generating AI execute region-specific cooking procedure instructions.

[0084] The assistance unit can analyze a chef's social media activity and provide relevant cooking instructions. For example, the assistance unit can provide instructions for cooking procedures shared by the chef on social media. The assistance unit can also provide instructions for cooking procedures from chefs the chef follows. The assistance unit can provide instructions for cooking procedures that the chef has "liked". By analyzing the chef's social media activity and providing relevant cooking instructions, the accuracy of the cooking is improved. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the chef's social media activity data into a generating AI and have the generating AI execute instructions for relevant cooking procedures.

[0085] The suggestion unit can estimate the chef's emotions and suggest recipe improvements based on those emotions. For example, if the chef is relaxed, the suggestion unit can suggest improvements to complex recipes. If the chef is stressed, the suggestion unit can suggest improvements to simple recipes. If the chef is excited, the suggestion unit can suggest improvements to challenging recipes. This makes recipe improvement easier by suggesting improvements based on the chef's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not using AI. For example, the suggestion unit can input chef emotion data into a generative AI and have the generative AI execute recipe improvement suggestions.

[0086] The suggestion unit can make optimal improvement suggestions by referring to past cooking data. For example, the suggestion unit can make improvement suggestions with a high success rate based on past cooking data. The suggestion unit can also analyze past cooking data, identify the causes of failures, and make improvement suggestions. Based on past cooking data, the suggestion unit can make improvement suggestions that optimize cooking time and procedures. This makes it easier to improve recipes by making optimal improvement suggestions by referring to past cooking data. Some or all of the above processes in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input past cooking data into a generating AI and have the generating AI execute optimal improvement suggestions.

[0087] The suggestion unit can make improvement suggestions by taking into account fluctuations in the cooking environment. For example, the suggestion unit can make optimal improvement suggestions by taking into account temperature fluctuations in the cooking environment. The suggestion unit can also make improvement suggestions for food storage methods by taking into account humidity fluctuations in the cooking environment. Based on fluctuations in the cooking environment, the suggestion unit can make improvement suggestions that optimize cooking time and heat level. This makes it easier to improve recipes by making improvement suggestions while taking into account fluctuations in the cooking environment. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without using AI. For example, the suggestion unit can input cooking environment data into a generating AI and have the generating AI execute improvement suggestions.

[0088] The suggestion unit can estimate the chef's emotions and prioritize improvement suggestions based on those emotions. For example, if the chef is relaxed, the suggestion unit may prioritize complex improvement suggestions. If the chef is stressed, the suggestion unit may prioritize simple improvement suggestions. If the chef is excited, the suggestion unit may prioritize challenging improvement suggestions. This makes recipe improvement easier by prioritizing improvement suggestions based on the chef's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input chef emotion data into a generative AI and have the generative AI determine the priority of improvement suggestions.

[0089] The suggestion unit can make region-specific improvement suggestions by taking into account the geographical location of the chef. For example, if the chef is in Japan, the suggestion unit can make region-specific improvement suggestions for Japan. If the chef is in Italy, the suggestion unit can also make region-specific improvement suggestions for Italy. If the chef is in India, the suggestion unit can make region-specific improvement suggestions for India. This makes it easier to improve recipes by making region-specific improvement suggestions by taking into account the geographical location of the chef. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the chef's geographical location information into a generating AI and have the generating AI execute region-specific improvement suggestions.

[0090] The suggestion unit can analyze a chef's social media activity and make relevant improvement suggestions. For example, the suggestion unit can make improvement suggestions based on recipes shared by the chef on social media. The suggestion unit can also make improvement suggestions based on recipes from chefs followed by the chef. The suggestion unit can also make improvement suggestions based on recipes that the chef has "liked". This makes it easier to improve recipes by analyzing the chef's social media activity and making relevant improvement suggestions. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit can input the chef's social media activity data into a generating AI and have the generating AI execute relevant improvement suggestions.

[0091] The creation unit can estimate the chef's emotions and create new variations based on the estimated emotions. For example, if the chef is relaxed, the creation unit can create complex new variations. If the chef is stressed, the creation unit can also create simple new variations. If the chef is excited, the creation unit can create challenging new variations. In this way, new culinary ideas can be obtained by creating new variations based on the chef's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the creation unit may be performed using AI, for example, or not using AI. For example, the creation unit can input the chef's emotion data into the generative AI and have the generative AI perform the creation of new variations.

[0092] The creation unit can create optimal new variations by referring to past cooking data. For example, the creation unit can create new variations with a high success rate from past cooking data. The creation unit can also analyze past cooking data, identify the causes of failures, and create new variations. Based on past cooking data, the creation unit can create new variations that optimize cooking time and procedures. In this way, new culinary ideas can be obtained by creating optimal new variations by referring to past cooking data. Some or all of the above processes in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input past cooking data into a generation AI and have the generation AI perform the creation of new variations.

[0093] The creation unit can create new variations by taking into account fluctuations in the cooking environment. For example, the creation unit can create an optimal new variation by taking into account temperature fluctuations in the cooking environment. The creation unit can also incorporate food preservation methods into the new variations by taking into account humidity fluctuations in the cooking environment. Based on fluctuations in the cooking environment, the creation unit can create new variations with optimized cooking time and heat levels. In this way, new cooking ideas can be obtained by creating new variations while taking into account fluctuations in the cooking environment. Some or all of the above processes in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input cooking environment data into a generation AI and have the generation AI perform the creation of new variations.

[0094] The creation unit can estimate the chef's emotions and determine the priority of new variations based on the estimated emotions. For example, if the chef is relaxed, the creation unit may prioritize complex new variations. If the chef is stressed, the creation unit may also prioritize simple new variations. If the chef is excited, the creation unit may prioritize challenging new variations. This allows for the generation of new culinary ideas by determining the priority of new variations based on the chef's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the creation unit may be performed using AI or not. For example, the creation unit can input chef emotion data into a generative AI and have the generative AI determine the priority of new variations.

[0095] The creation unit can create new regional variations by taking into account the geographical location of the chef. For example, if the chef is in Japan, the creation unit can create new regional variations specific to Japan. If the chef is in Italy, the creation unit can also create new regional variations specific to Italy. If the chef is in India, the creation unit can create new regional variations specific to India. In this way, new culinary ideas can be obtained by creating new regional variations by taking into account the geographical location of the chef. Some or all of the above processing in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input the chef's geographical location information into a generation AI and have the generation AI perform the creation of new regional variations.

[0096] The creation unit can analyze a chef's social media activity and create related new variations. For example, the creation unit can create new variations based on recipes shared by the chef on social media. The creation unit can also create new variations based on recipes from chefs that the chef follows. The creation unit can also create new variations based on recipes that the chef "likes". In this way, new culinary ideas can be obtained by analyzing a chef's social media activity and creating related new variations. Some or all of the above processes in the creation unit may be performed using AI, for example, or without AI. For example, the creation unit can input the chef's social media activity data into a generation AI and have the generation AI create related new variations.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The cooking assistance system can also include a health management unit that monitors the user's health condition and suggests recipes based on that condition. For example, the health management unit can monitor the user's blood pressure and blood sugar levels and suggest low-salt and low-sugar recipes based on this data. The health management unit can also consider the user's allergy information and suggest recipes that do not contain allergens. Furthermore, the health management unit can monitor the user's weight and BMI and suggest recipes suitable for dieting and weight management. This makes it possible to suggest recipes that are tailored to the user's health condition, making health management easier.

[0099] The cooking assistance system can also include a history management unit that records the user's meal history and suggests recipes based on that history. For example, the history management unit records dishes the user has made and eaten in the past and suggests new recipes based on this data. The history management unit can also learn the user's preferences and eating habits and suggest recipes that suit the user's tastes. Furthermore, the history management unit can record the user's ratings of dishes they have made in the past and prioritize suggesting highly-rated dishes. This enables recipe suggestions based on the user's meal history, improving meal satisfaction.

[0100] The cooking assistance system can also include an emotion adjustment unit that estimates the user's emotions and adjusts the difficulty of the recipe based on those emotions. For example, if the user is relaxed, the emotion adjustment unit can suggest a more difficult recipe. If the user is stressed, the emotion adjustment unit can suggest an easier recipe. Furthermore, if the user is excited, the emotion adjustment unit can suggest a challenging recipe. This allows for recipe suggestions tailored to the user's emotions, enhancing the enjoyment of cooking.

[0101] The cooking assistance system can also include an inventory management unit that manages the user's food inventory and suggests recipes based on that inventory. For example, the inventory management unit monitors the food inventory in the refrigerator and pantry and suggests recipes based on this data. The inventory management unit can also suggest recipes that prioritize the use of ingredients nearing their expiration date. Furthermore, the inventory management unit can record the history of ingredients purchased by the user and suggest recipes based on this. This reduces food waste and enables efficient food management.

[0102] The cooking assistance system may also include a time adjustment unit that estimates the user's emotions and adjusts the cooking time based on those emotions. For example, if the user is relaxed, the time adjustment unit may suggest a recipe with a longer cooking time. If the user is stressed, the time adjustment unit may suggest a recipe with a shorter cooking time. Furthermore, if the user is excited, the time adjustment unit may suggest a recipe with a medium cooking time. This allows for adjustment of cooking time according to the user's emotions, improving cooking efficiency.

[0103] The cooking assistance system can also include a nutrition management unit that suggests recipes considering the nutritional balance of the user's diet. For example, the nutrition management unit monitors the user's daily nutrient intake and suggests balanced recipes based on this. If a specific nutrient is deficient, the nutrition management unit can also suggest recipes that supplement that nutrient. Furthermore, the nutrition management unit can suggest recipes tailored to the user's health goals (e.g., muscle building or weight loss). This enables recipe suggestions that consider the user's nutritional balance, promoting a healthy diet.

[0104] The cooking assistance system may also include an appliance adjustment unit that estimates the user's emotions and adjusts the use of cooking utensils based on those emotions. For example, if the user is relaxed, the appliance adjustment unit may suggest using complex cooking utensils. If the user is stressed, the appliance adjustment unit may suggest using simple cooking utensils. Furthermore, if the user is excited, the appliance adjustment unit may suggest using challenging cooking utensils. This allows for adjustments to the use of cooking utensils according to the user's emotions, improving cooking efficiency.

[0105] The cooking assistance system can also be equipped with a preference learning unit that learns the user's dietary preferences and suggests recipes based on those preferences. For example, the preference learning unit can learn the user's favorite ingredients and types of dishes and suggest recipes based on that. The preference learning unit can also prioritize suggesting dishes that the user has previously given high ratings to. Furthermore, the preference learning unit can analyze the user's eating patterns and suggest recipes based on that. This makes it possible to suggest recipes that match the user's preferences, improving meal satisfaction.

[0106] The cooking assistance system may also include a progress adjustment unit that estimates the user's emotions and adjusts the cooking progress based on those emotions. For example, if the user is relaxed, the progress adjustment unit can slow down the cooking process. If the user is stressed, the progress adjustment unit can speed up the cooking process. Furthermore, if the user is excited, the progress adjustment unit can adjust the cooking process to a moderate level. This allows for adjustment of the cooking progress according to the user's emotions, improving cooking efficiency.

[0107] The cooking assistance system can also include a cultural consideration unit that suggests recipes taking into account the user's cultural background. For example, the cultural consideration unit can suggest traditional dishes or regionally specific recipes based on the user's place of origin and cultural background. The cultural consideration unit can also suggest appropriate recipes considering the user's religious dietary restrictions. Furthermore, the cultural consideration unit can suggest recipes that the whole family can enjoy, taking into account the eating habits of the user's family. This enables recipe suggestions that are tailored to the user's cultural background, thereby improving meal satisfaction.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The learning unit learns the secret recipe. The learning unit inputs detailed recipes and records and analyzes the cooking process. For example, by filming a chef cooking with a camera and having the AI ​​analyze the footage, the AI ​​can learn cooking procedures and techniques. Step 2: The assist unit assists with cooking based on the recipe learned by the learning unit. The assist unit guides the cook through the cooking procedure via an interactive touchscreen interface. It can also guide the cook through the cooking procedure using voice and visual guides. Step 3: The suggestion unit makes recipe improvement suggestions based on the cooking results obtained by the assistance unit. The suggestion unit analyzes the cooking process in detail using image and voice recognition, and the generating AI makes recipe improvement suggestions. Based on the recipes that the generating AI has learned, it can also suggest new cooking methods and ingredient combinations. Step 4: The creation unit creates new variations based on the proposals received from the suggestion unit. The creation unit can create new variations based on the new cooking methods and ingredient combinations suggested by the generation AI.

[0110] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0111] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0112] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0113] Each of the multiple elements described above, including the learning unit, assist unit, suggestion unit, and creation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the learning unit is implemented by using the camera 42 of the smart device 14 to film the chef's cooking process and analyzing the video with the specific processing unit 290 of the data processing unit 12. The assist unit is implemented by providing cooking instructions through the interactive touchscreen interface of the smart device 14. The suggestion unit is implemented by analyzing the cooking results with the specific processing unit 290 of the data processing unit 12 and having the generating AI suggest improvements to the recipe. The creation unit is implemented by suggesting new cooking methods and ingredient combinations with the specific processing unit 290 of the data processing unit 12 and creating new variations. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0120] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0121] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0122] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0123] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0124] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0126] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0128] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements described above, including the learning unit, assist unit, suggestion unit, and creation unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the learning unit is implemented by using the camera 42 of the smart glasses 214 to film the chef's cooking process and analyzing the video with the specific processing unit 290 of the data processing unit 12. The assist unit is implemented, for example, by providing cooking instructions through the interactive touchscreen interface of the smart glasses 214. The suggestion unit is implemented, for example, by analyzing the cooking results with the specific processing unit 290 of the data processing unit 12 and having the generating AI suggest improvements to the recipe. The creation unit is implemented, for example, by having the specific processing unit 290 of the data processing unit 12 suggest new cooking methods and ingredient combinations, and creating new variations. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0133] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0134] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0138] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0140] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the learning unit, assist unit, suggestion unit, and creation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by using the camera 42 of the headset terminal 314 to film the chef's cooking process and analyzing the video using the specific processing unit 290 of the data processing unit 12. The assist unit is implemented by providing instructions for cooking procedures through the interactive touchscreen interface of the headset terminal 314. The suggestion unit is implemented by analyzing the cooking results using the specific processing unit 290 of the data processing unit 12 and having the generating AI suggest improvements to the recipe. The creation unit is implemented by suggesting new cooking methods and ingredient combinations using the specific processing unit 290 of the data processing unit 12 and creating new variations. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] As shown in Figure 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.

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0153] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0154] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0155] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0157] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the learning unit, assist unit, suggestion unit, and creation unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the learning unit is implemented by using the camera 42 of the robot 414 to film the cooking process of a chef and analyzing the video with the specific processing unit 290 of the data processing unit 12. The assist unit is implemented, for example, by giving instructions for cooking procedures through the robot 414's interactive touchscreen interface. The suggestion unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 analyzing the cooking results and the generating AI suggesting improvements to the recipe. The creation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 suggesting new cooking methods and ingredient combinations and creating new variations. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0163] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0165] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0166] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0167] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0171] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0172] 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.

[0173] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0174] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0175] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0176] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0178] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0179] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0180] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0181] (Note 1) A learning section where you can learn secret recipes, An assist unit that assists cooking based on the recipe learned by the learning unit, A suggestion unit that proposes recipe improvements based on the cooking results obtained by the assist unit, The system includes a creation unit that creates new variations based on the proposals obtained by the aforementioned proposal unit. A system characterized by the following features. (Note 2) The aforementioned learning unit, Detailed recipe input and recording and analysis of the cooking process. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned assist unit is Instructions for cooking are provided through an interactive touchscreen interface. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned proposal section is, Using image and voice recognition, the cooking process is analyzed in detail, and the generative AI suggests improvements to the recipe. The system described in Appendix 1, characterized by the features described herein. (Note 5) The creation unit is, The AI ​​generates new cooking methods and ingredient combinations. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned learning unit, The system estimates the emotions of the chefs and selects training data based on the estimated emotions of the chefs. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, Optimize the learning algorithm by referring to past cooking data. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, Learn while taking into account variations in the cooking environment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, The system estimates the chef's emotions and adjusts the learning frequency based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, Learn regionally specific recipes by taking into account the geographical location of the chef. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, Analyze chefs' social media activity and learn related recipes. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned assist unit is The system estimates the chef's emotions and adjusts the cooking procedure instructions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned assist unit is The system monitors the usage of cooking equipment in real time and issues instructions at the optimal time. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned assist unit is Give instructions while taking into account fluctuations in the cooking environment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned assist unit is The system estimates the chef's emotions and determines the priority of cooking steps based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned assist unit is The system takes into account the geographical location of the chef and provides instructions for region-specific cooking procedures. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned assist unit is Analyze chefs' social media activity and provide relevant cooking instructions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned proposal section is, It estimates the chef's emotions and suggests recipe improvements based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned proposal section is, We will make optimal improvement suggestions by referring to past cooking data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned proposal section is, We will propose improvements while taking into account fluctuations in the cooking environment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned proposal section is, The system estimates the chef's emotions and prioritizes improvement suggestions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned proposal section is, Proposing improvements specific to the region, taking into account the geographical location of the chefs. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned proposal section is, Analyze chefs' social media activity and make relevant improvement suggestions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The creation unit is, The system estimates the chef's emotions and creates new variations based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The creation unit is, By referring to past cooking data, we create optimal new variations. The system described in Appendix 1, characterized by the features described herein. (Note 26) The creation unit is, Create new variations to take into account changes in the cooking environment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The creation unit is, The system estimates the chef's emotions and determines the priority of new variations based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The creation unit is, By taking into account the geographical location of the chef, we create new variations that are unique to each region. The system described in Appendix 1, characterized by the features described herein. (Note 29) The creation unit is, Analyze chefs' social media activity and create related new variations. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A learning section where you can learn secret recipes, An assist unit that assists cooking based on the recipe learned by the learning unit, A suggestion unit that proposes recipe improvements based on the cooking results obtained by the assist unit, The system includes a creation unit that creates new variations based on the proposals obtained by the aforementioned proposal unit. A system characterized by the following features.

2. The aforementioned learning unit, Detailed recipe input and recording and analysis of the cooking process. The system according to feature 1.

3. The aforementioned assist unit is Instructions for cooking are provided through an interactive touchscreen interface. The system according to feature 1.

4. The aforementioned proposal section is, Using image and voice recognition, the cooking process is analyzed in detail, and the generative AI suggests improvements to the recipe. The system according to feature 1.

5. The creation unit is, The AI ​​generates new cooking methods and ingredient combinations. The system according to feature 1.

6. The aforementioned learning unit, The system estimates the emotions of the chefs and selects training data based on the estimated emotions of the chefs. The system according to feature 1.

7. The aforementioned learning unit, Optimize the learning algorithm by referring to past cooking data. The system according to feature 1.

8. The aforementioned learning unit, Learn while taking into account variations in the cooking environment. The system according to feature 1.

Images