system

Abstract

The system according to the embodiment aims to allow people to learn Japanese cuisine techniques and receive evaluations. [Solution] A system according to an embodiment includes a technique selection unit, an instruction unit, an image receiving unit, an evaluation unit, and an advice unit. The technique selection unit receives a selection of a technique or recipe. The instruction unit provides step-by-step instruction based on the technique or recipe selected by the technique selection unit. The image receiving unit receives images of the dish being taught by the instruction unit. The evaluation unit analyzes and evaluates the images received by the image receiving unit. The advice unit provides advice based on the evaluation results obtained by the evaluation unit.

Description

[Technical Field]

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

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

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

[0004] With conventional techniques, it was difficult to learn the advanced techniques of Japanese cuisine and receive recognition.

[0005] The system according to the embodiment aims to allow people to learn Japanese cuisine techniques and receive evaluations. [Means for solving the problem]

[0006] The system according to the embodiment includes a technique selection unit, an instruction unit, an image receiving unit, an evaluation unit, and an advice unit. The technique selection unit receives a selection of a technique or recipe. The instruction unit provides step-by-step instruction based on the technique or recipe selected by the technique selection unit. The image receiving unit receives images of the dish being taught by the instruction unit. The evaluation unit analyzes and evaluates the images received by the image receiving unit. The advice unit provides advice based on the evaluation results obtained by the evaluation unit. [Effects of the Invention]

[0007] The system according to the embodiment allows users to learn Japanese cuisine techniques and receive evaluations. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The learning system according to an embodiment of the present invention is a learning service that uses AI to preserve Japanese food culture. This learning system supports a wide range of skills, from basic to applied, and even advanced techniques. When users upload images of their completed dishes, the AI ​​scores the images and provides specific advice. This learning system goes beyond simply providing recipes; it is a comprehensive platform for learning Japanese cuisine techniques, supporting everything from cooking classes to traditional Japanese restaurants. It is also designed to solve challenges facing the Japanese cuisine industry in the food processing, restaurant, and overseas expansion sectors. For example, users select the skills and recipes they want to learn. They can start with basic skills, such as how to use a knife, how to fillet fish, and how to make sushi. Next, the AI ​​provides step-by-step instruction based on the selected skills and recipes. Video and text instructions are provided, and users follow the instructions to actually cook the dish. Once the dish is complete, the user uploads an image of the dish to the AI. The AI ​​analyzes the image and evaluates the appearance, presentation, and accuracy of the technique. For example, specific criteria, such as whether the sushi is made correctly or the sashimi is beautifully cut, are evaluated. Based on the evaluation results, the AI ​​provides advice on areas for improvement and the next skills to learn. This learning system not only provides practical learning in cooking classes and restaurants, but also helps improve skills in the processing and food service industries. For example, food processors wanting to learn new techniques or restaurants wanting to improve the quality of their menus can use this learning system to efficiently acquire new skills. It can also be a useful tool for Japanese food industries aiming to expand overseas, allowing local staff to learn Japanese techniques. In this way, the learning system is a new-generation learning platform that utilizes AI to preserve Japanese food culture and learn new skills. Users can learn a wide range of techniques, from basic to advanced, and the AI ​​evaluates images of finished dishes and provides specific advice to help improve their skills. In this way, the learning system allows users to efficiently learn the techniques of Japanese food culture and improve their skills.

[0029] A learning system according to an embodiment includes a skill selection unit, an instruction unit, an image receiving unit, an evaluation unit, and an advice unit. The skill selection unit selects a skill or recipe that a user wants to learn. For example, the user can select skills such as how to use a knife, how to fillet fish, or how to make sushi. The instruction unit provides step-by-step instruction based on the selected skill or recipe. For example, the instruction unit provides video or text instructions that the user can follow to actually prepare the dish. The image receiving unit receives images of the completed dish. For example, the user can upload images taken with a smartphone or digital camera. The evaluation unit analyzes and evaluates the received images. For example, the image is analyzed and evaluated based on evaluation criteria such as appearance, presentation, and technical accuracy. Some or all of the above-described processing by the evaluation unit may be performed using, for example, AI, or may be performed without AI. For example, the evaluation unit may analyze and evaluate the image using an AI model that receives the image as input and outputs an evaluation result. The advice unit provides advice based on the evaluation result. For example, the advice unit provides advice on areas for improvement or the next skill to learn. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit may provide advice using an AI model that inputs evaluation results and outputs advice. This allows the learning system according to the embodiment to perform a consistent process from selecting techniques and recipes to providing instruction, evaluation, and advice.

[0030] The evaluation unit can analyze and evaluate images based on evaluation criteria such as appearance, presentation, and technical accuracy. For example, the evaluation unit considers color, arrangement, and overall balance as criteria for evaluating appearance. For example, the evaluation unit evaluates whether the color of the food is vivid and whether the presentation is beautiful. Furthermore, the evaluation unit considers the precision of knife use and cutting as criteria for evaluating technical accuracy. For example, the evaluation unit evaluates whether the sashimi is cut evenly and whether the sushi is made accurately. Furthermore, the evaluation unit considers the beauty of the food arrangement and decoration as criteria for evaluating presentation. For example, the evaluation unit evaluates whether the food is beautifully arranged and the decoration is appropriate. This allows the evaluation unit to make an accurate evaluation based on the evaluation criteria. Some or all of the above-described processing in the evaluation unit may be performed using, or without, AI. For example, the evaluation unit can analyze and evaluate images using an AI model that receives an image as input and outputs an evaluation result.

[0031] The skill selection unit can select skills such as how to use a knife, how to fillet fish, or how to make sushi. For example, as how to use a knife, the skill selection unit can select the basics of how to hold and cut a knife. For example, the skill selection unit provides lessons for learning the basics of how to hold and cut a knife. Furthermore, as how to fillet fish, the skill selection unit can select a filleting method depending on the type of fish. For example, the skill selection unit provides lessons for learning how to fillet fish such as sea bream or salmon. Furthermore, as how to make sushi, the skill selection unit can select how to make rice or how to place toppings on the sushi. For example, the skill selection unit provides lessons for learning how to make sushi rice or how to place toppings on the sushi. This allows the skill selection unit to select a specific skill that the user wants to learn.

[0032] The instruction unit can provide explanations in the form of video or text. For example, as video explanations, the instruction unit provides videos that visually show the steps of cooking. For example, the instruction unit uses videos to explain techniques such as how to use a knife, how to fillet fish, and how to make sushi. Furthermore, the instruction unit can provide text that describes the steps of cooking in detail as text explanations. For example, the instruction unit provides text that describes in detail the steps of cooking and important points to note. Furthermore, the instruction unit can provide explanations that combine video and text. For example, the instruction unit provides supplementary explanations in text in addition to video explanations. This allows the instruction unit to provide instruction that is visually easy for the user to understand.

[0033] The advice unit can provide advice on areas for improvement or the next skill to learn based on the evaluation results. For example, the advice unit can provide advice on areas for improvement in the appearance or presentation of a dish based on the evaluation results. For example, the advice unit can specifically suggest areas for improvement in the color, arrangement, or decoration of a dish. The advice unit can also provide advice on areas for improvement in the accuracy of techniques. For example, the advice unit can specifically suggest areas for improvement in knife usage, cutting accuracy, or sushi making. The advice unit can also provide advice on the next skill to learn. For example, the advice unit can specifically suggest the next skill or recipe the user should learn. This allows the advice unit to know the specific areas for improvement or the next skill to learn. Some or all of the above-described processing in the advice unit may be performed using, or without, AI. For example, the advice unit can provide advice using an AI model that inputs the evaluation results and outputs advice.

[0034] The evaluation unit can analyze and evaluate images using AI. The evaluation unit analyzes images using, for example, an image recognition algorithm using deep learning. For example, the evaluation unit uses a deep learning model to evaluate the appearance, presentation, and technical accuracy of the food. The evaluation unit can also use an image recognition algorithm to extract and evaluate the characteristics of the food. For example, the evaluation unit uses an image recognition algorithm to evaluate the color, arrangement, and technical accuracy of the food. The evaluation unit can also analyze and evaluate images based on evaluation criteria using AI. For example, the evaluation unit uses an AI model to evaluate the appearance, presentation, and technical accuracy. In this way, the evaluation unit improves the accuracy of image analysis and evaluation by using AI. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can analyze and evaluate images using an AI model that receives images as input and outputs evaluation results.

[0035] The skill selection unit can analyze the user's past learning history and recommend optimal skills and recipes. For example, the skill selection unit recommends the next skill the user should learn based on skills the user has learned in the past. For example, the skill selection unit recommends the next skill the user should learn based on the knife usage or fish filleting techniques the user has learned in the past. The skill selection unit can also recommend related new recipes based on recipes the user has successfully made in the past. For example, the skill selection unit recommends related new sushi recipes based on the sushi techniques the user has successfully made in the past. Furthermore, the skill selection unit can analyze the user's level of skill acquisition from the user's past learning history and recommend skills and recipes with an appropriate level of difficulty. For example, the skill selection unit analyzes the user's past learning history and recommends skills and recipes with an appropriate level of difficulty according to the user's level of skill acquisition. This allows the skill selection unit to recommend optimal skills and recipes based on the user's past learning history. Some or all of the above-described processing in the skill selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the technology selection unit can input the user's past learning history data into the generation AI and have the generation AI recommend optimal technologies and recipes.

[0036] The technique selection unit can automatically select techniques and recipes according to the season or event. The technique selection unit automatically selects recipes using seasonal ingredients, for example. For example, the technique selection unit selects recipes using seasonal ingredients, such as dishes using cherry blossoms in spring, chilled Chinese noodles in summer, matsutake rice in autumn, and oden in winter. The technique selection unit can also automatically select techniques and recipes suited to specific events (e.g., New Year's Day and Christmas). For example, the technique selection unit selects techniques and recipes suited to events, such as osechi ryori (New Year's dishes) for New Year's and roast chicken for Christmas. The technique selection unit can also automatically select traditional Japanese cuisine techniques and recipes for each season. For example, the technique selection unit selects traditional Japanese cuisine techniques and recipes for each season, such as cherry blossom viewing bento in spring, chilled somen noodles in summer, chestnut rice in autumn, and hot pot dishes in winter. This allows the technique selection unit to automatically select optimal techniques and recipes according to the season or event. Some or all of the above-described processing by the technique selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the technology selection unit can input seasonal and event data into the generation AI and have the generation AI select the optimal technology and recipe.

[0037] The technique selection unit can prioritize regional techniques and recipes taking into account the user's geographical location information. For example, if the user is in Hokkaido, the technique selection unit prioritizes selecting techniques and recipes using Hokkaido's specialty products. For example, the technique selection unit prioritizes selecting techniques and recipes using salmon and potatoes, which are Hokkaido specialty products. Furthermore, if the user is in Kyoto, the technique selection unit can prioritize selecting traditional Kyoto techniques and recipes. For example, the technique selection unit prioritizes selecting Kyoto cuisine and yudofu recipes, which are traditional Kyoto techniques. Furthermore, if the user is overseas, the technique selection unit can prioritize selecting techniques and recipes using ingredients available in that region. For example, if the user is overseas, the technique selection unit prioritizes selecting Japanese cuisine techniques and recipes using ingredients available in that region. This allows the technique selection unit to prioritize regional techniques and recipes based on the user's geographical location information. Some or all of the above-described processing by the technique selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the technology selection unit can input the user's geographic location data into the generation AI and cause the generation AI to select region-specific technologies and recipes.

[0038] The technique selection unit can analyze a user's social media activity and select related techniques and recipes. For example, the technique selection unit can select related techniques and recipes based on images of food shared by the user on social media. For example, the technique selection unit can select related sushi techniques and recipes based on images of sushi shared by the user. The technique selection unit can also analyze the content of posts from cooking accounts followed by the user and select related techniques and recipes. For example, the technique selection unit can analyze the content of posts from Japanese food cooking accounts followed by the user and select related techniques and recipes. The technique selection unit can also select techniques and recipes that the user is likely to be interested in based on posts that the user has "liked." For example, the technique selection unit can select techniques and recipes that the user is likely to be interested in based on Japanese food posts that the user has "liked." This allows the technique selection unit to select related techniques and recipes based on the user's social media activity. Some or all of the above-described processing by the technique selection unit may be performed using, or without, AI. For example, the technique selection unit can input the user's social media activity data into a generation AI and cause the generation AI to select related techniques and recipes.

[0039] During instruction, the instructor can customize the instruction content according to the user's learning speed. For example, if the user is learning at a fast pace, the instructor can accelerate the timing of moving on to the next step. For example, if the user is learning how to use a knife at a fast pace, the instructor can accelerate the timing of moving on to the next step, how to fillet a fish. Furthermore, if the user is learning at a slow pace, the instructor can provide detailed explanations and supplemental information. For example, if the user is learning how to use a knife at a slow pace, the instructor can provide detailed explanations and supplemental information. Furthermore, the instructor can adjust the difficulty of the instruction content according to the user's learning speed. For example, the instructor can adjust the difficulty of how to use a knife or how to fillet a fish according to the user's learning speed. This allows the instructor to provide optimal instruction content according to the user's learning speed. Some or all of the above-described processing in the instructor may be performed using, or without, AI. For example, the instructor can input the user's learning speed data into a generation AI and cause the generation AI to customize the instruction content based on the learning speed.

[0040] When providing instruction, the instruction unit can select the optimal instruction method by referring to the user's past learning history. For example, the instruction unit teaches a related new technique based on a technique the user previously learned. For example, if the user previously learned how to use a knife, the instruction unit teaches the user how to fillet fish, which is a related new technique. The instruction unit can also provide instruction to complement weak techniques based on the user's past learning history. For example, the instruction unit provides instruction to complement knife use, which the user previously struggled with. Furthermore, the instruction unit can analyze the user's past learning history and select the optimal instruction method. For example, the instruction unit analyzes the user's past learning history and selects the optimal instruction method. This allows the instruction unit to select the optimal instruction method based on the user's past learning history. Some or all of the above-mentioned processing in the instruction unit may be performed using, for example, AI, or may be performed without AI. For example, the instruction unit can input the user's past learning history data into a generation AI and have the generation AI select the optimal instruction method.

[0041] The instructor can provide the optimal instruction method by taking into account the user's device information during instruction. For example, if the user is using a smartphone, the instructor can provide an instruction method tailored to the screen size. For example, the instructor can provide an instruction method for using a knife or filleting fish optimized for the small screen of a smartphone. Furthermore, if the user is using a tablet, the instructor can provide an instruction method optimized for a large screen. For example, the instructor can provide an instruction method for using a knife or filleting fish optimized for the large screen of a tablet. Furthermore, if the user is using a smartwatch, the instructor can provide a concise and highly visible instruction method. For example, the instructor can provide an instruction method for using a knife or filleting fish optimized for the small screen of a smartwatch. This allows the instructor to provide the optimal instruction method based on the user's device information. Some or all of the above-described processing by the instructor can be performed using AI, for example, or without AI. For example, the instructor can input the user's device information data into a generation AI and cause the generation AI to provide an instruction method based on the device information.

[0042] During instruction, the instruction unit can analyze the user's social media activity and provide relevant instruction content. For example, the instruction unit can provide instruction on related techniques and recipes based on images of dishes shared by the user on social media. For example, the instruction unit can provide instruction on related sushi techniques and recipes based on images of sushi shared by the user. The instruction unit can also analyze the content posted by cooking accounts followed by the user and provide instruction on related techniques and recipes. For example, the instruction unit can analyze the content posted by Japanese food cooking accounts followed by the user and provide instruction on related techniques and recipes. The instruction unit can also provide instruction on techniques and recipes that the user is likely to be interested in based on posts that the user has "liked." For example, the instruction unit can provide instruction on techniques and recipes that the user is likely to be interested in based on Japanese food posts that the user has "liked." This allows the instruction unit to provide relevant instruction content based on the user's social media activity. Some or all of the above-described processing by the instruction unit may be performed using, or without, AI. For example, the instruction unit can input the user's social media activity data into a generation AI and cause the generation AI to provide relevant instruction content.

[0043] When accepting images, the image accepting unit can analyze the user's past image submission history and select the optimal acceptance method. The image accepting unit selects the optimal acceptance method, for example, based on the quality of images previously submitted by the user. For example, the image accepting unit analyzes the quality of images previously submitted by the user and selects the optimal acceptance method. The image accepting unit can also optimize the submission timing based on the user's past image submission history. For example, the image accepting unit analyzes the user's past image submission history and selects the optimal submission timing. Furthermore, the image accepting unit can analyze the user's past image submission history and provide optimal feedback. For example, the image accepting unit analyzes the user's past image submission history and provides optimal feedback. This allows the image accepting unit to select the optimal acceptance method based on the user's past image submission history. Some or all of the above-described processing in the image accepting unit may be performed using, for example, AI, or may be performed without using AI. For example, the image accepting unit can input the user's past image submission history data into a generation AI and cause the generation AI to select the optimal acceptance method.

[0044] The image receiving unit may perform filtering based on the user's current project or field of interest when receiving images. For example, the image receiving unit may preferentially receive images related to a project the user is currently working on. For example, the image receiving unit may preferentially receive images of dishes related to the project the user is currently working on. The image receiving unit may also filter and receive related images based on the user's field of interest. For example, the image receiving unit may filter and receive images of related dishes based on the user's field of interest. Furthermore, the image receiving unit may select an optimal image receiving method taking into account the user's current project or field of interest. For example, the image receiving unit may select an optimal image receiving method taking into account the user's current project or field of interest. This allows the image receiving unit to filter and receive related images based on the user's current project or field of interest. Some or all of the above-described processing in the image receiving unit may be performed using, or without, AI. For example, the image receiving unit may input the user's current project or field of interest data to a generation AI and cause the generation AI to perform filtering.

[0045] When receiving images, the image receiving unit can prioritize receiving highly relevant images taking into account the user's geographical location information. For example, if the user is in Hokkaido, the image receiving unit prioritizes receiving images of dishes using Hokkaido's specialty products. For example, if the user is in Hokkaido, the image receiving unit prioritizes receiving images of dishes using Hokkaido's specialty products such as salmon and potatoes. Furthermore, if the user is in Kyoto, the image receiving unit can prioritize receiving images of traditional Kyoto dishes. For example, if the user is in Kyoto, the image receiving unit prioritizes receiving images of Kyoto cuisine and yudofu, which are traditional Kyoto dishes. Furthermore, if the user is overseas, the image receiving unit can prioritize receiving images of dishes using ingredients available in that region. For example, if the user is overseas, the image receiving unit prioritizes receiving images of Japanese cuisine using ingredients available in that region. This allows the image receiving unit to prioritize receiving highly relevant images based on the user's geographical location information. Some or all of the above-described processing in the image receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the image reception unit can input the user's geographical location information data into the generation AI and cause the generation AI to receive highly relevant images.

[0046] The image receiving unit can analyze the user's social media activity when receiving images and receive related images. For example, the image receiving unit prioritizes receiving images of food shared by the user on social media. For example, the image receiving unit prioritizes receiving images of sushi shared by the user on social media. The image receiving unit can also analyze the content posted by cooking accounts followed by the user and receive related images. For example, the image receiving unit analyzes the content posted by Japanese food cooking accounts followed by the user and receive related images. The image receiving unit can also receive related images based on posts that the user has "liked." For example, the image receiving unit receives related images based on Japanese food posts that the user has "liked." This allows the image receiving unit to receive related images based on the user's social media activity. Some or all of the above-described processing in the image receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the image receiving unit can input the user's social media activity data into a generation AI and cause the generation AI to receive related images.

[0047] The evaluation unit can improve the accuracy of the evaluation by taking into account the interrelationships between dishes during evaluation. The evaluation unit, for example, evaluates the overall balance by taking into account the combination of dishes. For example, the evaluation unit evaluates the overall balance by taking into account the combination of dishes. The evaluation unit can also evaluate the accuracy of the technique based on the interrelationships between dishes. For example, the evaluation unit evaluates the accuracy of the technique of knife use or fish filleting based on the interrelationships between dishes. The evaluation unit can also evaluate the appearance and presentation by taking into account the interrelationships between dishes. For example, the evaluation unit evaluates the appearance and presentation by taking into account the interrelationships between dishes. In this way, the evaluation unit improves the accuracy of the evaluation by taking into account the interrelationships between dishes. Some or all of the above-mentioned processing in the evaluation unit may be performed using, or without using, AI, for example. For example, the evaluation unit can input interrelationship data between dishes into the generation AI and cause the generation AI to improve the accuracy of the evaluation based on the interrelationships.

[0048] The evaluation unit can perform the evaluation by taking into account the attribute information of the person who submitted the dish. The evaluation unit adjusts the evaluation criteria, for example, by taking into account the experience level of the person who submitted the dish. For example, the evaluation unit adjusts the evaluation criteria for knife usage and fish filleting techniques, taking into account the experience level of the person who submitted the dish. The evaluation unit can also adjust the evaluation criteria based on the person's past evaluation history. For example, the evaluation unit adjusts the evaluation criteria for knife usage and fish filleting techniques, taking into account the person's past evaluation history. The evaluation unit can also adjust the evaluation criteria by taking into account the person's attribute information (e.g., age, occupation). For example, the evaluation unit adjusts the evaluation criteria for knife usage and fish filleting techniques, taking into account the person's age and occupation. This allows the evaluation unit to perform an optimal evaluation based on the person's attribute information. Some or all of the above-described processing in the evaluation unit may be performed using, or without, AI. For example, the evaluation unit can input the person's attribute information data to the generation AI and cause the generation AI to adjust the evaluation criteria based on the attribute information.

[0049] The evaluation unit can perform the evaluation taking into account the geographical distribution of the dishes. For example, the evaluation unit applies region-specific evaluation criteria based on the geographical distribution of the dishes. For example, the evaluation unit applies Hokkaido-specific evaluation criteria to Hokkaido dishes and Kyoto-specific evaluation criteria to Kyoto dishes based on the geographical distribution of the dishes. The evaluation unit can also reflect the difficulty of obtaining ingredients in the evaluation taking into account the geographical distribution. For example, the evaluation unit reflects the difficulty of obtaining ingredients in the evaluation taking into account the geographical distribution. Furthermore, the evaluation unit can also perform an evaluation taking into account the food culture of the region based on the geographical distribution. For example, the evaluation unit performs an evaluation taking into account the food culture of the region based on the geographical distribution. This allows the evaluation unit to perform an optimal evaluation based on the geographical distribution of the dishes. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input geographical distribution data of the dishes to the generation AI and cause the generation AI to perform an evaluation based on the geographical distribution.

[0050] The evaluation unit can improve the accuracy of the evaluation by referring to literature related to cooking during the evaluation. The evaluation unit, for example, evaluates the accuracy of the technique based on literature related to cooking. For example, the evaluation unit evaluates the accuracy of the technique of knife use and fish filleting based on literature related to cooking. The evaluation unit can also evaluate the appearance and presentation by referring to related literature. For example, the evaluation unit evaluates the appearance and presentation of knife use and fish filleting based on related literature. The evaluation unit can also adjust the evaluation criteria based on literature related to cooking. For example, the evaluation unit adjusts the evaluation criteria of knife use and fish filleting based on literature related to cooking. In this way, the evaluation unit improves the accuracy of the evaluation by referring to literature related to cooking. Some or all of the above-mentioned processing in the evaluation unit may be performed using, or without, AI, for example. For example, the evaluation unit can input literature data related to cooking into the generation AI and cause the generation AI to improve the accuracy of the evaluation based on the related literature.

[0051] When giving advice, the advice unit can provide optimal advice by referring to the user's past learning history. For example, the advice unit can provide advice on a related new technique based on a technique the user learned in the past. For example, if the user previously learned how to use a knife, the advice unit can provide advice on a related new technique, such as how to fillet fish. The advice unit can also provide advice to compensate for weak techniques based on the user's past learning history. For example, the advice unit can provide advice to compensate for a knife technique that the user previously struggled with. Furthermore, the advice unit can analyze the user's past learning history and provide optimal advice. For example, the advice unit can analyze the user's past learning history and provide optimal advice. This allows the advice unit to provide optimal advice based on the user's past learning history. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the user's past learning history data into the generation AI and cause the generation AI to provide optimal advice.

[0052] When providing advice, the advice unit can customize the content of the advice based on the user's current learning status. The advice unit, for example, provides advice related to a skill the user is currently learning. For example, the advice unit provides advice related to how to use a knife that the user is currently learning. The advice unit can also provide advice on the next skill to be learned based on the user's current learning status. For example, the advice unit provides advice on how to fillet fish that the user should learn next based on the user's current learning status. The advice unit can also customize the content of the advice taking into account the user's current learning status. For example, the advice unit customizes the content of advice on how to use a knife or how to fillet fish taking into account the user's current learning status. This allows the advice unit to provide optimal advice based on the user's current learning status. Some or all of the above-described processing in the advice unit may be performed using, or without, AI. For example, the advice unit can input data on the user's current learning status into the generation AI and cause the generation AI to customize the advice based on the learning status.

[0053] When providing advice, the advice unit can provide optimal advice taking into account the user's geographical location information. For example, if the user is in Hokkaido, the advice unit can provide advice on dishes using Hokkaido's specialties. For example, if the user is in Hokkaido, the advice unit can provide advice on dishes using Hokkaido's specialties such as salmon and potatoes. Furthermore, if the user is in Kyoto, the advice unit can provide advice on traditional Kyoto dishes. For example, if the user is in Kyoto, the advice unit can provide advice on Kyoto cuisine and yudofu, which are traditional Kyoto dishes. Furthermore, if the user is overseas, the advice unit can provide advice on dishes using ingredients available in that area. For example, if the user is overseas, the advice unit can provide advice on Japanese cuisine using ingredients available in that area. This allows the advice unit to provide optimal advice based on the user's geographical location information. Some or all of the above-described processing by the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the user's geographical location information data into the generation AI and cause the generation AI to provide advice based on the geographical location information.

[0054] When providing advice, the advice unit can analyze the user's social media activity and provide relevant advice. For example, the advice unit can provide relevant advice based on images of food shared by the user on social media. For example, the advice unit can provide advice on related sushi techniques and recipes based on images of sushi shared by the user on social media. The advice unit can also analyze the content of posts from cooking accounts followed by the user and provide relevant advice. For example, the advice unit can analyze the content of posts from Japanese food cooking accounts followed by the user and provide advice on related techniques and recipes. The advice unit can also provide advice that is likely to be of interest to the user based on posts that the user has "liked." For example, the advice unit can provide advice on techniques and recipes that the user is likely to be interested in based on Japanese food posts that the user has "liked." This allows the advice unit to provide relevant advice based on the user's social media activity. Some or all of the above-described processing by the advice unit may be performed using, or without, AI. For example, the advice unit can input the user's social media activity data into a generation AI and cause the generation AI to provide relevant advice.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The learning system may further include a health management unit that monitors the user's health condition and presents options for techniques and recipes based on the health condition. For example, the health management unit may monitor the user's blood pressure and heart rate and select techniques and recipes according to the user's health condition. For example, if the user's blood pressure is high, it may select recipes with low salt content. The health management unit may also analyze the user's dietary history and select techniques and recipes that take nutritional balance into consideration. For example, if the user has not eaten vegetables recently, it may select recipes with a high concentration of vegetables. Furthermore, the health management unit may monitor the user's exercise volume and select techniques and recipes according to the amount of exercise. For example, if the user is not exercising enough, it may select recipes with low calories. This allows the learning system to provide the optimal techniques and recipes according to the user's health condition.

[0057] The evaluation unit can adjust the evaluation criteria by taking into account the cultural background of the user. For example, if the user is from a different cultural sphere, the evaluation unit makes the evaluation by taking into account the aesthetic standards of cuisine in that culture. For example, if the user is from France, the evaluation unit makes the evaluation by taking into account the aesthetic standards of French cuisine. The evaluation unit can also adjust the evaluation criteria by taking into account the religious background of the user. For example, if the user is Muslim, the evaluation unit makes the evaluation by taking into account Halal standards. Furthermore, the evaluation unit can adjust the evaluation criteria by taking into account the eating habits of the user. For example, if the user is vegetarian, the evaluation unit makes the evaluation by taking into account the standards of vegetarian cuisine. This allows the evaluation unit to make an optimal evaluation according to the cultural background of the user.

[0058] The skill selection unit can present options for skills and recipes according to the user's learning style. For example, if the user is a visual learner, the skill selection unit selects skills and recipes that make extensive use of videos. For example, the skill selection unit uses videos to explain to a visual learner how to use a knife or how to fillet fish. Furthermore, if the user is an auditory learner, the skill selection unit can select skills and recipes that make extensive use of audio guidance. For example, the skill selection unit uses audio guidance to explain to an auditory learner how to make sushi. Furthermore, if the user is an experiential learner, the skill selection unit can also select skills and recipes that emphasize hands-on experience. For example, the skill selection unit provides an experiential learner with the experience of actually filleting fish. In this way, the skill selection unit can provide optimal skills and recipes according to the user's learning style.

[0059] The instructor can monitor the user's learning progress in real time and adjust the instruction content according to the progress. For example, if the user is struggling with a particular technique, the instructor can provide detailed explanations and supplementary information about that technique. For example, if the user is struggling with how to use a knife, the instructor can provide detailed video or text explanations. Furthermore, if the user is making good progress in their learning, the instructor can expedite the timing for the user to move on to the next step, which is how to make sushi. Furthermore, the instructor can adjust the difficulty of the learning content according to the user's learning progress. For example, the instructor can adjust the difficulty of how to use a knife or how to fillet fish according to the user's learning progress. This allows the instructor to provide optimal instruction content according to the user's learning progress.

[0060] The advice unit can customize the content of the advice based on the user's learning goals. For example, if the user is aiming to become a professional chef, the advice unit can provide advice on advanced techniques and specialized knowledge. For example, the advice unit can provide advice on advanced techniques for using knives and filleting fish to a user who is aiming to become a professional chef. Furthermore, the advice unit can provide simple and practical advice to a user who wants to enjoy home cooking. For example, the advice unit can provide simple and practical advice on how to use knives and fillet fish to a user who wants to enjoy home cooking. Furthermore, if the user is aiming to participate in a specific cooking contest, the advice unit can provide advice specific to that contest. For example, the advice unit can provide advice on the techniques and presentation required for the contest to a user who is participating in a cooking contest. This allows the advice unit to provide optimal advice based on the user's learning goals.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The skill selection section allows users to select the skills or recipes they want to learn. For example, they can select skills such as how to use a knife, how to fillet fish, or how to make sushi. Step 2: The instructor provides step-by-step instruction based on the selected technique or recipe, for example, providing video or text instructions that the user can follow to actually cook the dish. Step 3: The image receiving unit receives an image of the completed dish from the user. For example, the user can upload an image taken with a smartphone or digital camera. Step 4: The evaluation unit analyzes and evaluates the received image. For example, the image is analyzed and evaluated based on evaluation criteria such as appearance, presentation, and technical accuracy. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may analyze and evaluate the image using an AI model that takes the image as input and outputs an evaluation result. Step 5: The advice unit provides advice based on the evaluation results. For example, the advice unit provides advice on areas for improvement or the next technology to learn. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can provide advice using an AI model that inputs the evaluation results and outputs advice.

[0063] (Example 2) The learning system according to an embodiment of the present invention is a learning service that uses AI to preserve Japanese food culture. This learning system supports a wide range of skills, from basic to applied, and even advanced techniques. When users upload images of their completed dishes, the AI ​​scores the images and provides specific advice. This learning system goes beyond simply providing recipes; it is a comprehensive platform for learning Japanese cuisine techniques, supporting everything from cooking classes to traditional Japanese restaurants. It is also designed to solve challenges facing the Japanese cuisine industry in the food processing, restaurant, and overseas expansion sectors. For example, users select the skills and recipes they want to learn. They can start with basic skills, such as how to use a knife, how to fillet fish, and how to make sushi. Next, the AI ​​provides step-by-step instruction based on the selected skills and recipes. Video and text instructions are provided, and users follow the instructions to actually cook the dish. Once the dish is complete, the user uploads an image of the dish to the AI. The AI ​​analyzes the image and evaluates the appearance, presentation, and accuracy of the technique. For example, specific criteria, such as whether the sushi is made correctly or the sashimi is beautifully cut, are evaluated. Based on the evaluation results, the AI ​​provides advice on areas for improvement and the next skills to learn. This learning system not only provides practical learning in cooking classes and restaurants, but also helps improve skills in the processing and food service industries. For example, food processors wanting to learn new techniques or restaurants wanting to improve the quality of their menus can use this learning system to efficiently acquire new skills. It can also be a useful tool for Japanese food industries aiming to expand overseas, allowing local staff to learn Japanese techniques. In this way, the learning system is a new-generation learning platform that utilizes AI to preserve Japanese food culture and learn new skills. Users can learn a wide range of techniques, from basic to advanced, and the AI ​​evaluates images of finished dishes and provides specific advice to help improve their skills. In this way, the learning system allows users to efficiently learn the techniques of Japanese food culture and improve their skills.

[0064] A learning system according to an embodiment includes a skill selection unit, an instruction unit, an image receiving unit, an evaluation unit, and an advice unit. The skill selection unit selects a skill or recipe that a user wants to learn. For example, the user can select skills such as how to use a knife, how to fillet fish, or how to make sushi. The instruction unit provides step-by-step instruction based on the selected skill or recipe. For example, the instruction unit provides video or text instructions that the user can follow to actually prepare the dish. The image receiving unit receives images of the completed dish. For example, the user can upload images taken with a smartphone or digital camera. The evaluation unit analyzes and evaluates the received images. For example, the image is analyzed and evaluated based on evaluation criteria such as appearance, presentation, and technical accuracy. Some or all of the above-described processing by the evaluation unit may be performed using, for example, AI, or may be performed without AI. For example, the evaluation unit may analyze and evaluate the image using an AI model that receives the image as input and outputs an evaluation result. The advice unit provides advice based on the evaluation result. For example, the advice unit provides advice on areas for improvement or the next skill to learn. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit may provide advice using an AI model that inputs evaluation results and outputs advice. This allows the learning system according to the embodiment to perform a consistent process from selecting techniques and recipes to providing instruction, evaluation, and advice.

[0065] The evaluation unit can analyze and evaluate images based on evaluation criteria such as appearance, presentation, and technical accuracy. For example, the evaluation unit considers color, arrangement, and overall balance as criteria for evaluating appearance. For example, the evaluation unit evaluates whether the color of the food is vivid and whether the presentation is beautiful. Furthermore, the evaluation unit considers the precision of knife use and cutting as criteria for evaluating technical accuracy. For example, the evaluation unit evaluates whether the sashimi is cut evenly and whether the sushi is made accurately. Furthermore, the evaluation unit considers the beauty of the food arrangement and decoration as criteria for evaluating presentation. For example, the evaluation unit evaluates whether the food is beautifully arranged and the decoration is appropriate. This allows the evaluation unit to make an accurate evaluation based on the evaluation criteria. Some or all of the above-described processing in the evaluation unit may be performed using, or without, AI. For example, the evaluation unit can analyze and evaluate images using an AI model that receives an image as input and outputs an evaluation result.

[0066] The skill selection unit can select skills such as how to use a knife, how to fillet fish, or how to make sushi. For example, as how to use a knife, the skill selection unit can select the basics of how to hold and cut a knife. For example, the skill selection unit provides lessons for learning the basics of how to hold and cut a knife. Furthermore, as how to fillet fish, the skill selection unit can select a filleting method depending on the type of fish. For example, the skill selection unit provides lessons for learning how to fillet fish such as sea bream or salmon. Furthermore, as how to make sushi, the skill selection unit can select how to make rice or how to place toppings on the sushi. For example, the skill selection unit provides lessons for learning how to make sushi rice or how to place toppings on the sushi. This allows the skill selection unit to select a specific skill that the user wants to learn.

[0067] The instruction unit can provide explanations in the form of video or text. For example, as video explanations, the instruction unit provides videos that visually show the steps of cooking. For example, the instruction unit uses videos to explain techniques such as how to use a knife, how to fillet fish, and how to make sushi. Furthermore, the instruction unit can provide text that describes the steps of cooking in detail as text explanations. For example, the instruction unit provides text that describes in detail the steps of cooking and important points to note. Furthermore, the instruction unit can provide explanations that combine video and text. For example, the instruction unit provides supplementary explanations in text in addition to video explanations. This allows the instruction unit to provide instruction that is visually easy for the user to understand.

[0068] The advice unit can provide advice on areas for improvement or the next skill to learn based on the evaluation results. For example, the advice unit can provide advice on areas for improvement in the appearance or presentation of a dish based on the evaluation results. For example, the advice unit can specifically suggest areas for improvement in the color, arrangement, or decoration of a dish. The advice unit can also provide advice on areas for improvement in the accuracy of techniques. For example, the advice unit can specifically suggest areas for improvement in knife usage, cutting accuracy, or sushi making. The advice unit can also provide advice on the next skill to learn. For example, the advice unit can specifically suggest the next skill or recipe the user should learn. This allows the advice unit to know the specific areas for improvement or the next skill to learn. Some or all of the above-described processing in the advice unit may be performed using, or without, AI. For example, the advice unit can provide advice using an AI model that inputs the evaluation results and outputs advice.

[0069] The evaluation unit can analyze and evaluate images using AI. The evaluation unit analyzes images using, for example, an image recognition algorithm using deep learning. For example, the evaluation unit uses a deep learning model to evaluate the appearance, presentation, and technical accuracy of the food. The evaluation unit can also use an image recognition algorithm to extract and evaluate the characteristics of the food. For example, the evaluation unit uses an image recognition algorithm to evaluate the color, arrangement, and technical accuracy of the food. The evaluation unit can also analyze and evaluate images based on evaluation criteria using AI. For example, the evaluation unit uses an AI model to evaluate the appearance, presentation, and technical accuracy. In this way, the evaluation unit improves the accuracy of image analysis and evaluation by using AI. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can analyze and evaluate images using an AI model that receives images as input and outputs evaluation results.

[0070] The learning system further includes a technology selection unit that estimates the user's emotions and presents technology and recipe options based on the estimated user emotions. The technology selection unit, for example, captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the technology selection unit calculates an emotion score based on changes in facial expression and presents technology and recipe options. The technology selection unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the technology selection unit analyzes the tone and speed of the voice, calculates an emotion score, and presents technology and recipe options. The technology selection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the technology selection unit calculates an emotion score based on heart rate fluctuations and presents technology and recipe options. This allows the technology selection unit to present optimal technologies and recipes based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the technology selection unit may be performed using AI, or may be performed without using AI. For example, the technology selection unit may input user emotion data into the generation AI and cause the generation AI to select techniques or recipes based on the emotion.

[0071] The skill selection unit can analyze the user's past learning history and recommend optimal skills and recipes. For example, the skill selection unit recommends the next skill the user should learn based on skills the user has learned in the past. For example, the skill selection unit recommends the next skill the user should learn based on the knife usage or fish filleting techniques the user has learned in the past. The skill selection unit can also recommend related new recipes based on recipes the user has successfully made in the past. For example, the skill selection unit recommends related new sushi recipes based on the sushi techniques the user has successfully made in the past. Furthermore, the skill selection unit can analyze the user's level of skill acquisition from the user's past learning history and recommend skills and recipes with an appropriate level of difficulty. For example, the skill selection unit analyzes the user's past learning history and recommends skills and recipes with an appropriate level of difficulty according to the user's level of skill acquisition. This allows the skill selection unit to recommend optimal skills and recipes based on the user's past learning history. Some or all of the above-described processing in the skill selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the technology selection unit can input the user's past learning history data into the generation AI and have the generation AI recommend optimal technologies and recipes.

[0072] The technique selection unit can automatically select techniques and recipes according to the season or event. The technique selection unit automatically selects recipes using seasonal ingredients, for example. For example, the technique selection unit selects recipes using seasonal ingredients, such as dishes using cherry blossoms in spring, chilled Chinese noodles in summer, matsutake rice in autumn, and oden in winter. The technique selection unit can also automatically select techniques and recipes suited to specific events (e.g., New Year's Day and Christmas). For example, the technique selection unit selects techniques and recipes suited to events, such as osechi ryori (New Year's dishes) for New Year's and roast chicken for Christmas. The technique selection unit can also automatically select traditional Japanese cuisine techniques and recipes for each season. For example, the technique selection unit selects traditional Japanese cuisine techniques and recipes for each season, such as cherry blossom viewing bento in spring, chilled somen noodles in summer, chestnut rice in autumn, and hot pot dishes in winter. This allows the technique selection unit to automatically select optimal techniques and recipes according to the season or event. Some or all of the above-described processing by the technique selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the technology selection unit can input seasonal and event data into the generation AI and have the generation AI select the optimal technology and recipe.

[0073] The skill selection unit can estimate the user's emotions and adjust the selection order of skills and recipes based on the estimated user emotions. For example, when the user is relaxed, the skill selection unit first presents more difficult skills and recipes. For example, when the user is relaxed, the skill selection unit first presents more difficult skills and recipes, such as how to use a knife or how to fillet fish. Furthermore, when the user is stressed, the skill selection unit can first present easier skills and recipes. For example, when the user is stressed, the skill selection unit first presents easier skills and recipes that provide a sense of accomplishment. Furthermore, when the user is excited, the skill selection unit can first present more challenging skills and recipes. For example, when the user is excited, the skill selection unit first presents new skills and recipes. This allows the skill selection unit to present skills and recipes in an optimal order according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the technology selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the technology selection unit may input user emotion data into the generation AI and have the generation AI execute a selection order of technologies and recipes based on the emotion.

[0074] The technique selection unit can prioritize regional techniques and recipes taking into account the user's geographical location information. For example, if the user is in Hokkaido, the technique selection unit prioritizes selecting techniques and recipes using Hokkaido's specialty products. For example, the technique selection unit prioritizes selecting techniques and recipes using salmon and potatoes, which are Hokkaido specialty products. Furthermore, if the user is in Kyoto, the technique selection unit can prioritize selecting traditional Kyoto techniques and recipes. For example, the technique selection unit prioritizes selecting Kyoto cuisine and yudofu recipes, which are traditional Kyoto techniques. Furthermore, if the user is overseas, the technique selection unit can prioritize selecting techniques and recipes using ingredients available in that region. For example, if the user is overseas, the technique selection unit prioritizes selecting Japanese cuisine techniques and recipes using ingredients available in that region. This allows the technique selection unit to prioritize regional techniques and recipes based on the user's geographical location information. Some or all of the above-described processing by the technique selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the technology selection unit can input the user's geographic location data into the generation AI and cause the generation AI to select region-specific technologies and recipes.

[0075] The technique selection unit can analyze a user's social media activity and select related techniques and recipes. For example, the technique selection unit can select related techniques and recipes based on images of food shared by the user on social media. For example, the technique selection unit can select related sushi techniques and recipes based on images of sushi shared by the user. The technique selection unit can also analyze the content of posts from cooking accounts followed by the user and select related techniques and recipes. For example, the technique selection unit can analyze the content of posts from Japanese food cooking accounts followed by the user and select related techniques and recipes. The technique selection unit can also select techniques and recipes that the user is likely to be interested in based on posts that the user has "liked." For example, the technique selection unit can select techniques and recipes that the user is likely to be interested in based on Japanese food posts that the user has "liked." This allows the technique selection unit to select related techniques and recipes based on the user's social media activity. Some or all of the above-described processing by the technique selection unit may be performed using, or without, AI. For example, the technique selection unit can input the user's social media activity data into a generation AI and cause the generation AI to select related techniques and recipes.

[0076] The instructor can estimate the user's emotions and adjust the way the instruction is expressed based on the estimated user's emotions. For example, when the user is relaxed, the instructor can provide instruction including detailed explanations. For example, when the user is relaxed, the instructor can provide instruction including detailed explanations on how to use a knife or how to fillet a fish. Furthermore, when the user is stressed, the instructor can provide concise and to-the-point instruction. For example, when the user is stressed, the instructor can provide concise and to-the-point instruction on how to use a knife or how to fillet a fish. Furthermore, when the user is excited, the instructor can provide instruction with visually stimulating effects. For example, when the user is excited, the instructor can provide instruction on how to use a knife or how to fillet a fish with visually stimulating effects. This allows the instructor to provide instruction in an optimal way of expression according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the instruction unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction unit may input the user's emotion data into the generation AI and cause the generation AI to execute an emotion-based instruction expression method.

[0077] During instruction, the instructor can customize the instruction content according to the user's learning speed. For example, if the user is learning at a fast pace, the instructor can accelerate the timing of moving on to the next step. For example, if the user is learning how to use a knife at a fast pace, the instructor can accelerate the timing of moving on to the next step, how to fillet a fish. Furthermore, if the user is learning at a slow pace, the instructor can provide detailed explanations and supplemental information. For example, if the user is learning how to use a knife at a slow pace, the instructor can provide detailed explanations and supplemental information. Furthermore, the instructor can adjust the difficulty of the instruction content according to the user's learning speed. For example, the instructor can adjust the difficulty of how to use a knife or how to fillet a fish according to the user's learning speed. This allows the instructor to provide optimal instruction content according to the user's learning speed. Some or all of the above-described processing in the instructor may be performed using, or without, AI. For example, the instructor can input the user's learning speed data into a generation AI and cause the generation AI to customize the instruction content based on the learning speed.

[0078] When providing instruction, the instruction unit can select the optimal instruction method by referring to the user's past learning history. For example, the instruction unit teaches a related new technique based on a technique the user previously learned. For example, if the user previously learned how to use a knife, the instruction unit teaches the user how to fillet fish, which is a related new technique. The instruction unit can also provide instruction to complement weak techniques based on the user's past learning history. For example, the instruction unit provides instruction to complement knife use, which the user previously struggled with. Furthermore, the instruction unit can analyze the user's past learning history and select the optimal instruction method. For example, the instruction unit analyzes the user's past learning history and selects the optimal instruction method. This allows the instruction unit to select the optimal instruction method based on the user's past learning history. Some or all of the above-mentioned processing in the instruction unit may be performed using, for example, AI, or may be performed without AI. For example, the instruction unit can input the user's past learning history data into a generation AI and have the generation AI select the optimal instruction method.

[0079] The instructor can estimate the user's emotions and adjust the length of the instruction based on the estimated user emotions. For example, when the user is relaxed, the instructor can provide longer instruction. For example, when the user is relaxed, the instructor can provide longer instruction on how to use a knife or how to fillet a fish. Furthermore, when the user is stressed, the instructor can provide shorter, more to-the-point instruction. For example, when the user is stressed, the instructor can provide shorter, more to-the-point instruction on how to use a knife or how to fillet a fish. Furthermore, when the user is excited, the instructor can provide instruction with visually stimulating effects. For example, when the user is excited, the instructor can provide instruction on how to use a knife or how to fillet a fish with visually stimulating effects. This allows the instructor to provide instruction at an optimal length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the instruction unit may be performed using AI, or may be performed without AI. For example, the instruction unit may input the user's emotion data into the generation AI and have the generation AI execute instruction based on the emotion.

[0080] The instructor can provide the optimal instruction method by taking into account the user's device information during instruction. For example, if the user is using a smartphone, the instructor can provide an instruction method tailored to the screen size. For example, the instructor can provide an instruction method for using a knife or filleting fish optimized for the small screen of a smartphone. Furthermore, if the user is using a tablet, the instructor can provide an instruction method optimized for a large screen. For example, the instructor can provide an instruction method for using a knife or filleting fish optimized for the large screen of a tablet. Furthermore, if the user is using a smartwatch, the instructor can provide a concise and highly visible instruction method. For example, the instructor can provide an instruction method for using a knife or filleting fish optimized for the small screen of a smartwatch. This allows the instructor to provide the optimal instruction method based on the user's device information. Some or all of the above-described processing by the instructor can be performed using AI, for example, or without AI. For example, the instructor can input the user's device information data into a generation AI and cause the generation AI to provide an instruction method based on the device information.

[0081] During instruction, the instruction unit can analyze the user's social media activity and provide relevant instruction content. For example, the instruction unit can provide instruction on related techniques and recipes based on images of dishes shared by the user on social media. For example, the instruction unit can provide instruction on related sushi techniques and recipes based on images of sushi shared by the user. The instruction unit can also analyze the content posted by cooking accounts followed by the user and provide instruction on related techniques and recipes. For example, the instruction unit can analyze the content posted by Japanese food cooking accounts followed by the user and provide instruction on related techniques and recipes. The instruction unit can also provide instruction on techniques and recipes that the user is likely to be interested in based on posts that the user has "liked." For example, the instruction unit can provide instruction on techniques and recipes that the user is likely to be interested in based on Japanese food posts that the user has "liked." This allows the instruction unit to provide relevant instruction content based on the user's social media activity. Some or all of the above-described processing by the instruction unit may be performed using, or without, AI. For example, the instruction unit can input the user's social media activity data into a generation AI and cause the generation AI to provide relevant instruction content.

[0082] The image receiving unit can estimate the user's emotions and adjust the timing of receiving images based on the estimated user's emotions. For example, if the user is relaxed, the image receiving unit receives an image immediately after the food is finished cooking. For example, if the user is relaxed, the image receiving unit receives an image immediately after the food is finished cooking. Furthermore, if the user is stressed, the image receiving unit can receive an image before the food cools down. For example, if the user is stressed, the image receiving unit receives an image before the food cools down. Furthermore, if the user is excited, the image receiving unit can receive an image immediately after the food is finished being plated. For example, if the user is excited, the image receiving unit receives an image immediately after the food is finished being plated. This allows the image receiving unit to receive images at the optimal timing according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the image receiving unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the image receiving unit can input the user's emotion data into the generation AI and cause the generation AI to execute the timing of receiving images based on the emotion.

[0083] When accepting images, the image accepting unit can analyze the user's past image submission history and select the optimal acceptance method. The image accepting unit selects the optimal acceptance method, for example, based on the quality of images previously submitted by the user. For example, the image accepting unit analyzes the quality of images previously submitted by the user and selects the optimal acceptance method. The image accepting unit can also optimize the submission timing based on the user's past image submission history. For example, the image accepting unit analyzes the user's past image submission history and selects the optimal submission timing. Furthermore, the image accepting unit can analyze the user's past image submission history and provide optimal feedback. For example, the image accepting unit analyzes the user's past image submission history and provides optimal feedback. This allows the image accepting unit to select the optimal acceptance method based on the user's past image submission history. Some or all of the above-described processing in the image accepting unit may be performed using, for example, AI, or may be performed without using AI. For example, the image accepting unit can input the user's past image submission history data into a generation AI and cause the generation AI to select the optimal acceptance method.

[0084] The image receiving unit may perform filtering based on the user's current project or field of interest when receiving images. For example, the image receiving unit may preferentially receive images related to a project the user is currently working on. For example, the image receiving unit may preferentially receive images of dishes related to the project the user is currently working on. The image receiving unit may also filter and receive related images based on the user's field of interest. For example, the image receiving unit may filter and receive images of related dishes based on the user's field of interest. Furthermore, the image receiving unit may select an optimal image receiving method taking into account the user's current project or field of interest. For example, the image receiving unit may select an optimal image receiving method taking into account the user's current project or field of interest. This allows the image receiving unit to filter and receive related images based on the user's current project or field of interest. Some or all of the above-described processing in the image receiving unit may be performed using, or without, AI. For example, the image receiving unit may input the user's current project or field of interest data to a generation AI and cause the generation AI to perform filtering.

[0085] The image receiving unit can estimate the user's emotions and determine the priority of images to be received based on the estimated user's emotions. For example, when the user is relaxed, the image receiving unit receives all images equally. For example, when the user is relaxed, the image receiving unit receives all food images equally. Furthermore, when the user is stressed, the image receiving unit can preferentially receive important images. For example, when the user is stressed, the image receiving unit preferentially receives images of important dishes. Furthermore, when the user is excited, the image receiving unit can preferentially receive the latest images. For example, when the user is excited, the image receiving unit preferentially receives images of the latest dishes. This allows the image receiving unit to receive images in an optimal priority order according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the image receiving unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the image receiving unit can input the user's emotional data into the generation AI and cause the generation AI to prioritize images based on the emotion.

[0086] When receiving images, the image receiving unit can prioritize receiving highly relevant images taking into account the user's geographical location information. For example, if the user is in Hokkaido, the image receiving unit prioritizes receiving images of dishes using Hokkaido's specialty products. For example, if the user is in Hokkaido, the image receiving unit prioritizes receiving images of dishes using Hokkaido's specialty products such as salmon and potatoes. Furthermore, if the user is in Kyoto, the image receiving unit can prioritize receiving images of traditional Kyoto dishes. For example, if the user is in Kyoto, the image receiving unit prioritizes receiving images of Kyoto cuisine and yudofu, which are traditional Kyoto dishes. Furthermore, if the user is overseas, the image receiving unit can prioritize receiving images of dishes using ingredients available in that region. For example, if the user is overseas, the image receiving unit prioritizes receiving images of Japanese cuisine using ingredients available in that region. This allows the image receiving unit to prioritize receiving highly relevant images based on the user's geographical location information. Some or all of the above-described processing in the image receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the image reception unit can input the user's geographical location information data into the generation AI and cause the generation AI to receive highly relevant images.

[0087] The image receiving unit can analyze the user's social media activity when receiving images and receive related images. For example, the image receiving unit prioritizes receiving images of food shared by the user on social media. For example, the image receiving unit prioritizes receiving images of sushi shared by the user on social media. The image receiving unit can also analyze the content posted by cooking accounts followed by the user and receive related images. For example, the image receiving unit analyzes the content posted by Japanese food cooking accounts followed by the user and receive related images. The image receiving unit can also receive related images based on posts that the user has "liked." For example, the image receiving unit receives related images based on Japanese food posts that the user has "liked." This allows the image receiving unit to receive related images based on the user's social media activity. Some or all of the above-described processing in the image receiving unit may be performed using, for example, AI, or may be performed without using AI. For example, the image receiving unit can input the user's social media activity data into a generation AI and cause the generation AI to receive related images.

[0088] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated user's emotions. For example, when the user is relaxed, the evaluation unit applies strict evaluation criteria. For example, when the user is relaxed, the evaluation unit applies strict evaluation criteria for knife usage and fish filleting. Furthermore, when the user is stressed, the evaluation unit can apply lenient evaluation criteria. For example, when the user is stressed, the evaluation unit applies lenient evaluation criteria for knife usage and fish filleting. Furthermore, when the user is excited, the evaluation unit can perform evaluation by adding visually stimulating effects. For example, when the user is excited, the evaluation unit evaluates knife usage and fish filleting with visually stimulating effects. This allows the evaluation unit to perform evaluation using optimal evaluation criteria according to the user's emotions. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input user emotion data to the generation AI and cause the generation AI to adjust the evaluation criteria based on the emotion.

[0089] The evaluation unit can improve the accuracy of the evaluation by taking into account the interrelationships between dishes during evaluation. The evaluation unit, for example, evaluates the overall balance by taking into account the combination of dishes. For example, the evaluation unit evaluates the overall balance by taking into account the combination of dishes. The evaluation unit can also evaluate the accuracy of the technique based on the interrelationships between dishes. For example, the evaluation unit evaluates the accuracy of the technique of knife use or fish filleting based on the interrelationships between dishes. The evaluation unit can also evaluate the appearance and presentation by taking into account the interrelationships between dishes. For example, the evaluation unit evaluates the appearance and presentation by taking into account the interrelationships between dishes. In this way, the evaluation unit improves the accuracy of the evaluation by taking into account the interrelationships between dishes. Some or all of the above-mentioned processing in the evaluation unit may be performed using, or without using, AI, for example. For example, the evaluation unit can input interrelationship data between dishes into the generation AI and cause the generation AI to improve the accuracy of the evaluation based on the interrelationships.

[0090] The evaluation unit can perform the evaluation by taking into account the attribute information of the person who submitted the dish. The evaluation unit adjusts the evaluation criteria, for example, by taking into account the experience level of the person who submitted the dish. For example, the evaluation unit adjusts the evaluation criteria for knife usage and fish filleting techniques, taking into account the experience level of the person who submitted the dish. The evaluation unit can also adjust the evaluation criteria based on the person's past evaluation history. For example, the evaluation unit adjusts the evaluation criteria for knife usage and fish filleting techniques, taking into account the person's past evaluation history. The evaluation unit can also adjust the evaluation criteria by taking into account the person's attribute information (e.g., age, occupation). For example, the evaluation unit adjusts the evaluation criteria for knife usage and fish filleting techniques, taking into account the person's age and occupation. This allows the evaluation unit to perform an optimal evaluation based on the person's attribute information. Some or all of the above-described processing in the evaluation unit may be performed using, or without, AI. For example, the evaluation unit can input the person's attribute information data to the generation AI and cause the generation AI to adjust the evaluation criteria based on the attribute information.

[0091] The evaluation unit can estimate the user's emotions and adjust the order in which the evaluation results are displayed based on the estimated user's emotions. For example, when the user is relaxed, the evaluation unit can first display detailed evaluation results. For example, when the user is relaxed, the evaluation unit can first display detailed evaluation results on how to use a knife or how to fillet a fish. Furthermore, when the user is stressed, the evaluation unit can first display brief evaluation results. For example, when the user is stressed, the evaluation unit can first display brief evaluation results on how to use a knife or how to fillet a fish. Furthermore, when the user is excited, the evaluation unit can first display evaluation results with visually stimulating effects. For example, when the user is excited, the evaluation unit can first display evaluation results on how to use a knife or how to fillet a fish with visually stimulating effects. This allows the evaluation unit to display the evaluation results in an optimal order according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input user emotion data to the generation AI and have the generation AI execute the display order of the evaluation results based on the emotion.

[0092] The evaluation unit can perform the evaluation taking into account the geographical distribution of the dishes. For example, the evaluation unit applies region-specific evaluation criteria based on the geographical distribution of the dishes. For example, the evaluation unit applies Hokkaido-specific evaluation criteria to Hokkaido dishes and Kyoto-specific evaluation criteria to Kyoto dishes based on the geographical distribution of the dishes. The evaluation unit can also reflect the difficulty of obtaining ingredients in the evaluation taking into account the geographical distribution. For example, the evaluation unit reflects the difficulty of obtaining ingredients in the evaluation taking into account the geographical distribution. Furthermore, the evaluation unit can also perform an evaluation taking into account the food culture of the region based on the geographical distribution. For example, the evaluation unit performs an evaluation taking into account the food culture of the region based on the geographical distribution. This allows the evaluation unit to perform an optimal evaluation based on the geographical distribution of the dishes. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input geographical distribution data of the dishes to the generation AI and cause the generation AI to perform an evaluation based on the geographical distribution.

[0093] The evaluation unit can improve the accuracy of the evaluation by referring to literature related to cooking during the evaluation. The evaluation unit, for example, evaluates the accuracy of the technique based on literature related to cooking. For example, the evaluation unit evaluates the accuracy of the technique of knife use and fish filleting based on literature related to cooking. The evaluation unit can also evaluate the appearance and presentation by referring to related literature. For example, the evaluation unit evaluates the appearance and presentation of knife use and fish filleting based on related literature. The evaluation unit can also adjust the evaluation criteria based on literature related to cooking. For example, the evaluation unit adjusts the evaluation criteria of knife use and fish filleting based on literature related to cooking. In this way, the evaluation unit improves the accuracy of the evaluation by referring to literature related to cooking. Some or all of the above-mentioned processing in the evaluation unit may be performed using, or without, AI, for example. For example, the evaluation unit can input literature data related to cooking into the generation AI and cause the generation AI to improve the accuracy of the evaluation based on the related literature.

[0094] The advice unit can estimate the user's emotions and adjust the way in which advice is expressed based on the estimated user's emotions. For example, when the user is relaxed, the advice unit provides detailed advice. For example, when the user is relaxed, the advice unit provides detailed advice on how to use a knife or how to fillet a fish. Furthermore, when the user is stressed, the advice unit can provide concise and to-the-point advice. For example, when the user is stressed, the advice unit provides concise and to-the-point advice on how to use a knife or how to fillet a fish. Furthermore, when the user is excited, the advice unit can provide advice with visually stimulating effects. For example, when the user is excited, the advice unit provides advice on how to use a knife or how to fillet a fish with visually stimulating effects. This allows the advice unit to provide advice in an optimal way of expression according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit may input user emotion data to the generation AI and cause the generation AI to execute a method of expressing emotion-based advice.

[0095] When giving advice, the advice unit can provide optimal advice by referring to the user's past learning history. For example, the advice unit can provide advice on a related new technique based on a technique the user learned in the past. For example, if the user previously learned how to use a knife, the advice unit can provide advice on a related new technique, such as how to fillet fish. The advice unit can also provide advice to compensate for weak techniques based on the user's past learning history. For example, the advice unit can provide advice to compensate for a knife technique that the user previously struggled with. Furthermore, the advice unit can analyze the user's past learning history and provide optimal advice. For example, the advice unit can analyze the user's past learning history and provide optimal advice. This allows the advice unit to provide optimal advice based on the user's past learning history. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the user's past learning history data into the generation AI and cause the generation AI to provide optimal advice.

[0096] When providing advice, the advice unit can customize the content of the advice based on the user's current learning status. The advice unit, for example, provides advice related to a skill the user is currently learning. For example, the advice unit provides advice related to how to use a knife that the user is currently learning. The advice unit can also provide advice on the next skill to be learned based on the user's current learning status. For example, the advice unit provides advice on how to fillet fish that the user should learn next based on the user's current learning status. The advice unit can also customize the content of the advice taking into account the user's current learning status. For example, the advice unit customizes the content of advice on how to use a knife or how to fillet fish taking into account the user's current learning status. This allows the advice unit to provide optimal advice based on the user's current learning status. Some or all of the above-described processing in the advice unit may be performed using, or without, AI. For example, the advice unit can input data on the user's current learning status into the generation AI and cause the generation AI to customize the advice based on the learning status.

[0097] The advice unit can estimate the user's emotions and determine the priority of advice based on the estimated user's emotions. For example, when the user is relaxed, the advice unit provides all advice equally. For example, when the user is relaxed, the advice unit provides all advice equally, such as advice on how to use a knife or how to fillet fish. Furthermore, when the user is stressed, the advice unit can prioritize providing important advice. For example, when the user is stressed, the advice unit prioritizes providing important advice on how to use a knife or how to fillet fish. Furthermore, when the user is excited, the advice unit can prioritize providing the latest advice. For example, when the user is excited, the advice unit prioritizes providing the latest advice on how to use a knife or how to fillet fish. This allows the advice unit to provide advice in an optimal priority order according to the user's emotions. Emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit may input user emotion data to the generation AI and have the generation AI execute advice priorities based on emotions.

[0098] When providing advice, the advice unit can provide optimal advice taking into account the user's geographical location information. For example, if the user is in Hokkaido, the advice unit can provide advice on dishes using Hokkaido's specialties. For example, if the user is in Hokkaido, the advice unit can provide advice on dishes using Hokkaido's specialties such as salmon and potatoes. Furthermore, if the user is in Kyoto, the advice unit can provide advice on traditional Kyoto dishes. For example, if the user is in Kyoto, the advice unit can provide advice on Kyoto cuisine and yudofu, which are traditional Kyoto dishes. Furthermore, if the user is overseas, the advice unit can provide advice on dishes using ingredients available in that area. For example, if the user is overseas, the advice unit can provide advice on Japanese cuisine using ingredients available in that area. This allows the advice unit to provide optimal advice based on the user's geographical location information. Some or all of the above-described processing by the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can input the user's geographical location information data into the generation AI and cause the generation AI to provide advice based on the geographical location information.

[0099] When providing advice, the advice unit can analyze the user's social media activity and provide relevant advice. For example, the advice unit can provide relevant advice based on images of food shared by the user on social media. For example, the advice unit can provide advice on related sushi techniques and recipes based on images of sushi shared by the user on social media. The advice unit can also analyze the content of posts from cooking accounts followed by the user and provide relevant advice. For example, the advice unit can analyze the content of posts from Japanese food cooking accounts followed by the user and provide advice on related techniques and recipes. The advice unit can also provide advice that is likely to be of interest to the user based on posts that the user has "liked." For example, the advice unit can provide advice on techniques and recipes that the user is likely to be interested in based on Japanese food posts that the user has "liked." This allows the advice unit to provide relevant advice based on the user's social media activity. Some or all of the above-described processing by the advice unit may be performed using, or without, AI. For example, the advice unit can input the user's social media activity data into a generation AI and cause the generation AI to provide relevant advice. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned technique selection unit, instruction unit, image reception unit, evaluation unit, and advice unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the technique selection unit is realized by the control unit 46A of the smart device 14 and selects a technique or recipe the user wants to learn. The instruction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides step-by-step instruction based on the selected technique or recipe. The image reception unit is realized, for example, by the camera 42 of the smart device 14 and receives images of dishes completed by the user. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes and evaluates the received images. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides advice based on the evaluation results. Furthermore, the technique selection unit has a function of estimating the user's emotions and presenting technique and recipe options based on the estimated user emotions, for example, by analyzing the user's facial expressions and voice using the camera 42 or microphone 38B of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned technique selection unit, instruction unit, image reception unit, evaluation unit, and advice unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the technique selection unit is realized by the control unit 46A of the smart glasses 214 and selects a technique or recipe the user wants to learn. The instruction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides step-by-step instruction based on the selected technique or recipe. The image reception unit is realized, for example, using the camera 42 of the smart glasses 214 and receives images of the dish the user has completed. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes and evaluates the received images. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides advice based on the evaluation results. Furthermore, the technology selection unit has the function of estimating the user's emotions and presenting technology and recipe options based on the estimated user emotions, and for example, analyzes the user's facial expressions and voice using the camera 42 and microphone 238 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned technique selection unit, instruction unit, image reception unit, evaluation unit, and advice unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the technique selection unit is realized by the control unit 46A of the headset-type terminal 314 and selects a technique or recipe that the user wants to learn. The instruction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides step-by-step instruction based on the selected technique or recipe. The image reception unit is realized, for example, using the camera 42 of the headset-type terminal 314 and receives images of dishes completed by the user. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes and evaluates the received images. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides advice based on the evaluation results. Furthermore, the technology selection unit has the function of estimating the user's emotions and presenting technology and recipe options based on the estimated user emotions, and for example, analyzes the user's facial expressions and voice using the camera 42 and microphone 238 of the headset-type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned technique selection unit, instruction unit, image reception unit, evaluation unit, and advice unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the technique selection unit is realized by the control unit 46A of the robot 414 and selects a technique or recipe the user wants to learn. The instruction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides step-by-step instruction based on the selected technique or recipe. The image reception unit is realized, for example, by the camera 42 of the robot 414 and receives images of dishes completed by the user. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes and evaluates the received images. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides advice based on the evaluation results. Furthermore, the technique selection unit has a function of estimating the user's emotions and presenting options of techniques and recipes based on the estimated user emotions, for example, by analyzing the user's facial expressions and voice using the camera 42 and microphone 238 of the robot 414.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The learning system may further include a health management unit that monitors the user's health condition and presents options for techniques and recipes based on the health condition. For example, the health management unit may monitor the user's blood pressure and heart rate and select techniques and recipes according to the user's health condition. For example, if the user's blood pressure is high, it may select recipes with low salt content. The health management unit may also analyze the user's dietary history and select techniques and recipes that take nutritional balance into consideration. For example, if the user has not eaten vegetables recently, it may select recipes with a high concentration of vegetables. Furthermore, the health management unit may monitor the user's exercise volume and select techniques and recipes according to the amount of exercise. For example, if the user is not exercising enough, it may select recipes with low calories. This allows the learning system to provide the optimal techniques and recipes according to the user's health condition.

[0102] The evaluation unit can adjust the evaluation criteria by taking into account the cultural background of the user. For example, if the user is from a different cultural sphere, the evaluation unit makes the evaluation by taking into account the aesthetic standards of cuisine in that culture. For example, if the user is from France, the evaluation unit makes the evaluation by taking into account the aesthetic standards of French cuisine. The evaluation unit can also adjust the evaluation criteria by taking into account the religious background of the user. For example, if the user is Muslim, the evaluation unit makes the evaluation by taking into account Halal standards. Furthermore, the evaluation unit can adjust the evaluation criteria by taking into account the eating habits of the user. For example, if the user is vegetarian, the evaluation unit makes the evaluation by taking into account the standards of vegetarian cuisine. This allows the evaluation unit to make an optimal evaluation according to the cultural background of the user.

[0103] The skill selection unit can present options for skills and recipes according to the user's learning style. For example, if the user is a visual learner, the skill selection unit selects skills and recipes that make extensive use of videos. For example, the skill selection unit uses videos to explain to a visual learner how to use a knife or how to fillet fish. Furthermore, if the user is an auditory learner, the skill selection unit can select skills and recipes that make extensive use of audio guidance. For example, the skill selection unit uses audio guidance to explain to an auditory learner how to make sushi. Furthermore, if the user is an experiential learner, the skill selection unit can also select skills and recipes that emphasize hands-on experience. For example, the skill selection unit provides an experiential learner with the experience of actually filleting fish. In this way, the skill selection unit can provide optimal skills and recipes according to the user's learning style.

[0104] The instructor can monitor the user's learning progress in real time and adjust the instruction content according to the progress. For example, if the user is struggling with a particular technique, the instructor can provide detailed explanations and supplementary information about that technique. For example, if the user is struggling with how to use a knife, the instructor can provide detailed video or text explanations. Furthermore, if the user is making good progress in their learning, the instructor can expedite the timing for the user to move on to the next step, which is how to make sushi. Furthermore, the instructor can adjust the difficulty of the learning content according to the user's learning progress. For example, the instructor can adjust the difficulty of how to use a knife or how to fillet fish according to the user's learning progress. This allows the instructor to provide optimal instruction content according to the user's learning progress.

[0105] The advice unit can customize the content of the advice based on the user's learning goals. For example, if the user is aiming to become a professional chef, the advice unit can provide advice on advanced techniques and specialized knowledge. For example, the advice unit can provide advice on advanced techniques for using knives and filleting fish to a user who is aiming to become a professional chef. Furthermore, the advice unit can provide simple and practical advice to a user who wants to enjoy home cooking. For example, the advice unit can provide simple and practical advice on how to use knives and fillet fish to a user who wants to enjoy home cooking. Furthermore, if the user is aiming to participate in a specific cooking contest, the advice unit can provide advice specific to that contest. For example, the advice unit can provide advice on the techniques and presentation required for the contest to a user who is participating in a cooking contest. This allows the advice unit to provide optimal advice based on the user's learning goals.

[0106] The evaluation unit can estimate the user's emotions and adjust the feedback method of the evaluation result based on the estimated user's emotions. For example, the evaluation unit provides detailed feedback when the user is relaxed. For example, the evaluation unit provides detailed feedback on how to use a knife or how to fillet a fish when the user is relaxed. Furthermore, the evaluation unit can provide concise and to-the-point feedback when the user is stressed. For example, the evaluation unit provides concise and to-the-point feedback on how to use a knife or how to fillet a fish when the user is stressed. Furthermore, the evaluation unit can also provide feedback with visually stimulating effects when the user is excited. For example, the evaluation unit provides feedback on how to use a knife or how to fillet a fish with visually stimulating effects when the user is excited. This allows the evaluation unit to provide the evaluation result using an optimal feedback method according to the user's emotions.

[0107] The skill selection unit can estimate the user's emotions and present options for skills and recipes based on the estimated user's emotions. For example, when the user is relaxed, the skill selection unit presents difficult skills and recipes. For example, when the user is relaxed, the skill selection unit presents difficult skills and recipes, such as how to use a knife or how to fillet fish. Furthermore, when the user is feeling stressed, the skill selection unit can present simple skills and recipes. For example, when the user is feeling stressed, the skill selection unit presents simple skills and recipes that provide a sense of accomplishment. Furthermore, when the user is excited, the skill selection unit can present challenging skills and recipes. For example, when the user is excited, the skill selection unit presents new skills and recipes. In this way, the skill selection unit can present optimal skills and recipes according to the user's emotions.

[0108] The instructor can estimate the user's emotions and adjust the manner in which the instruction is expressed based on the estimated user's emotions. For example, if the user is relaxed, the instructor can provide instruction that includes detailed explanations. For example, if the user is relaxed, the instructor can provide instruction that includes detailed explanations on how to use a knife or how to fillet a fish. Furthermore, if the user is feeling stressed, the instructor can provide concise and to-the-point instruction. For example, if the user is feeling stressed, the instructor can provide concise and to-the-point instruction on how to use a knife or how to fillet a fish. Furthermore, if the user is excited, the instructor can provide instruction that adds visually stimulating effects. For example, if the user is excited, the instructor can provide instruction on how to use a knife or how to fillet a fish with visually stimulating effects. This allows the instructor to provide instruction in an optimal manner according to the user's emotions.

[0109] The advice unit can estimate the user's emotions and adjust the manner in which advice is expressed based on the estimated user's emotions. For example, the advice unit provides detailed advice when the user is relaxed. For example, the advice unit provides detailed advice on how to use a knife or how to fillet a fish when the user is relaxed. Furthermore, the advice unit can provide concise and to-the-point advice when the user is stressed. For example, the advice unit provides concise and to-the-point advice on how to use a knife or how to fillet a fish when the user is stressed. Furthermore, the advice unit can provide advice with visually stimulating effects when the user is excited. For example, the advice unit provides advice on how to use a knife or how to fillet a fish with visually stimulating effects when the user is excited. This allows the advice unit to provide advice in an optimal manner according to the user's emotions.

[0110] The evaluation unit can estimate the user's emotions and adjust the order in which the evaluation results are displayed based on the estimated user's emotions. For example, when the user is relaxed, the evaluation unit can first display detailed evaluation results. For example, when the user is relaxed, the evaluation unit can first display detailed evaluation results on how to use a knife or how to fillet a fish. Furthermore, when the user is stressed, the evaluation unit can first display brief evaluation results. For example, when the user is stressed, the evaluation unit can first display brief evaluation results on how to use a knife or how to fillet a fish. Furthermore, when the user is excited, the evaluation unit can also first display evaluation results with visually stimulating effects. For example, when the user is excited, the evaluation unit can first display evaluation results on how to use a knife or how to fillet a fish with visually stimulating effects. This allows the evaluation unit to display the evaluation results in an optimal order according to the user's emotions.

[0111] The processing flow of the second embodiment will be briefly explained below.

[0112] Step 1: The skill selection section allows users to select the skills or recipes they want to learn. For example, they can select skills such as how to use a knife, how to fillet fish, or how to make sushi. Step 2: The instructor provides step-by-step instruction based on the selected technique or recipe, for example, providing video or text instructions that the user can follow to actually cook the dish. Step 3: The image receiving unit receives an image of the completed dish from the user. For example, the user can upload an image taken with a smartphone or digital camera. Step 4: The evaluation unit analyzes and evaluates the received image. For example, the image is analyzed and evaluated based on evaluation criteria such as appearance, presentation, and technical accuracy. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may analyze and evaluate the image using an AI model that takes the image as input and outputs an evaluation result. Step 5: The advice unit provides advice based on the evaluation results. For example, the advice unit provides advice on areas for improvement or the next technology to learn. Some or all of the above-described processing in the advice unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice unit can provide advice using an AI model that inputs the evaluation results and outputs advice.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0115] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0117] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0118] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0131] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0143] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0149] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0150] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0151] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0153] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0155] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0156] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0157] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0158] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0159] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0160] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0161] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0162] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0163] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0164] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0165] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0166] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0168] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0169] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0170] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0174] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0175] 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.

[0176] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0177] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0178] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0179] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0181] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0182] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0183] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0184] [Explanation of symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a technique selection unit that accepts a technique or recipe selection; a teaching unit that provides step-by-step instruction based on the technique or recipe selected by the technique selection unit; an image receiving unit that receives an image of the dish that has been instructed by the instruction unit; an evaluation unit that analyzes and evaluates the image received by the image receiving unit; an advice unit that provides advice based on the evaluation result obtained by the evaluation unit; Equipped with A system characterized by:

2. The evaluation unit Analyze and evaluate images based on criteria such as appearance, presentation, and technical accuracy 2. The system of claim 1.

3. The technology selection unit Choose skills such as how to use a knife, fillet a fish, or make sushi.

2. The system of claim 1.

4. The leadership team: Provide video or text instructions 2. The system of claim 1.

5. The advice unit Based on the evaluation results, we provide advice on areas for improvement and the next skills to learn.

2. The system of claim 1.

6. The evaluation unit Analyze and evaluate images using AI 2. The system of claim 1.

7. The technology selection unit Estimate the user's emotions and present options for techniques and recipes based on the estimated user emotions.

2. The system of claim 1.

8. The technology selection unit Analyzes the user's past learning history and recommends optimal techniques and recipes 2. The system of claim 1.

Images