system

Abstract

An object of a system according to an embodiment is to learn preferences and needs of a user and actively propose an idea based on the learned preferences and needs.SOLUTION: A system includes a preference learning part, an idea proposing part, and a generation AIBuilder part. The preference learning unit automatically learns preferences and needs of the user through interaction with the user. The idea proposing section actively proposes an idea based on the user's preferences and needs learned by the preference learning section. The generation AIBuilder component provides functionality for users to build their own generation AI.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of making it difficult to accurately grasp a user's preferences and needs and make appropriate suggestions based on them.

[0005] The system according to the embodiment aims to learn the preferences and needs of users and actively propose ideas based on the learned preferences and needs. [Means for solving the problem]

[0006] The system according to the embodiment includes a preference learning unit, an idea suggestion unit, and a generative AI builder unit. The preference learning unit automatically learns a user's preferences and needs through interactions with the user. The idea suggestion unit actively suggests ideas based on the user's preferences and needs learned by the preference learning unit. The generative AI builder unit provides a function that enables a user to build their own generative AI. [Effects of the Invention]

[0007] The system according to the embodiment can learn the preferences and needs of the user and actively suggest ideas based on the learned preferences and needs. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A generative AI system according to an embodiment of the present invention is a system that automatically learns a user's preferences and needs through interactions with the user, and actively suggests ideas and provides assistance. As a result, the generative AI system can improve the user experience by learning the user's preferences and needs and actively suggesting ideas.

[0029] A generative AI system according to an embodiment includes a preference learning unit, an idea suggestion unit, and a generation AI Builder unit. The preference learning unit automatically learns a user's preferences and needs through interactions with the user. For example, the preference learning unit collects user utterance and behavioral data, and the generation AI learns the user's preferences and needs based on that data. The generation AI, for example, analyzes the user's utterance and behavioral data using a machine learning algorithm to identify the user's preferences and needs. The generation AI can also learn the user's preferences and needs using deep learning technology. Furthermore, the generation AI can predict preferences and needs based on the user's past behavioral data. The idea suggestion unit actively suggests ideas based on the user's preferences and needs learned by the preference learning unit. For example, if a user says, "I'm not sure what to do this weekend," the idea suggestion unit suggests appropriate activities and events based on the user's past behavioral data and preferences. Furthermore, if a user says, "I'm looking for a new product," the idea suggestion unit recommends products that match the user's preferences. The Generative AI Builder section provides functions that allow users to build their own generative AI. For example, if a user prefers a specific language or tone, the Generative AI Builder section can reflect those settings in the generative AI. The Generative AI Builder section also allows users to add specific tasks and functions. This allows the generative AI system to learn the user's preferences and needs and actively suggest ideas to improve the user experience. For example, a generative AI system can automatically respond to customer inquiries in customer support and propose appropriate solutions. In addition, a generative AI system can analyze a user's purchasing history and preferences to recommend products that suit the user.

[0030] The preference learning unit analyzes a user's past purchase history and browsing history to learn preferences and needs with greater accuracy. For example, the preference learning unit analyzes the user's history of past purchases, and the generation AI learns the user's preferences based on that data. For example, new books are recommended based on the genres of books previously purchased. The preference learning unit also analyzes the user's website browsing history, and the generation AI learns the user's interests based on that data. For example, related content is suggested based on the content of frequently visited sites. The preference learning unit also integrates the user's past purchase history and browsing history, and the generation AI learns the user's preferences with greater accuracy based on that data. For example, new products are recommended based on reviews of purchased products. This makes it possible to learn preferences and needs with greater accuracy by analyzing past purchase history and browsing history.

[0031] The preference learning unit can also take into account the preferences of the user's social network and learn mutual influences. For example, the preference learning unit analyzes the content preferred by the user's friends and followers, and the generation AI learns the user's preferences based on that data. For example, it can recommend movies to the user based on the movies that friends often watch. The preference learning unit also analyzes information shared within the user's social network, and the generation AI learns the user's interests based on that data. For example, it can suggest related news based on articles shared by friends. The preference learning unit also analyzes products purchased by the user's followers, and the generation AI learns the user's purchasing trends based on that data. For example, it can recommend new products based on the products purchased by followers. This makes it possible to learn preferences and needs more accurately by taking into account the preferences of the social network.

[0032] The preference learning unit can share preferences and needs learned through interactions with the user across different devices, providing a seamless user experience. For example, the preference learning unit synchronizes preference data entered by the user on a smartphone with a smart speaker, and the generation AI makes suggestions as a voice assistant based on that data. The preference learning unit also synchronizes what the user says on the smart speaker with the smartphone, and the generation AI displays related information within the app based on that data. The preference learning unit also integrates the operation history performed by the user on different devices, and the generation AI makes seamless suggestions based on that data. For example, something searched on a smartphone can be played on a smart speaker. This allows preferences and needs to be shared across different devices, providing a seamless user experience.

[0033] The preference learning unit can also collect information from the user's voice and facial expressions, making it possible to utilize multimodal data. For example, the preference learning unit analyzes the user's speech, and the generation AI uses that data to learn the user's emotions and preferences. For example, the user's interests can be estimated based on the tone and speed of the voice. The preference learning unit also analyzes the user's facial expressions using a camera, and the generation AI uses that data to learn the user's emotions and preferences. For example, the user's preferences can be estimated based on smiling and surprised expressions. The preference learning unit also analyzes the user's voice and facial expressions simultaneously, and the generation AI uses that data to more accurately learn the user's emotions and preferences. For example, the user's interests can be estimated based on the degree of agreement between voice and facial expressions. In this way, by collecting information from voice and facial expressions, it is possible to learn preferences and needs with greater accuracy.

[0034] The idea suggestion unit can predict future needs based on the user's past behavioral data and preferences and proactively suggest ideas. For example, the idea suggestion unit analyzes data on past trips the user has taken, and the generation AI suggests the next travel destination based on that data. For example, it recommends new travel destinations based on the characteristics of places visited in the past. The idea suggestion unit also analyzes the user's past purchasing history, and the generation AI suggests products that are likely to be purchased next based on that data. For example, it recommends new products based on trends in products purchased in the past. The idea suggestion unit also analyzes the user's past behavioral data, and the generation AI predicts future needs based on that data. For example, it suggests the next event based on past event participation history. In this way, the user's convenience is improved by predicting future needs and proactively suggesting ideas.

[0035] The idea suggestion unit learns the user's lifestyle and daily routine, and based on that, can suggest ideas and provide assistance at the optimal timing. For example, the idea suggestion unit analyzes the user's daily schedule, and the generation AI suggests activities at the optimal timing based on that data. For example, it suggests activities that allow you to relax after work. The idea suggestion unit also analyzes the user's lifestyle data, and the generation AI recommends products at the optimal timing based on that data. For example, it suggests new coffee beans for your morning coffee. The idea suggestion unit also learns the user's daily routine, and the generation AI suggests events and activities at the optimal timing based on that data. For example, it suggests events when there are free weekend plans. This improves user convenience by making suggestions at the optimal timing based on the user's lifestyle and daily routine.

[0036] The idea suggestion unit can suggest ideas in different fields based on the user's preferences and needs. For example, if a user says, "I want to go on a trip," the generation AI infers the user's preferences from the statement and suggests travel destinations. For example, it recommends new travel destinations based on the characteristics of places visited in the past. If a user says, "I want to try a new dish," the generation AI infers the user's preferences from the statement and suggests new recipes. For example, it recommends new recipes based on the genre of dishes made in the past. If a user says, "I want to start a new hobby," the generation AI infers the user's preferences from the statement and suggests new hobbies. For example, it recommends new hobbies based on activities that the user has been interested in in the past. This allows the generation AI to suggest ideas in different fields and meet the diverse needs of users.

[0037] The idea suggestion unit can propose personalized study plans and training plans based on the user's preferences and needs. For example, if a user says, "I want to learn a new skill," the generation AI infers the user's preferences from the statement and proposes a personalized study plan. For example, it may recommend a new study plan based on skills learned in the past. If a user says, "I want to start fitness," the idea suggestion unit infers the user's preferences from the statement and proposes a personalized training plan. For example, it may recommend a new training plan based on past exercise history. If a user says, "I want to learn a language," the generation AI infers the user's preferences from the statement and proposes a personalized language study plan. For example, it may recommend a new language study plan based on languages ​​learned in the past. This allows the generation AI to propose personalized study plans and training plans that support the user's growth and health.

[0038] The generative AI Builder unit can learn the user's past customization history and suggest optimal customization options. For example, the generative AI Builder unit analyzes customization options set by the user in the past, and the generative AI Builder suggests optimal customization options based on that data. For example, it suggests new options based on the tone and language set in the past. The generative AI Builder unit also learns the user's past customization history, and the generative AI Builder suggests optimal customization options based on that data. For example, it suggests new options based on functions and tasks set in the past. The generative AI Builder unit also integrates the user's past customization history, and the generative AI Builder suggests optimal customization options based on that data. For example, it suggests new options based on environment settings set in the past. In this way, by learning past customization history, it is possible to suggest optimal customization options to the user.

[0039] The generation AI Builder unit can monitor user usage in real time and automatically update customization options based on usage frequency and patterns. For example, the generation AI Builder unit monitors user usage in real time, and the generation AI Builder automatically updates customization options based on that data. For example, it prioritizes displaying frequently used functions. The generation AI Builder unit also analyzes the user's usage frequency and patterns, and the generation AI Builder automatically updates customization options based on that data. For example, it automatically applies frequently used settings. The generation AI Builder unit also monitors user usage in real time, and the generation AI Builder automatically updates customization options based on that data. For example, it dynamically adjusts settings according to usage patterns. This makes it possible to automatically update customization options that are optimal for the user by monitoring usage in real time.

[0040] The Generative AI Builder unit provides customization options that support different languages ​​and cultures, making it possible to accommodate global users. For example, the Generative AI Builder unit provides customization options that support different languages, allowing users to configure the Generative AI in their own language. For example, it supports English, Japanese, French, etc. The Generative AI Builder unit also provides customization options that support different cultures, making it possible for users to configure the Generative AI that suits their own culture. For example, it provides settings that suit cultural customs and preferences. The Generative AI Builder unit also provides customization options that support different languages ​​and cultures, making it possible to accommodate global users. For example, it provides settings that suit the characteristics of each region. This makes it possible to accommodate global users by supporting different languages ​​and cultures.

[0041] The generation AI Builder unit can suggest personalized entertainment content based on the user's preferences and needs. For example, the generation AI Builder unit analyzes the user's preferences and needs, and the generation AI Builder suggests personalized music based on that data. For example, the generation AI Builder creates a playlist based on the user's favorite genres and artists. The generation AI Builder unit also analyzes the user's preferences and needs, and the generation AI Builder suggests personalized movies based on that data. For example, the generation AI Builder recommends movies based on the user's favorite genres and directors. The generation AI Builder unit also analyzes the user's preferences and needs, and the generation AI Builder suggests personalized entertainment content based on that data. For example, the generation AI Builder recommends TV programs and podcasts that the user likes. This makes it possible to improve user satisfaction by suggesting personalized entertainment content.

[0042] The customer support department can learn from past inquiry data and propose the most effective solution. For example, the customer support department analyzes past inquiry data and the generation AI proposes the most effective solution based on that data. For example, it makes a new proposal based on solutions to similar problems. The customer support department can also learn from customers' past inquiry history and the generation AI proposes the most effective solution based on that data. For example, it makes a new proposal based on past solutions. The customer support department can also integrate past inquiry data and the generation AI proposes the most effective solution based on that data. For example, it makes a new proposal based on solutions to similar problems. In this way, by learning from past inquiry data, it can propose the most effective solution.

[0043] The customer support department can analyze a customer's purchasing history and preferences to provide personalized support. For example, the customer support department analyzes a customer's purchasing history, and the generation AI provides personalized support based on that data. For example, it suggests how to use a purchased product or troubleshooting. The customer support department can also analyze a customer's preferences, and the generation AI provides personalized support based on that data. For example, it responds based on the customer's preferred support method. The customer support department can also integrate a customer's purchasing history and preferences, and the generation AI provides personalized support based on that data. For example, it suggests how to use a purchased product or troubleshooting. In this way, personalized support can be provided by analyzing a customer's purchasing history and preferences.

[0044] The customer support department can integrate customer support from different channels to provide a consistent support experience. For example, the generation AI can integrate support data from different channels, such as telephone, email, and chat, to provide a consistent support experience. For example, the same information can be provided regardless of which channel a customer uses. The customer support department can also integrate support history from different channels, and the generation AI can use that data to provide a consistent support experience. For example, it can respond based on the content of past inquiries. The customer support department can also integrate support data from different channels in real time to provide a consistent support experience. For example, the same information can be provided regardless of which channel a customer uses. This makes it possible to provide a consistent support experience by integrating support from different channels.

[0045] The customer support department can suggest related products and services based on the customer's preferences and needs. For example, the customer support department analyzes the customer's preferences and needs, and the generation AI suggests related products and services based on that data. For example, it recommends products related to products purchased in the past. The customer support department can also analyze the customer's preferences and needs, and the generation AI suggests related services based on that data. For example, it recommends services related to services used in the past. The customer support department can also analyze the customer's preferences and needs, and the generation AI suggests related products and services based on that data. For example, it recommends products related to products purchased in the past. In this way, customer satisfaction can be improved by suggesting related products and services based on the customer's preferences and needs.

[0046] The product recommendation unit can analyze a user's purchasing history and preferences and recommend the most relevant products. For example, the product recommendation unit analyzes a user's purchasing history and the generation AI recommends the most relevant products based on that data. For example, it suggests products related to products purchased in the past. The product recommendation unit also analyzes a user's preferences and the generation AI recommends the most relevant products based on that data. For example, it suggests products from brands or categories that the user likes. The product recommendation unit also integrates a user's purchasing history and preferences and the generation AI recommends the most relevant products based on that data. For example, it suggests new products based on reviews of products purchased in the past. In this way, the most relevant products can be recommended by analyzing a user's purchasing history and preferences.

[0047] The product recommendation unit can learn the user's lifestyle and daily routine and recommend the most suitable products based on that. For example, the product recommendation unit analyzes the user's lifestyle data, and the generation AI recommends the most suitable products based on that data. For example, if the user is health-conscious, health foods and fitness goods are suggested. The product recommendation unit also learns the user's daily routine, and the generation AI recommends the most suitable products based on that data. For example, if the user has the habit of drinking coffee every morning, new coffee beans are suggested. The product recommendation unit also integrates the user's lifestyle and daily routine, and the generation AI recommends the most suitable products based on that data. For example, if the user likes the outdoors, camping equipment is suggested. This makes it possible to improve user satisfaction by recommending the most suitable products based on the user's lifestyle and daily routine.

[0048] The product recommendation unit can recommend products in different categories. For example, if a user says, "I'm looking for new clothes," the generation AI infers the user's preferences from that statement and recommends products in the fashion category. For example, it would suggest clothes in the style the user prefers. Also, if a user says, "I want a new home appliance," the generation AI infers the user's preferences from that statement and recommends products in the home appliance category. For example, it would suggest home appliances with the functions the user needs. Also, if a user says, "I want to try a new recipe," the product recommendation unit infers the user's preferences from that statement and recommends products in the food category. For example, it would suggest recipes using ingredients the user likes. This allows the system to meet the diverse needs of users by recommending products in different categories.

[0049] The product recommendation unit can provide a personalized gift guide based on the user's preferences and needs. For example, the product recommendation unit analyzes the user's preferences and needs, and the generation AI provides a personalized gift guide based on that data. For example, it suggests products from brands or categories that the user likes. The product recommendation unit also analyzes the user's past purchasing history, and the generation AI provides a personalized gift guide based on that data. For example, it suggests products related to products purchased in the past. The product recommendation unit also integrates the user's preferences and needs, and the generation AI provides a personalized gift guide based on that data. For example, it suggests products in a style or theme that the user likes. This makes it possible to improve user satisfaction by providing a personalized gift guide based on the user's preferences and needs.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The generative AI system can also be equipped with a health management unit that monitors the user's health status and provides health advice. For example, the health management unit collects the user's heart rate and sleep data, and the generative AI analyzes the user's health status based on that data. If the user says, "I've been feeling tired lately," the generative AI will provide appropriate rest and exercise advice based on that statement and the collected data. The health management unit also collects the user's dietary data, and the generative AI analyzes nutritional balance based on that data. If the user says, "I want to start a diet," the generative AI will suggest an appropriate meal plan based on that statement and the collected data. This allows the system to monitor the user's health status and provide health advice, thereby supporting the user's health management.

[0052] The generative AI system can also include a learning support unit that provides learning content based on the user's hobbies and interests. For example, if a user says, "I want to learn a new skill," the learning support unit analyzes the user's statement and suggests appropriate online courses and learning materials. The learning support unit also analyzes the user's past learning history, and the generative AI uses that data to propose a learning plan tailored to the user. If a user says, "I want to learn programming," the generative AI will suggest an appropriate programming course based on the user's statement and past learning history. This can increase the user's motivation to learn by providing learning content based on the user's hobbies and interests.

[0053] The generative AI system can also be equipped with a purchasing support unit that analyzes a user's purchasing history and suggests new products based on their purchasing patterns. For example, the purchasing support unit analyzes data on products the user has previously purchased, and the generative AI uses that data to suggest new products. If a user says, "I'm looking for a new book," the generative AI recommends an appropriate book based on that statement and their past purchasing history. The purchasing support unit also analyzes the user's purchasing patterns, and the generative AI uses that data to suggest products that the user might be interested in. This improves the user's purchasing experience by suggesting new products based on the user's purchasing history and patterns.

[0054] The generative AI system may further include a social network unit that analyzes the user's social network and suggests new content based on the preferences of friends and followers. For example, the social network unit analyzes content shared by the user's friends, and the generative AI uses that data to suggest content relevant to the user. If a user says, "I want to see a new movie," the generative AI recommends an appropriate movie based on that statement and the preferences of their friends. The social network unit may also analyze products purchased by the user's followers, and the generative AI uses that data to suggest products relevant to the user. This can improve user satisfaction by suggesting new content based on the user's social network.

[0055] The generative AI system can also include a lifestyle section that analyzes the user's lifestyle data and suggests new activities based on the user's lifestyle. For example, the lifestyle section analyzes the user's daily schedule, and the generative AI suggests optimal activities based on that data. If the user says, "I'm not sure what to do this weekend," the generative AI suggests appropriate activities based on that statement and the schedule data. The lifestyle section also analyzes the user's lifestyle data, and the generative AI uses that data to suggest events and activities that the user might be interested in. This can improve user satisfaction by suggesting new activities based on the user's lifestyle.

[0056] The generative AI system can also be equipped with a prediction unit that analyzes the user's past behavioral data, predicts future needs, and makes proactive suggestions. For example, the prediction unit analyzes data from the user's past trips, and the generative AI uses that data to suggest the next travel destination. If the user says, "I want to decide on my next travel destination," the generative AI will recommend an appropriate destination based on that statement and past travel data. The prediction unit also analyzes the user's past purchasing history, and the generative AI uses that data to suggest products that the user is likely to purchase next. This improves user convenience by predicting future needs and making proactive suggestions.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The preference learning unit automatically learns the user's preferences and needs through interactions with the user. For example, the preference learning unit collects user utterances and behavioral data, and the generation AI learns the user's preferences and needs based on that data. The generation AI analyzes the user's utterances and behavioral data using machine learning algorithms and deep learning techniques to identify the user's preferences and needs. The generation AI can also predict preferences and needs based on the user's past behavioral data. Step 2: The idea suggestion unit actively suggests ideas based on the user's preferences and needs learned by the preference learning unit. For example, if a user says, "I'm not sure what to do this weekend," the generation AI will suggest appropriate activities and events based on the user's past behavioral data and preferences. Also, if a user says, "I'm looking for a new product," the generation AI will recommend products that match the user's preferences. Step 3: Generative AI The Builder section provides functions for users to build their own generative AI. For example, if a user prefers a specific language or tone, they can reflect that preference in the generative AI. Users can also add specific tasks or functions.

[0059] (Example 2) A generative AI system according to an embodiment of the present invention is a system that automatically learns a user's preferences and needs through interactions with the user, and actively suggests ideas and provides assistance. As a result, the generative AI system can improve the user experience by learning the user's preferences and needs and actively suggesting ideas.

[0060] A generative AI system according to an embodiment includes a preference learning unit, an idea suggestion unit, and a generation AI Builder unit. The preference learning unit automatically learns a user's preferences and needs through interactions with the user. For example, the preference learning unit collects user utterance and behavioral data, and the generation AI learns the user's preferences and needs based on that data. The generation AI, for example, analyzes the user's utterance and behavioral data using a machine learning algorithm to identify the user's preferences and needs. The generation AI can also learn the user's preferences and needs using deep learning technology. Furthermore, the generation AI can predict preferences and needs based on the user's past behavioral data. The idea suggestion unit actively suggests ideas based on the user's preferences and needs learned by the preference learning unit. For example, if a user says, "I'm not sure what to do this weekend," the idea suggestion unit suggests appropriate activities and events based on the user's past behavioral data and preferences. Furthermore, if a user says, "I'm looking for a new product," the idea suggestion unit recommends products that match the user's preferences. The Generative AI Builder section provides functions that allow users to build their own generative AI. For example, if a user prefers a specific language or tone, the Generative AI Builder section can reflect those settings in the generative AI. The Generative AI Builder section also allows users to add specific tasks and functions. This allows the generative AI system to learn the user's preferences and needs and actively suggest ideas to improve the user experience. For example, a generative AI system can automatically respond to customer inquiries in customer support and propose appropriate solutions. In addition, a generative AI system can analyze a user's purchasing history and preferences to recommend products that suit the user.

[0061] The preference learning unit allows the generation AI to infer a user's emotions based on the user's statements and behavioral data, and learn preferences and needs based on those emotions. For example, if a user says, "I'm tired today," the generation AI can infer the user's level of fatigue from that statement and suggest relaxing music or movies. Similarly, if a user says, "This movie was interesting," the generation AI can infer the user's excitement level from that statement and recommend movies in the same genre. Similarly, if a user says, "I've been feeling stressed lately," the generation AI can infer the user's stress level from that statement and suggest activities that will help relieve stress. This allows the generation AI to learn preferences and needs based on the user's emotions, enabling more accurate suggestions.

[0062] The preference learning unit analyzes a user's past purchase history and browsing history to learn preferences and needs with greater accuracy. For example, the preference learning unit analyzes the user's history of past purchases, and the generation AI learns the user's preferences based on that data. For example, new books are recommended based on the genres of books previously purchased. The preference learning unit also analyzes the user's website browsing history, and the generation AI learns the user's interests based on that data. For example, related content is suggested based on the content of frequently visited sites. The preference learning unit also integrates the user's past purchase history and browsing history, and the generation AI learns the user's preferences with greater accuracy based on that data. For example, new products are recommended based on reviews of purchased products. This makes it possible to learn preferences and needs with greater accuracy by analyzing past purchase history and browsing history.

[0063] The preference learning unit can also take into account the preferences of the user's social network and learn mutual influences. For example, the preference learning unit analyzes the content preferred by the user's friends and followers, and the generation AI learns the user's preferences based on that data. For example, it can recommend movies to the user based on the movies that friends often watch. The preference learning unit also analyzes information shared within the user's social network, and the generation AI learns the user's interests based on that data. For example, it can suggest related news based on articles shared by friends. The preference learning unit also analyzes products purchased by the user's followers, and the generation AI learns the user's purchasing trends based on that data. For example, it can recommend new products based on the products purchased by followers. This makes it possible to learn preferences and needs more accurately by taking into account the preferences of the social network.

[0064] The preference learning unit can share preferences and needs learned through interactions with the user across different devices, providing a seamless user experience. For example, the preference learning unit synchronizes preference data entered by the user on a smartphone with a smart speaker, and the generation AI makes suggestions as a voice assistant based on that data. The preference learning unit also synchronizes what the user says on the smart speaker with the smartphone, and the generation AI displays related information within the app based on that data. The preference learning unit also integrates the operation history performed by the user on different devices, and the generation AI makes seamless suggestions based on that data. For example, something searched on a smartphone can be played on a smart speaker. This allows preferences and needs to be shared across different devices, providing a seamless user experience.

[0065] The preference learning unit can also collect information from the user's voice and facial expressions, making it possible to utilize multimodal data. For example, the preference learning unit analyzes the user's speech, and the generation AI uses that data to learn the user's emotions and preferences. For example, the user's interests can be estimated based on the tone and speed of the voice. The preference learning unit also analyzes the user's facial expressions using a camera, and the generation AI uses that data to learn the user's emotions and preferences. For example, the user's preferences can be estimated based on smiling and surprised expressions. The preference learning unit also analyzes the user's voice and facial expressions simultaneously, and the generation AI uses that data to more accurately learn the user's emotions and preferences. For example, the user's interests can be estimated based on the degree of agreement between voice and facial expressions. In this way, by collecting information from voice and facial expressions, it is possible to learn preferences and needs with greater accuracy.

[0066] The preference learning unit uses the emotion estimation function to learn preferences and needs based on the user's emotions in real time and instantly reflect them. For example, if a user says, "Today is fun," the preference learning unit infers the user's emotions from that statement and suggests fun activities in real time. Also, if a user says, "I like this music," the preference learning unit infers the user's emotions from that statement and instantly recommends music in the same genre. Also, if a user says, "This movie moved me," the preference learning unit infers the user's emotions from that statement and instantly suggests moving movies in real time. In this way, the emotion estimation function allows preferences and needs to be learned in real time and instantly reflected.

[0067] The idea suggestion unit can estimate the user's emotions and provide idea suggestions and assistance according to the emotions. For example, if the user says, "I'm stressed today," the idea suggestion unit's generation AI estimates the user's emotions from the utterance and suggests relaxing yoga or meditation. Also, if the user says, "I'm tired," the idea suggestion unit estimates the user's emotions from the utterance and recommends relaxing music or movies. Also, if the user says, "I'm irritated," the idea suggestion unit estimates the user's emotions from the utterance and suggests relaxing activities or massages. In this way, by providing idea suggestions and assistance according to the user's emotions, user satisfaction is improved.

[0068] The idea suggestion unit can predict future needs based on the user's past behavioral data and preferences and proactively suggest ideas. For example, the idea suggestion unit analyzes data on past trips the user has taken, and the generation AI suggests the next travel destination based on that data. For example, it recommends new travel destinations based on the characteristics of places visited in the past. The idea suggestion unit also analyzes the user's past purchasing history, and the generation AI suggests products that are likely to be purchased next based on that data. For example, it recommends new products based on trends in products purchased in the past. The idea suggestion unit also analyzes the user's past behavioral data, and the generation AI predicts future needs based on that data. For example, it suggests the next event based on past event participation history. In this way, the user's convenience is improved by predicting future needs and proactively suggesting ideas.

[0069] The idea suggestion unit learns the user's lifestyle and daily routine, and based on that, can suggest ideas and provide assistance at the optimal timing. For example, the idea suggestion unit analyzes the user's daily schedule, and the generation AI suggests activities at the optimal timing based on that data. For example, it suggests activities that allow you to relax after work. The idea suggestion unit also analyzes the user's lifestyle data, and the generation AI recommends products at the optimal timing based on that data. For example, it suggests new coffee beans for your morning coffee. The idea suggestion unit also learns the user's daily routine, and the generation AI suggests events and activities at the optimal timing based on that data. For example, it suggests events when there are free weekend plans. This improves user convenience by making suggestions at the optimal timing based on the user's lifestyle and daily routine.

[0070] The idea suggestion unit can suggest ideas in different fields based on the user's preferences and needs. For example, if a user says, "I want to go on a trip," the generation AI infers the user's preferences from the statement and suggests travel destinations. For example, it recommends new travel destinations based on the characteristics of places visited in the past. If a user says, "I want to try a new dish," the generation AI infers the user's preferences from the statement and suggests new recipes. For example, it recommends new recipes based on the genre of dishes made in the past. If a user says, "I want to start a new hobby," the generation AI infers the user's preferences from the statement and suggests new hobbies. For example, it recommends new hobbies based on activities that the user has been interested in in the past. This allows the generation AI to suggest ideas in different fields and meet the diverse needs of users.

[0071] The idea suggestion unit can propose personalized study plans and training plans based on the user's preferences and needs. For example, if a user says, "I want to learn a new skill," the generation AI infers the user's preferences from the statement and proposes a personalized study plan. For example, it may recommend a new study plan based on skills learned in the past. If a user says, "I want to start fitness," the idea suggestion unit infers the user's preferences from the statement and proposes a personalized training plan. For example, it may recommend a new training plan based on past exercise history. If a user says, "I want to learn a language," the generation AI infers the user's preferences from the statement and proposes a personalized language study plan. For example, it may recommend a new language study plan based on languages ​​learned in the past. This allows the generation AI to propose personalized study plans and training plans that support the user's growth and health.

[0072] The idea suggestion unit uses the emotion estimation function to suggest ideas and provide assistance based on the user's emotions, thereby improving user satisfaction. For example, if a user says, "Today is fun," the idea suggestion unit's generation AI infers the user's emotions from the utterance and suggests fun activities. For example, it may recommend movies or events. Also, if a user says, "I like this music," the idea suggestion unit infers the user's emotions from the utterance and recommends music in the same genre. For example, it may create a playlist. Also, if a user says, "This movie moved me," the idea suggestion unit's generation AI infers the user's emotions from the utterance and suggests moving movies. For example, it may recommend works by the same director. In this way, the emotion estimation function can improve user satisfaction.

[0073] The generation AI Builder unit can estimate the user's emotions and suggest customization options based on the emotions. For example, if a user says, "I want to relax today," the generation AI Builder unit estimates the user's emotions from the utterance and sets a calm tone for the response. Also, if a user says, "I'm stressed," the generation AI Builder unit estimates the user's emotions from the utterance and suggests customization options that will help them relax. For example, playing calm music. Also, if a user says, "I'm tired," the generation AI Builder unit estimates the user's emotions from the utterance and suggests environmental settings that will help them relax. For example, dimming the lights. This makes it possible to improve user satisfaction by suggesting customization options based on emotions.

[0074] The generative AI Builder unit can learn the user's past customization history and suggest optimal customization options. For example, the generative AI Builder unit analyzes customization options set by the user in the past, and the generative AI Builder suggests optimal customization options based on that data. For example, it suggests new options based on the tone and language set in the past. The generative AI Builder unit also learns the user's past customization history, and the generative AI Builder suggests optimal customization options based on that data. For example, it suggests new options based on functions and tasks set in the past. The generative AI Builder unit also integrates the user's past customization history, and the generative AI Builder suggests optimal customization options based on that data. For example, it suggests new options based on environment settings set in the past. In this way, by learning past customization history, it is possible to suggest optimal customization options to the user.

[0075] The generation AI Builder unit can monitor user usage in real time and automatically update customization options based on usage frequency and patterns. For example, the generation AI Builder unit monitors user usage in real time, and the generation AI Builder automatically updates customization options based on that data. For example, it prioritizes displaying frequently used functions. The generation AI Builder unit also analyzes the user's usage frequency and patterns, and the generation AI Builder automatically updates customization options based on that data. For example, it automatically applies frequently used settings. The generation AI Builder unit also monitors user usage in real time, and the generation AI Builder automatically updates customization options based on that data. For example, it dynamically adjusts settings according to usage patterns. This makes it possible to automatically update customization options that are optimal for the user by monitoring usage in real time.

[0076] The Generative AI Builder unit provides customization options that support different languages ​​and cultures, making it possible to accommodate global users. For example, the Generative AI Builder unit provides customization options that support different languages, allowing users to configure the Generative AI in their own language. For example, it supports English, Japanese, French, etc. The Generative AI Builder unit also provides customization options that support different cultures, making it possible for users to configure the Generative AI that suits their own culture. For example, it provides settings that suit cultural customs and preferences. The Generative AI Builder unit also provides customization options that support different languages ​​and cultures, making it possible to accommodate global users. For example, it provides settings that suit the characteristics of each region. This makes it possible to accommodate global users by supporting different languages ​​and cultures.

[0077] The generation AI Builder unit can suggest personalized entertainment content based on the user's preferences and needs. For example, the generation AI Builder unit analyzes the user's preferences and needs, and the generation AI Builder suggests personalized music based on that data. For example, the generation AI Builder creates a playlist based on the user's favorite genres and artists. The generation AI Builder unit also analyzes the user's preferences and needs, and the generation AI Builder suggests personalized movies based on that data. For example, the generation AI Builder recommends movies based on the user's favorite genres and directors. The generation AI Builder unit also analyzes the user's preferences and needs, and the generation AI Builder suggests personalized entertainment content based on that data. For example, the generation AI Builder recommends TV programs and podcasts that the user likes. This makes it possible to improve user satisfaction by suggesting personalized entertainment content.

[0078] The Generative AI Builder unit uses the emotion estimation function to suggest customization options in real time based on the user's emotions, improving the user experience. For example, if a user says, "I'm having fun today," the Generative AI Builder unit infers the user's emotions from that statement and suggests fun customization options. For example, it could set a bright tone for the response. Also, if a user says, "I'm stressed," the Generative AI Builder unit infers the user's emotions from that statement and suggests relaxing customization options. For example, it could play calming music. Also, if a user says, "I'm tired," the Generative AI Builder unit infers the user's emotions from that statement and suggests relaxing environmental settings. For example, it could dim the lights. In this way, the emotion estimation function can be used to improve the user experience.

[0079] The customer support department can infer a customer's emotions and respond accordingly. For example, if a customer says, "I'm dissatisfied with this product," the generation AI can infer the customer's emotions from that statement and provide a prompt and courteous response. For example, it can suggest specific steps to resolve the problem. If a customer says, "The support is slow," the generation AI can infer the customer's emotions from that statement and provide a prompt response. For example, it can escalate the issue to the support team as a priority. If a customer says, "I'm not satisfied with this service," the generation AI can infer the customer's emotions from that statement and provide a courteous response. For example, it can suggest additional support options. This makes it possible to improve customer satisfaction by responding according to the customer's emotions.

[0080] The customer support department can learn from past inquiry data and propose the most effective solution. For example, the customer support department analyzes past inquiry data and the generation AI proposes the most effective solution based on that data. For example, it makes a new proposal based on solutions to similar problems. The customer support department can also learn from customers' past inquiry history and the generation AI proposes the most effective solution based on that data. For example, it makes a new proposal based on past solutions. The customer support department can also integrate past inquiry data and the generation AI proposes the most effective solution based on that data. For example, it makes a new proposal based on solutions to similar problems. In this way, by learning from past inquiry data, it can propose the most effective solution.

[0081] The customer support department can analyze a customer's purchasing history and preferences to provide personalized support. For example, the customer support department analyzes a customer's purchasing history, and the generation AI provides personalized support based on that data. For example, it suggests how to use a purchased product or troubleshooting. The customer support department can also analyze a customer's preferences, and the generation AI provides personalized support based on that data. For example, it responds based on the customer's preferred support method. The customer support department can also integrate a customer's purchasing history and preferences, and the generation AI provides personalized support based on that data. For example, it suggests how to use a purchased product or troubleshooting. In this way, personalized support can be provided by analyzing a customer's purchasing history and preferences.

[0082] The customer support department can integrate customer support from different channels to provide a consistent support experience. For example, the generation AI can integrate support data from different channels, such as telephone, email, and chat, to provide a consistent support experience. For example, the same information can be provided regardless of which channel a customer uses. The customer support department can also integrate support history from different channels, and the generation AI can use that data to provide a consistent support experience. For example, it can respond based on the content of past inquiries. The customer support department can also integrate support data from different channels in real time to provide a consistent support experience. For example, the same information can be provided regardless of which channel a customer uses. This makes it possible to provide a consistent support experience by integrating support from different channels.

[0083] The customer support department can suggest related products and services based on the customer's preferences and needs. For example, the customer support department analyzes the customer's preferences and needs, and the generation AI suggests related products and services based on that data. For example, it recommends products related to products purchased in the past. The customer support department can also analyze the customer's preferences and needs, and the generation AI suggests related services based on that data. For example, it recommends services related to services used in the past. The customer support department can also analyze the customer's preferences and needs, and the generation AI suggests related products and services based on that data. For example, it recommends products related to products purchased in the past. In this way, customer satisfaction can be improved by suggesting related products and services based on the customer's preferences and needs.

[0084] The customer support department can use the emotion estimation function to provide support that corresponds to the customer's emotions in real time, thereby improving customer satisfaction. For example, if a customer says, "I'm dissatisfied with this product," the generation AI can infer the customer's emotions from that statement and provide a prompt and courteous response, such as suggesting specific steps to resolve the issue. Similarly, if a customer says, "The support is slow," the generation AI can infer the customer's emotions from that statement and provide a prompt response, such as escalating the issue to the support team as a priority. Similarly, if a customer says, "I'm not satisfied with this service," the generation AI can infer the customer's emotions from that statement and provide a courteous response, such as suggesting additional support options. In this way, the emotion estimation function can improve customer satisfaction.

[0085] The product recommendation unit can infer the user's emotions and recommend products that correspond to those emotions. For example, if a user says, "I'm happy today," the generation AI infers the user's emotions from that statement and suggests products that would make a suitable gift. For example, it could recommend a gift card or a bouquet of flowers. Also, if a user says, "I like this product," the generation AI infers the user's emotions from that statement and recommends other products from the same brand. For example, it could suggest items from the same series. Also, if a user says, "This movie moved me," the generation AI infers the user's emotions from that statement and suggests related products. For example, it could recommend the movie soundtrack or related goods. This can increase purchasing motivation by recommending products that correspond to the user's emotions.

[0086] The product recommendation unit can analyze a user's purchasing history and preferences and recommend the most relevant products. For example, the product recommendation unit analyzes a user's purchasing history and the generation AI recommends the most relevant products based on that data. For example, it suggests products related to products purchased in the past. The product recommendation unit also analyzes a user's preferences and the generation AI recommends the most relevant products based on that data. For example, it suggests products from brands or categories that the user likes. The product recommendation unit also integrates a user's purchasing history and preferences and the generation AI recommends the most relevant products based on that data. For example, it suggests new products based on reviews of products purchased in the past. In this way, the most relevant products can be recommended by analyzing a user's purchasing history and preferences.

[0087] The product recommendation unit can learn the user's lifestyle and daily routine and recommend the most suitable products based on that. For example, the product recommendation unit analyzes the user's lifestyle data, and the generation AI recommends the most suitable products based on that data. For example, if the user is health-conscious, health foods and fitness goods are suggested. The product recommendation unit also learns the user's daily routine, and the generation AI recommends the most suitable products based on that data. For example, if the user has the habit of drinking coffee every morning, new coffee beans are suggested. The product recommendation unit also integrates the user's lifestyle and daily routine, and the generation AI recommends the most suitable products based on that data. For example, if the user likes the outdoors, camping equipment is suggested. This makes it possible to improve user satisfaction by recommending the most suitable products based on the user's lifestyle and daily routine.

[0088] The product recommendation unit can recommend products in different categories. For example, if a user says, "I'm looking for new clothes," the generation AI infers the user's preferences from that statement and recommends products in the fashion category. For example, it would suggest clothes in the style the user prefers. Also, if a user says, "I want a new home appliance," the generation AI infers the user's preferences from that statement and recommends products in the home appliance category. For example, it would suggest home appliances with the functions the user needs. Also, if a user says, "I want to try a new recipe," the product recommendation unit infers the user's preferences from that statement and recommends products in the food category. For example, it would suggest recipes using ingredients the user likes. This allows the system to meet the diverse needs of users by recommending products in different categories.

[0089] The product recommendation unit can provide a personalized gift guide based on the user's preferences and needs. For example, the product recommendation unit analyzes the user's preferences and needs, and the generation AI provides a personalized gift guide based on that data. For example, it suggests products from brands or categories that the user likes. The product recommendation unit also analyzes the user's past purchasing history, and the generation AI provides a personalized gift guide based on that data. For example, it suggests products related to products purchased in the past. The product recommendation unit also integrates the user's preferences and needs, and the generation AI provides a personalized gift guide based on that data. For example, it suggests products in a style or theme that the user likes. This makes it possible to improve user satisfaction by providing a personalized gift guide based on the user's preferences and needs.

[0090] The product recommendation unit uses the emotion estimation function to recommend products in real time based on the user's emotions, increasing purchasing motivation. For example, if a user says, "I'm happy today," the generation AI infers the user's emotions from that statement and suggests products suitable for gifts. For example, it could recommend a gift card or a bouquet of flowers. Also, if a user says, "I like this product," the generation AI infers the user's emotions from that statement and recommends other products from the same brand. For example, it could suggest items from the same series. Also, if a user says, "This movie moved me," the generation AI infers the user's emotions from that statement and suggests related products. For example, it could recommend the movie soundtrack or related goods. In this way, the emotion estimation function can increase the user's purchasing motivation.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The generative AI system can also be equipped with a health management unit that monitors the user's health status and provides health advice. For example, the health management unit collects the user's heart rate and sleep data, and the generative AI analyzes the user's health status based on that data. If the user says, "I've been feeling tired lately," the generative AI will provide appropriate rest and exercise advice based on that statement and the collected data. The health management unit also collects the user's dietary data, and the generative AI analyzes nutritional balance based on that data. If the user says, "I want to start a diet," the generative AI will suggest an appropriate meal plan based on that statement and the collected data. This allows the system to monitor the user's health status and provide health advice, thereby supporting the user's health management.

[0093] The generative AI system can also include a learning support unit that provides learning content based on the user's hobbies and interests. For example, if a user says, "I want to learn a new skill," the learning support unit analyzes the user's statement and suggests appropriate online courses and learning materials. The learning support unit also analyzes the user's past learning history, and the generative AI uses that data to propose a learning plan tailored to the user. If a user says, "I want to learn programming," the generative AI will suggest an appropriate programming course based on the user's statement and past learning history. This can increase the user's motivation to learn by providing learning content based on the user's hobbies and interests.

[0094] The generative AI system can also be equipped with a relaxation unit that infers the user's emotions and suggests relaxation methods according to the emotions. For example, if a user says, "I'm stressed today," the relaxation unit infers the user's emotions from the user's utterance and suggests relaxing music or meditation guides. Alternatively, if a user says, "I'm tired," the relaxation unit infers the user's emotions from the user's utterance and suggests relaxing aromatherapy or massage methods. In this way, by suggesting relaxation methods according to the user's emotions, the system can reduce the user's stress and promote relaxation.

[0095] The generative AI system can also include an entertainment unit that infers the user's emotions and provides entertainment content according to those emotions. For example, if a user says, "Today is fun," the generative AI infers the user's emotions from that statement and suggests fun movies or games. Similarly, if a user says, "I like this music," the generative AI infers the user's emotions from that statement and recommends music in the same genre. This can improve user satisfaction by providing entertainment content according to the user's emotions.

[0096] The generative AI system can also include a fitness section that estimates the user's emotions and suggests a fitness plan based on those emotions. For example, if a user says, "I feel good today," the fitness section estimates the user's emotions from that statement and suggests an energetic exercise plan. Alternatively, if a user says, "I'm tired," the fitness section estimates the user's emotions from that statement and suggests a relaxing stretching or yoga plan. This allows the system to support the user's health by suggesting a fitness plan based on the user's emotions.

[0097] The generative AI system can also be equipped with a purchasing support unit that analyzes a user's purchasing history and suggests new products based on their purchasing patterns. For example, the purchasing support unit analyzes data on products the user has previously purchased, and the generative AI uses that data to suggest new products. If a user says, "I'm looking for a new book," the generative AI recommends an appropriate book based on that statement and their past purchasing history. The purchasing support unit also analyzes the user's purchasing patterns, and the generative AI uses that data to suggest products that the user might be interested in. This improves the user's purchasing experience by suggesting new products based on the user's purchasing history and patterns.

[0098] The generative AI system may further include a social network unit that analyzes the user's social network and suggests new content based on the preferences of friends and followers. For example, the social network unit analyzes content shared by the user's friends, and the generative AI uses that data to suggest content relevant to the user. If a user says, "I want to see a new movie," the generative AI recommends an appropriate movie based on that statement and the preferences of their friends. The social network unit may also analyze products purchased by the user's followers, and the generative AI uses that data to suggest products relevant to the user. This can improve user satisfaction by suggesting new content based on the user's social network.

[0099] The generative AI system can also include a lifestyle section that analyzes the user's lifestyle data and suggests new activities based on the user's lifestyle. For example, the lifestyle section analyzes the user's daily schedule, and the generative AI suggests optimal activities based on that data. If the user says, "I'm not sure what to do this weekend," the generative AI suggests appropriate activities based on that statement and the schedule data. The lifestyle section also analyzes the user's lifestyle data, and the generative AI uses that data to suggest events and activities that the user might be interested in. This can improve user satisfaction by suggesting new activities based on the user's lifestyle.

[0100] The generative AI system can also be equipped with a prediction unit that analyzes the user's past behavioral data, predicts future needs, and makes proactive suggestions. For example, the prediction unit analyzes data from the user's past trips, and the generative AI uses that data to suggest the next travel destination. If the user says, "I want to decide on my next travel destination," the generative AI will recommend an appropriate destination based on that statement and past travel data. The prediction unit also analyzes the user's past purchasing history, and the generative AI uses that data to suggest products that the user is likely to purchase next. This improves user convenience by predicting future needs and making proactive suggestions.

[0101] The generative AI system can also be equipped with a learning support unit that infers the user's emotions and proposes a study plan based on those emotions. For example, if a user says, "I can concentrate today," the learning support unit infers the user's emotions from that statement and proposes a study plan that will help them concentrate. Also, if a user says, "I'm tired," the learning support unit infers the user's emotions from that statement and proposes a study plan that will help them relax. This makes it possible to improve the user's learning efficiency by proposing a study plan that is based on the user's emotions.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The preference learning unit automatically learns the user's preferences and needs through interactions with the user. For example, the preference learning unit collects user utterances and behavioral data, and the generation AI learns the user's preferences and needs based on that data. The generation AI analyzes the user's utterances and behavioral data using machine learning algorithms and deep learning techniques to identify the user's preferences and needs. The generation AI can also predict preferences and needs based on the user's past behavioral data. Step 2: The idea suggestion unit actively suggests ideas based on the user's preferences and needs learned by the preference learning unit. For example, if a user says, "I'm not sure what to do this weekend," the generation AI will suggest appropriate activities and events based on the user's past behavioral data and preferences. Also, if a user says, "I'm looking for a new product," the generation AI will recommend products that match the user's preferences. Step 3: Generative AI The Builder section provides functions for users to build their own generative AI. For example, if a user prefers a specific language or tone, they can reflect that preference in the generative AI. Users can also add specific tasks or functions.

[0104] 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.

[0105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0106] 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.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] 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.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0133] 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.

[0134] 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.

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

[0136] 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.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0148] In the robot 414, 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 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 processing similar to that of the specific processing unit 290 using these models.

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

[0150] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0152] The data processing system 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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."

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0170] 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. [Explanation of symbols]

[0171] 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 preference learning unit that automatically learns user preferences and needs through interactions with the user; an idea suggestion unit that actively suggests ideas based on the preferences and needs of the user learned by the preference learning unit; A Generative AI Builder section that allows users to build their own unique Generative AI. A system characterized by:

2. The preference learning unit Based on user comments and behavioral data, generative AI infers user emotions and learns preferences and needs based on those emotions.

2. The system of claim 1.

3. The preference learning unit Analyze users' past purchase and browsing history to learn more accurately their preferences and needs.

2. The system of claim 1.

4. The preference learning unit Learning mutual influences by taking into account the preferences of users' social networks 2. The system of claim 1.

5. The preference learning unit Learned preferences and needs are shared across devices to provide a seamless user experience.

2. The system of claim 1.

Images