System

Abstract

An object of a system according to an embodiment is to personalize information on the basis of a use record of a user and achieve monetization.SOLUTION: A system according to an embodiment includes a generation AI app, a trend analyzer, a personalization unit, and a monetization unit. The generation AI application analyzes the use result of the user and analyzes the tendency. A tendency analyzing part analyzes the use result of the user by the generation AI application, and analyzes the tendency. The personalization unit personalizes the information based on the trend analyzed by the trend analysis unit. The monetization unit provides the information personalized by the personalization unit for monetization.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 that they do not adequately personalize and monetize information based on users' usage history.

[0005] The system according to the embodiment aims to personalize information based on the user's usage history and to generate profits. [Means for solving the problem]

[0006] The system according to the embodiment includes a generating AI app, a trend analysis unit, a personalization unit, and a monetization unit. The generating AI app analyzes a user's usage history and analyzes trends. The trend analysis unit analyzes a user's usage history using the generating AI app and analyzes trends. The personalization unit personalizes information based on the trends analyzed by the trend analysis unit. The monetization unit provides the information personalized by the personalization unit and monetizes it. [Effects of the Invention]

[0007] The system according to the embodiment can personalize information based on the user's usage history and generate revenue. [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) An information provision system according to an embodiment of the present invention promotes high-quality decision-making and personal growth, leading to a fulfilling life. This system uses a generative AI app to provide and output summaries, translations, comparisons, reviews, and related information to users. This allows the information provision system to efficiently obtain the information users need and enable better decision-making.

[0029] An information provision system according to an embodiment includes a generating AI app, a trend analysis unit, a personalization unit, and a monetization unit. The generating AI app analyzes information input by a user and summarizes, translates, compares, reviews, provides related information, and outputs the necessary information. For example, if a user wants to know information about a specific product, the generating AI app provides summary information about the product and displays comparisons with other products and reviews. The generating AI app also provides links to related information. The trend analysis unit analyzes the user's usage history and analyzes trends using the generating AI app. For example, the trend analysis unit suggests new related information or products based on information the user has previously searched for or products they have purchased. The personalization unit personalizes information based on the trends analyzed by the trend analysis unit. For example, the personalization unit provides customized information based on the user's preferences. The monetization unit provides the information personalized by the personalization unit and monetizes it. For example, the monetization unit employs a revenue model such as a service usage fee or revenue share to monetize the information. As a result, the information provision system according to an embodiment can personalize information based on the user's usage history and monetize it.

[0030] Generative AI apps can analyze a user's past behavioral history, predict future behavior, and provide information in advance. For example, generative AI apps analyze a user's past search history and browsing history to predict future behavior. For example, they can provide the latest information related to topics the user frequently searches for in advance. Generative AI apps can also analyze a user's behavioral patterns to predict and provide information that will be needed at specific times of the day. For example, they can provide news during the morning commute and relaxing content in the evening. Generative AI apps can also predict future purchasing behavior based on a user's past purchase history and suggest related products and services in advance. For example, they can remind the user to purchase products that they regularly purchase. This makes it possible to predict future behavior based on a user's past behavioral history and provide information in advance.

[0031] A generative AI app can work in conjunction with a wearable device to optimize the information provided based on the user's biometric information. For example, a generative AI app can work in conjunction with a smartwatch to optimize the information provided based on the user's heart rate and stress level. For example, if the heart rate is high, it can provide information to help the user relax. The generative AI app can also analyze the biometric information obtained from the wearable device to provide information according to the user's health condition. For example, it can provide nutritional information after exercise. The generative AI app can also work in conjunction with a wearable device to analyze the user's sleep patterns and determine the optimal timing for providing information. For example, it can provide news immediately after waking up. This allows the app to work in conjunction with a wearable device to optimize the information provided based on the user's biometric information.

[0032] Generative AI apps can be applied in the field of education to provide customized learning materials according to students' learning progress. For example, generative AI apps can be linked to educational platforms to analyze students' learning progress in real time and provide individually customized learning materials. For example, they can provide practice questions that focus on areas of weakness. Generative AI apps can also generate and provide optimal learning plans based on students' past learning history. For example, they can suggest content that students should focus on studying before an exam. Generative AI apps can also analyze students' learning style and pace and provide learning materials accordingly. For example, they can provide visual learning materials to students who are good at visual learning. This allows generative AI apps to be applied in the field of education to provide customized learning materials according to students' learning progress.

[0033] The trend analysis unit can analyze a user's behavioral patterns, predict future behavior, and provide information in advance. The trend analysis unit, for example, analyzes a user's past search history and browsing history to predict future behavior. For example, it can provide the latest information related to topics that the user frequently searches for in advance. The trend analysis unit can also analyze a user's behavioral patterns to predict and provide information that will be needed at specific times of the day. For example, it can provide news during the morning commute and relaxing content in the evening. The trend analysis unit can also predict future purchasing behavior based on the user's past purchase history and suggest related products and services in advance. For example, it can remind the user of products that are regularly purchased. This makes it possible to predict future behavior based on a user's behavioral patterns and provide information in advance.

[0034] The trend analysis unit can consider applications in different industries or fields based on the results of the user trend analysis. The trend analysis unit, for example, considers applications in different industries based on the results of the user trend analysis. For example, in the education field, providing customized teaching materials according to learning progress. The trend analysis unit also considers applications in different fields based on the results of the user trend analysis. For example, in the medical field, providing customized treatment plans according to the patient's health condition. The trend analysis unit also considers applications in different industries or fields based on the results of the user trend analysis. For example, in the marketing field, providing customized advertisements according to consumer purchasing behavior. This makes it possible to consider applications in different industries or fields based on the results of the user trend analysis.

[0035] The trend analysis unit can provide personalized advertisements based on the results of the user's trend analysis. The trend analysis unit provides personalized advertisements based on the results of the user's trend analysis, for example. For example, advertisements related to products that the user has searched for in the past are displayed. The trend analysis unit also provides personalized advertisements based on the user's purchasing history. For example, advertisements related to products that the user frequently purchases are displayed. The trend analysis unit also analyzes the user's behavioral patterns and provides personalized advertisements. For example, advertisements related to topics that the user is interested in during a specific time period are displayed. In this way, personalized advertisements can be provided based on the results of the user's trend analysis.

[0036] The monetization unit can analyze a user's behavior history within the app and display advertisements at the optimal timing. For example, the monetization unit analyzes a user's behavior history within the app and displays advertisements at the optimal timing. For example, if a user is active during a specific time period, advertisements are displayed during that time period. The monetization unit also analyzes a user's behavior patterns and optimizes the timing of advertisement display. For example, advertisements are displayed immediately after a function that the user frequently uses. The monetization unit also dynamically adjusts the timing of advertisement display based on the user's past behavior history. For example, advertisements are displayed after the user completes a specific action. This allows advertisements to be displayed at the optimal timing based on the user's behavior history within the app.

[0037] The monetization unit can deploy the app to different platforms. For example, the monetization unit deploys the generated AI app to a smart speaker to provide information via voice commands. For example, when a user asks a question by voice, the generated AI app provides summary information. The monetization unit also deploys the generated AI app to a smart TV to display information on a large screen. For example, when a user operates the remote control, the generated AI app displays related information. The monetization unit also deploys the generated AI app to different platforms so that users can access it from any device. For example, it can be used on smartphones, tablets, PCs, etc. This allows the app to be deployed to different platforms.

[0038] The monetization department can apply the app to different industries and monetize it. For example, the monetization department can apply the generative AI app to the medical field to provide information based on a patient's health condition. For example, it can provide regular health checks and medication reminders. The monetization department can also apply the generative AI app to the education field to provide customized learning materials based on a student's learning progress. For example, it can provide practice questions specialized in weak areas. The monetization department can also apply the generative AI app to different industries and monetize it. For example, it can provide customized advertisements based on consumer purchasing behavior in the marketing field. This allows the app to be applied to different industries and monetized.

[0039] The generative AI app has a summarization function and can compare summarized information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generative AI app compares summarized information with the user's past search history and provides highly relevant information preferentially. For example, it provides summary information related to topics the user has previously searched for. The generative AI app also provides highly relevant summary information preferentially based on the user's past browsing history. For example, it provides summary information related to categories that the user frequently browses. The generative AI app also compares summarized information with the user's past behavioral history and provides highly relevant information preferentially. For example, it provides summary information related to products the user has previously purchased. This allows the generative AI app to compare summarized information with the user's past behavioral history and provide highly relevant information preferentially.

[0040] The generative AI app has a summarization function, and can support different languages ​​and obtain feedback from an international perspective. For example, the generative AI app can support different languages ​​and collect feedback from an international perspective. For example, it can translate into multiple languages ​​such as English, French, and Chinese. The generative AI app also builds a system that posts the translated summary information on a multilingual platform and obtains feedback from users around the world. The generative AI app can also collect advice and suggestions for improvement from an international perspective based on the summary information translated into different languages, improving the quality of the summaries. For example, it can reflect feedback that takes cultural and market differences into account. This allows the summarization function to support different languages ​​and obtain feedback from an international perspective.

[0041] Generative AI apps have a summarization function and can convert summarized information into visual notes or mind maps to make it easier to understand visually. For example, generative AI apps can convert summarized information into visual notes to visually display the main points of an idea. For example, they can indicate important points using diagrams or icons. Generative AI apps can also convert summarized information into mind map format to visually organize related keywords and concepts. This allows users to understand the overall picture of the information at a glance. Generative AI apps can also develop tools that automatically generate visual notes and mind maps to enable users to easily display summarized information visually. For example, they can provide a function to visualize summarized information using drag and drop. This allows summarized information to be converted into visual notes or mind maps to make it easier to understand visually.

[0042] The generative AI app has a translation function and can compare translated information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generative AI app compares translated information with the user's past search history and provides highly relevant information preferentially. For example, it provides translated information related to topics the user has previously searched for. The generative AI app also provides highly relevant translated information preferentially based on the user's past browsing history. For example, it provides translated information related to categories that the user frequently browses. The generative AI app also compares translated information with the user's past behavioral history and provides highly relevant information preferentially. For example, it provides translated information related to products the user has previously purchased. This allows the generative AI app to compare translated information with the user's past behavioral history and provide highly relevant information preferentially.

[0043] The generative AI app has a translation function and can support different languages ​​to obtain feedback from an international perspective. The generative AI app, for example, supports different languages ​​and collects feedback from an international perspective. For example, it translates into multiple languages ​​such as English, French, and Chinese. The generative AI app also builds a system that posts translated information on a multilingual platform and obtains feedback from users around the world. The generative AI app also collects advice and suggestions for improvement from an international perspective based on the information translated into different languages, improving the quality of the translation. For example, it reflects feedback that takes cultural and market differences into account. This allows the translation function to support different languages ​​and obtain feedback from an international perspective.

[0044] Generative AI apps have translation functions and can convert translated information into visual notes or mind maps, making it easier to understand visually. For example, generative AI apps can convert translated information into visual notes to visually display the key points of an idea. For example, they can indicate important points with diagrams or icons. Generative AI apps can also convert translated information into mind maps, visually organizing related keywords and concepts. This allows users to understand the overall picture of the information at a glance. Generative AI apps can also develop tools that automatically generate visual notes and mind maps, allowing users to easily display translated information visually. For example, they can provide a function to visualize translated information with drag and drop. This allows translated information to be converted into visual notes or mind maps, making it easier to understand visually.

[0045] The generative AI app has a comparison function and can compare the compared information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generative AI app compares the compared information with the user's past search history and provides highly relevant information preferentially. For example, it provides comparative information related to products the user has searched for in the past. The generative AI app also provides highly relevant comparative information preferentially based on the user's past browsing history. For example, it provides comparative information related to categories that the user frequently browses. The generative AI app also compares the compared information with the user's past behavioral history and provides highly relevant information preferentially. For example, it provides comparative information related to products the user has purchased in the past. This allows the generative AI app to compare the compared information with the user's past behavioral history and provide highly relevant information preferentially.

[0046] A generative AI app has a comparison function, and can apply the comparison function to different industries or applications to discover new market needs. For example, a generative AI app can apply the comparison function to different industries to discover new market needs. For example, in the medical field, it can compare treatments and recommend the most suitable treatment. A generative AI app can also apply the comparison function to different applications to discover new market needs. For example, in the education field, it can compare teaching materials and recommend the most suitable teaching materials. A generative AI app can also apply the comparison function to different industries and applications to discover new market needs. For example, in the travel field, it can compare tour packages and recommend the most suitable tour. In this way, the comparison function can be applied to different industries and applications to discover new market needs.

[0047] Generative AI apps have a comparison function and can convert the compared information into visual notes or mind maps, making it easier to understand visually. For example, generative AI apps can convert the compared information into visual notes and visually display the main points of an idea. For example, they can indicate important points with diagrams or icons. Generative AI apps can also convert the compared information into mind map format and visually organize related keywords and concepts. This allows users to understand the overall picture of the information at a glance. Generative AI apps can also develop tools that automatically generate visual notes and mind maps, allowing users to easily display comparative information visually. For example, they can provide a function to visualize comparative information with drag and drop. This allows the compared information to be converted into visual notes or mind maps, making it easier to understand visually.

[0048] The generation AI app has a function for providing reputation information, and can compare the reputation information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generation AI app compares the reputation information with the user's past search history and provides highly relevant information preferentially. For example, it provides reputation information related to products that the user has searched for in the past. The generation AI app also provides highly relevant reputation information preferentially based on the user's past browsing history. For example, it provides reputation information related to categories that the user frequently browses. The generation AI app also compares the reputation information with the user's past behavioral history and provides highly relevant information preferentially. For example, it provides reputation information related to products that the user has purchased in the past. This allows the generation AI app to compare the reputation information with the user's past behavioral history and provide highly relevant information preferentially.

[0049] The generative AI app has a function for providing reputation information, and can apply the reputation information to different industries or applications to discover new market needs. For example, the generative AI app applies reputation information to different industries to discover new market needs. For example, in the medical field, it collects reputations of treatments and suggests the most suitable treatment. The generative AI app also applies reputation information to different applications to discover new market needs. For example, in the education field, it collects reputations of teaching materials and suggests the most suitable teaching materials. The generative AI app also applies reputation information to different industries and applications to discover new market needs. For example, in the travel field, it collects reputations of tour packages and suggests the most suitable tour. In this way, reputation information can be applied to different industries and applications to discover new market needs.

[0050] The generative AI app has a function for providing reputation information and can convert it into visual notes or mind maps to make it easier to understand visually. For example, the generative AI app converts reputation information into visual notes to visually display the key points of an idea. For example, it can show important points using diagrams or icons. The generative AI app can also convert reputation information into mind map format to visually organize related keywords and concepts. This allows users to understand the overall picture of the information at a glance. The generative AI app also develops tools that automatically generate visual notes and mind maps, allowing users to easily display reputation information visually. For example, it provides a function for visualizing reputation information using drag and drop. This allows reputation information to be converted into visual notes or mind maps to make it easier to understand visually.

[0051] The generative AI app has a function for providing related information, and can compare related information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generative AI app compares related information with the user's past search history and provides highly relevant information preferentially. For example, it provides information related to topics that the user has previously searched for. The generative AI app also provides highly relevant information preferentially based on the user's past browsing history. For example, it provides information related to categories that the user frequently browses. The generative AI app also compares related information with the user's past behavioral history and provides highly relevant information preferentially. For example, it provides information related to products that the user has previously purchased. This allows the generative AI app to compare related information with the user's past behavioral history and provide highly relevant information preferentially.

[0052] A generative AI app has the function of providing related information and can apply it to different industries or applications to discover new market needs. For example, a generative AI app can apply related information to different industries to discover new market needs. For example, in the medical field, it can collect related information on treatments and recommend the most appropriate treatment. A generative AI app can also apply related information to different applications to discover new market needs. For example, in the education field, it can collect related information on teaching materials and recommend the most appropriate teaching materials. A generative AI app can also apply related information to different industries and applications to discover new market needs. For example, in the travel field, it can collect related information on tour packages and recommend the most appropriate tour. This allows related information to be applied to different industries and applications to discover new market needs.

[0053] Generative AI apps have the ability to provide related information and convert it into visual notes or mind maps, making it easier to understand visually. For example, generative AI apps convert related information into visual notes to visually display the key points of an idea. For example, they may indicate important points using diagrams or icons. Generative AI apps also convert related information into mind map format, visually organizing related keywords and concepts. This allows users to understand the overall picture of the information at a glance. Generative AI apps also develop tools that automatically generate visual notes and mind maps, allowing users to easily display related information visually. For example, they provide a function to visualize related information using drag and drop. This allows related information to be converted into visual notes or mind maps, making it easier to understand visually.

[0054] The generative AI app has an output function and can compare the output information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generative AI app can compare the output information with the user's past search history and provide highly relevant information preferentially. For example, it can provide information related to topics the user has previously searched for. The generative AI app can also provide highly relevant information preferentially based on the user's past browsing history. For example, it can provide information related to categories that the user frequently browses. The generative AI app can also compare the output information with the user's past behavioral history and provide highly relevant information preferentially. For example, it can provide information related to products the user has previously purchased. This allows the generative AI app to compare the output information with the user's past behavioral history and provide highly relevant information preferentially.

[0055] Generative AI apps have output functions and can support different formats. For example, generative AI apps can support visual notes as output functions to visually display the main points of information. For example, they can show important points using diagrams or icons. Generative AI apps can also support mind map formats as output functions to visually organize related keywords and concepts. This allows users to understand the overall picture of the information at a glance. Generative AI apps can also develop tools that automatically generate visual notes and mind maps, allowing users to easily display output information visually. For example, they can provide a function to visualize output information using drag and drop. This allows the output function to support different formats.

[0056] A generative AI app has an output function and can adapt the output information to different devices. For example, a generative AI app can adapt its output function to a smart speaker, providing information via voice commands. For example, when a user asks a question by voice, the generative AI app can provide summary information. A generative AI app can also adapt its output function to a smart TV, displaying information on a large screen. For example, when a user operates the remote control, the generative AI app displays related information. A generative AI app can also adapt its output function to different devices, allowing users to access it from any device. For example, it can be used on smartphones, tablets, PCs, etc. This allows the output information to be adapted to different devices.

[0057] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0058] Information provision systems can predict future behavior based on a user's behavioral history and provide information in advance. For example, they can provide the latest information related to topics the user has previously searched for in advance. They can also analyze a user's behavioral patterns and predict and provide the information they will need at specific times of the day. For example, they can provide news during the morning commute and relaxing content in the evening. They can also predict future purchasing behavior based on a user's past purchase history and suggest related products and services in advance. For example, they can remind users of products they regularly purchase. This makes it possible to predict future behavior based on a user's past behavioral history and provide information in advance.

[0059] The information provision system can work in conjunction with wearable devices to optimize the information provided based on the user's biometric information. For example, by working in conjunction with a smartwatch, the information provided can be optimized based on the user's heart rate and stress level. If the heart rate is high, information to help relax can be provided. The biometric information obtained from the wearable device can also be analyzed to provide information according to the user's health condition. Nutritional information can be provided after exercise. The information provision system can also work in conjunction with a wearable device to analyze the user's sleep patterns and determine the optimal timing for providing information. News can be provided immediately after waking up. In this way, the information provided can be optimized based on the user's biometric information by working in conjunction with a wearable device.

[0060] Information provision systems can be applied to the field of education to provide customized learning materials according to students' learning progress. For example, by linking with an educational platform, students' learning progress can be analyzed in real time and individually customized learning materials can be provided. Practice questions specific to weak areas can be provided. An optimal learning plan can also be generated and provided based on the student's past learning history. Content that should be focused on before an exam can be suggested. A student's learning style and pace can also be analyzed and learning materials can be provided accordingly. Visual learning materials can be provided to students who are good at visual learning. This allows the system to be applied to the field of education to provide customized learning materials according to students' learning progress.

[0061] Information provision systems can analyze user behavior patterns, predict future behavior, and provide information in advance. For example, they can analyze a user's past search history and browsing history to predict future behavior. They can provide the latest information related to topics that the user frequently searches for in advance. They can also analyze a user's behavior patterns to predict and provide information that will be needed at specific times of the day. They can provide news during the morning commute and relaxing content in the evening. They can also predict future purchasing behavior based on the user's past purchase history and suggest related products and services in advance. They can also remind the user of products that are regularly purchased. This makes it possible to predict future behavior based on a user's behavior patterns and provide information in advance.

[0062] The information provision system can consider applications in different industries or fields based on the results of a user trend analysis. For example, applications in different industries can be considered based on the results of a user trend analysis. In the education field, customized teaching materials can be provided according to learning progress. Applications in different fields can also be considered based on the results of a user trend analysis. In the medical field, customized treatment plans can be provided according to the patient's health condition. Applications in different industries or fields can also be considered based on the results of a user trend analysis. In the marketing field, customized advertisements can be provided according to consumer purchasing behavior. This allows applications in different industries or fields to be considered based on the results of a user trend analysis.

[0063] The information provision system can provide personalized advertisements based on the results of a user's trend analysis. For example, personalized advertisements are provided based on the results of a user's trend analysis. Advertisements related to products that the user has searched for in the past are displayed. Personalized advertisements are also provided based on the user's purchasing history. Advertisements related to products that the user frequently purchases are displayed. Personalized advertisements are also provided by analyzing the user's behavioral patterns. Advertisements related to topics that the user is interested in during specific time periods are displayed. This makes it possible to provide personalized advertisements based on the results of a user's trend analysis.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The AI ​​app analyzes the information entered by the user and summarizes, translates, compares, provides reviews, and provides related information, and outputs the necessary information. For example, if a user wants to know about a specific product, it will provide summary information about that product, compare it with other products, and display reviews. It will also provide links to related information. Step 2: The trend analysis unit analyzes the user's usage history and trends using the generated AI app. For example, it suggests new related information and products based on the user's past searches and purchased products. Step 3: The personalization unit personalizes the information based on the trends analyzed by the trend analysis unit, for example, providing customized information based on the user's preferences. Step 4: The monetization department provides the information personalized by the personalization department and aims to monetize it. For example, monetization can be achieved by adopting a revenue model such as a service fee or revenue share.

[0066] (Example 2) An information provision system according to an embodiment of the present invention promotes high-quality decision-making and personal growth, leading to a fulfilling life. This system uses a generative AI app to provide and output summaries, translations, comparisons, reviews, and related information to users. This allows the information provision system to efficiently obtain the information users need and enable better decision-making.

[0067] An information provision system according to an embodiment includes a generating AI app, a trend analysis unit, a personalization unit, and a monetization unit. The generating AI app analyzes information input by a user and summarizes, translates, compares, reviews, provides related information, and outputs the necessary information. For example, if a user wants to know information about a specific product, the generating AI app provides summary information about the product and displays comparisons with other products and reviews. The generating AI app also provides links to related information. The trend analysis unit analyzes the user's usage history and analyzes trends using the generating AI app. For example, the trend analysis unit suggests new related information or products based on information the user has previously searched for or products they have purchased. The personalization unit personalizes information based on the trends analyzed by the trend analysis unit. For example, the personalization unit provides customized information based on the user's preferences. The monetization unit provides the information personalized by the personalization unit and monetizes it. For example, the monetization unit employs a revenue model such as a service usage fee or revenue share to monetize the information. As a result, the information provision system according to an embodiment can personalize information based on the user's usage history and monetize it.

[0068] The generative AI app can estimate the user's emotions and dynamically change the order or content of information presented based on the emotion estimation function. For example, the generative AI app analyzes the user's emotions in real time when entering information. For example, if the user is excited, positive information will be displayed first. The generative AI app also dynamically changes the order of information presented according to the user's emotional state. For example, if the user is feeling stressed, relaxing information will be displayed first. The generative AI app also uses the emotion estimation function to provide customized information based on the user's emotions. For example, if the user is sad, encouraging messages or positive news will be displayed. This allows the order and content of information presented to be dynamically changed based on the user's emotions.

[0069] Generative AI apps can analyze a user's past behavioral history, predict future behavior, and provide information in advance. For example, generative AI apps analyze a user's past search history and browsing history to predict future behavior. For example, they can provide the latest information related to topics the user frequently searches for in advance. Generative AI apps can also analyze a user's behavioral patterns to predict and provide information that will be needed at specific times of the day. For example, they can provide news during the morning commute and relaxing content in the evening. Generative AI apps can also predict future purchasing behavior based on a user's past purchase history and suggest related products and services in advance. For example, they can remind the user to purchase products that they regularly purchase. This makes it possible to predict future behavior based on a user's past behavioral history and provide information in advance.

[0070] A generative AI app can customize information by analyzing a user's voice input and inferring emotions from the tone or speed of the voice. For example, a generative AI app can analyze a user's voice input in real time and infer emotions from the tone and speed of the voice. For example, if the user is excited, it can provide calm information. The generative AI app also uses voice analysis technology to customize information according to the user's emotional state. For example, if the user is calm, it can provide detailed information, and if the user is in a hurry, it can provide summary information. The generative AI app can also analyze the user's tone and speed of the voice to provide customized information based on emotions. For example, if the user is tired, it can provide relaxing content. This makes it possible to infer emotions and customize information based on the user's voice input.

[0071] A generative AI app can work in conjunction with a wearable device to optimize the information provided based on the user's biometric information. For example, a generative AI app can work in conjunction with a smartwatch to optimize the information provided based on the user's heart rate and stress level. For example, if the heart rate is high, it can provide information to help the user relax. The generative AI app can also analyze the biometric information obtained from the wearable device to provide information according to the user's health condition. For example, it can provide nutritional information after exercise. The generative AI app can also work in conjunction with a wearable device to analyze the user's sleep patterns and determine the optimal timing for providing information. For example, it can provide news immediately after waking up. This allows the app to work in conjunction with a wearable device to optimize the information provided based on the user's biometric information.

[0072] Generative AI apps can be applied in the field of education to provide customized learning materials according to students' learning progress. For example, generative AI apps can be linked to educational platforms to analyze students' learning progress in real time and provide individually customized learning materials. For example, they can provide practice questions that focus on areas of weakness. Generative AI apps can also generate and provide optimal learning plans based on students' past learning history. For example, they can suggest content that students should focus on studying before an exam. Generative AI apps can also analyze students' learning style and pace and provide learning materials accordingly. For example, they can provide visual learning materials to students who are good at visual learning. This allows generative AI apps to be applied in the field of education to provide customized learning materials according to students' learning progress.

[0073] A generative AI app can estimate a user's emotions in real time and make suggestions that elicit positive emotions. A generative AI app is equipped with a function that analyzes a user's facial expressions and voice to estimate emotions in real time. For example, it can analyze a user's emotions using a camera or microphone and make positive suggestions if it detects negative emotions. Furthermore, a generative AI app uses its emotion estimation function to provide an interface that elicits positive emotions when a user enters information. For example, it can present encouraging messages or success stories. Furthermore, when a user enters information, a generative AI app provides feedback in real time based on emotion estimation data and offers advice that strengthens positive emotions. For example, it can display appropriate encouragement or praise based on the input content. This allows a generative AI app to estimate a user's emotions in real time and make suggestions that elicit positive emotions.

[0074] The tendency analysis unit can provide positive information preferentially based on the user's emotion estimation result. For example, the tendency analysis unit provides information that elicits positive emotions based on the user's emotion estimation result. For example, if the user is feeling stressed, it provides relaxing content. The tendency analysis unit also analyzes the emotion estimation result and preferentially displays information that evokes positive emotions in the user. For example, if the user is excited, it provides success stories and positive news. The tendency analysis unit also dynamically changes the presentation order of information according to the user's emotional state. For example, if the user is sad, it displays encouraging messages and positive information first. This makes it possible to provide positive information preferentially based on the user's emotion estimation result.

[0075] The trend analysis unit can analyze a user's behavioral patterns, predict future behavior, and provide information in advance. The trend analysis unit, for example, analyzes a user's past search history and browsing history to predict future behavior. For example, it can provide the latest information related to topics that the user frequently searches for in advance. The trend analysis unit can also analyze a user's behavioral patterns to predict and provide information that will be needed at specific times of the day. For example, it can provide news during the morning commute and relaxing content in the evening. The trend analysis unit can also predict future purchasing behavior based on the user's past purchase history and suggest related products and services in advance. For example, it can remind the user of products that are regularly purchased. This makes it possible to predict future behavior based on a user's behavioral patterns and provide information in advance.

[0076] The trend analysis unit can analyze a user's voice input and infer emotions from the voice tone or speed to customize information. For example, the trend analysis unit analyzes a user's voice input in real time and infers emotions from the voice tone or speed. For example, if the user is excited, calm information is provided. The trend analysis unit also customizes information according to the user's emotional state using voice analysis technology. For example, if the user is calm, detailed information is provided, and if the user is in a hurry, summary information is provided. The trend analysis unit also analyzes the user's voice tone or speed to provide customized information based on emotions. For example, if the user is tired, content that helps them relax is provided. In this way, emotions can be inferred based on the user's voice input and information can be customized.

[0077] The trend analysis unit can consider applications in different industries or fields based on the results of the user trend analysis. The trend analysis unit, for example, considers applications in different industries based on the results of the user trend analysis. For example, in the education field, providing customized teaching materials according to learning progress. The trend analysis unit also considers applications in different fields based on the results of the user trend analysis. For example, in the medical field, providing customized treatment plans according to the patient's health condition. The trend analysis unit also considers applications in different industries or fields based on the results of the user trend analysis. For example, in the marketing field, providing customized advertisements according to consumer purchasing behavior. This makes it possible to consider applications in different industries or fields based on the results of the user trend analysis.

[0078] The trend analysis unit can provide personalized advertisements based on the results of the user's trend analysis. The trend analysis unit provides personalized advertisements based on the results of the user's trend analysis, for example. For example, advertisements related to products that the user has searched for in the past are displayed. The trend analysis unit also provides personalized advertisements based on the user's purchasing history. For example, advertisements related to products that the user frequently purchases are displayed. The trend analysis unit also analyzes the user's behavioral patterns and provides personalized advertisements. For example, advertisements related to topics that the user is interested in during a specific time period are displayed. In this way, personalized advertisements can be provided based on the results of the user's trend analysis.

[0079] The trend analysis unit can use the emotion estimation function to identify trends that the user is most interested in and promote the generation of new ideas based on those trends. The trend analysis unit, for example, uses the emotion estimation function to identify trends that the user is most interested in. For example, topics with high emotion scores are preferentially displayed. The trend analysis unit also analyzes the user's emotional responses and generates new ideas based on the results. For example, ideas related to themes with strong positive emotions are suggested. The trend analysis unit also identifies trends that the user is most interested in based on the emotion estimation data and generates new ideas based on those trends. For example, ideas are dynamically generated according to changes in the user's emotions. In this way, the emotion estimation function can be used to identify trends that the user is most interested in and promote the generation of new ideas.

[0080] The monetization unit can display positive advertisements based on the user's emotion estimation results within the app. For example, the monetization unit displays advertisements that elicit positive emotions based on the user's emotion estimation results within the app. For example, if the user is feeling stressed, advertisements for products that help relax are displayed. The monetization unit also analyzes the emotion estimation results and preferentially displays advertisements that evoke positive emotions within the user. For example, if the user is excited, entertainment-related advertisements are displayed. The monetization unit also dynamically changes the display order of advertisements according to the user's emotional state. For example, if the user is sad, advertisements containing encouraging messages are displayed first. In this way, positive advertisements can be displayed based on the user's emotion estimation results within the app.

[0081] The monetization unit can analyze a user's behavior history within the app and display advertisements at the optimal timing. For example, the monetization unit analyzes a user's behavior history within the app and displays advertisements at the optimal timing. For example, if a user is active during a specific time period, advertisements are displayed during that time period. The monetization unit also analyzes a user's behavior patterns and optimizes the timing of advertisement display. For example, advertisements are displayed immediately after a function that the user frequently uses. The monetization unit also dynamically adjusts the timing of advertisement display based on the user's past behavior history. For example, advertisements are displayed after the user completes a specific action. This allows advertisements to be displayed at the optimal timing based on the user's behavior history within the app.

[0082] The monetization unit can analyze a user's voice input within the app and infer emotions from the voice tone or speed to customize advertisements. For example, the monetization unit analyzes a user's voice input within the app in real time and infers emotions from the voice tone or speed. For example, if the user is excited, entertainment-related advertisements are displayed. The monetization unit also uses voice analysis technology to customize advertisements according to the user's emotional state. For example, if the user is calm, advertisements containing detailed information are displayed. The monetization unit also analyzes the user's voice tone and speed to provide customized advertisements based on emotions. For example, if the user is tired, advertisements for products that help relax are displayed. In this way, emotions can be inferred based on the user's voice input within the app and advertisements can be customized.

[0083] The monetization unit can deploy the app to different platforms. For example, the monetization unit deploys the generated AI app to a smart speaker to provide information via voice commands. For example, when a user asks a question by voice, the generated AI app provides summary information. The monetization unit also deploys the generated AI app to a smart TV to display information on a large screen. For example, when a user operates the remote control, the generated AI app displays related information. The monetization unit also deploys the generated AI app to different platforms so that users can access it from any device. For example, it can be used on smartphones, tablets, PCs, etc. This allows the app to be deployed to different platforms.

[0084] The monetization department can apply the app to different industries and monetize it. For example, the monetization department can apply the generative AI app to the medical field to provide information based on a patient's health condition. For example, it can provide regular health checks and medication reminders. The monetization department can also apply the generative AI app to the education field to provide customized learning materials based on a student's learning progress. For example, it can provide practice questions specialized in weak areas. The monetization department can also apply the generative AI app to different industries and monetize it. For example, it can provide customized advertisements based on consumer purchasing behavior in the marketing field. This allows the app to be applied to different industries and monetized.

[0085] The monetization unit can use the emotion estimation function to provide premium services based on the user's emotions and increase revenue. The monetization unit, for example, uses the emotion estimation function to provide premium services based on the user's emotions. For example, if the user is feeling stressed, it provides relaxing content. The monetization unit can also provide premium services according to the user's emotional state and increase revenue. For example, if the user is excited, it provides entertainment-related premium content. The monetization unit can also use the emotion estimation function to provide customized premium services based on the user's emotions. For example, if the user is sad, it provides encouraging messages or positive news. In this way, the emotion estimation function can be used to provide premium services based on the user's emotions and increase revenue.

[0086] A generative AI app has a summarization function and can incorporate an emotion estimation function into the summarized information to emphasize positive elements. A generative AI app, for example, can incorporate an emotion estimation function into summarized information to emphasize positive elements. For example, in summaries of news articles, it can emphasize positive events. A generative AI app can also use the emotion estimation function to emphasize positive elements of summarized information. For example, in summaries of product reviews, it can emphasize positive ratings. A generative AI app can also incorporate an emotion estimation function into summarized information to emphasize elements that users have positive emotions about. For example, in summaries of academic papers, it can emphasize successful research points. In this way, an emotion estimation function can be incorporated into summarized information to emphasize positive elements.

[0087] The generative AI app has a summarization function and can compare summarized information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generative AI app compares summarized information with the user's past search history and provides highly relevant information preferentially. For example, it provides summary information related to topics the user has previously searched for. The generative AI app also provides highly relevant summary information preferentially based on the user's past browsing history. For example, it provides summary information related to categories that the user frequently browses. The generative AI app also compares summarized information with the user's past behavioral history and provides highly relevant information preferentially. For example, it provides summary information related to products the user has previously purchased. This allows the generative AI app to compare summarized information with the user's past behavioral history and provide highly relevant information preferentially.

[0088] The generative AI app has a summarization function, provides summarized information by voice, and can customize the content by inferring the user's emotions from the user's voice tone and speed. For example, the generative AI app provides summarized information by voice and infers the user's emotions from the user's voice tone and speed. For example, if the user is excited, the app provides information in a calm tone. The generative AI app also uses voice analysis technology to customize the summary information according to the user's emotional state. For example, if the user is calm, the app provides detailed information, and if the user is in a hurry, the app provides summary information. The generative AI app also analyzes the user's voice tone and speed to provide customized summary information based on the user's emotions. For example, if the user is tired, the app provides content that helps them relax. This allows the app to provide summarized information by voice and customize the content by inferring the user's emotions from the user's voice tone and speed.

[0089] The generative AI app has a summarization function, and can support different languages ​​and obtain feedback from an international perspective. For example, the generative AI app can support different languages ​​and collect feedback from an international perspective. For example, it can translate into multiple languages ​​such as English, French, and Chinese. The generative AI app also builds a system that posts the translated summary information on a multilingual platform and obtains feedback from users around the world. The generative AI app can also collect advice and suggestions for improvement from an international perspective based on the summary information translated into different languages, improving the quality of the summaries. For example, it can reflect feedback that takes cultural and market differences into account. This allows the summarization function to support different languages ​​and obtain feedback from an international perspective.

[0090] Generative AI apps have a summarization function and can convert summarized information into visual notes or mind maps to make it easier to understand visually. For example, generative AI apps can convert summarized information into visual notes to visually display the main points of an idea. For example, they can indicate important points using diagrams or icons. Generative AI apps can also convert summarized information into mind map format to visually organize related keywords and concepts. This allows users to understand the overall picture of the information at a glance. Generative AI apps can also develop tools that automatically generate visual notes and mind maps to enable users to easily display summarized information visually. For example, they can provide a function to visualize summarized information using drag and drop. This allows summarized information to be converted into visual notes or mind maps to make it easier to understand visually.

[0091] The generative AI app has a summarization function and uses an emotion estimation function to collect users' emotional reactions to summarized information and improve the accuracy of the summary based on that. The generative AI app, for example, collects users' emotional reactions to summarized information in real time and improves the accuracy of the summary based on that data. For example, it prioritizes the adoption of summary information with a high number of positive reactions. The generative AI app also uses the emotion estimation function to collect feedback on the summarized information and regenerates the summary information if there are a high number of negative reactions. The generative AI app also analyzes users' emotional reaction data and identifies areas for improvement in the summary information based on the results. For example, it makes suggestions to correct parts with low emotion scores. In this way, the generative AI app can collect users' emotional reactions to summarized information using the emotion estimation function and improve the accuracy of the summary based on that feedback.

[0092] A generative AI app has a translation function and can incorporate an emotion estimation function into the translated information to emphasize positive elements. A generative AI app, for example, can incorporate an emotion estimation function into the translated information to emphasize positive elements. For example, when translating a news article, it can emphasize positive events. A generative AI app can also use the emotion estimation function to emphasize positive elements in the translated information. For example, when translating a product review, it can emphasize positive ratings. A generative AI app can also incorporate an emotion estimation function into the translated information to emphasize elements that the user feels positive about. For example, when translating an academic paper, it can emphasize research successes. This allows the generative AI app to incorporate an emotion estimation function into the translated information to emphasize positive elements.

[0093] The generative AI app has a translation function and can compare translated information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generative AI app compares translated information with the user's past search history and provides highly relevant information preferentially. For example, it provides translated information related to topics the user has previously searched for. The generative AI app also provides highly relevant translated information preferentially based on the user's past browsing history. For example, it provides translated information related to categories that the user frequently browses. The generative AI app also compares translated information with the user's past behavioral history and provides highly relevant information preferentially. For example, it provides translated information related to products the user has previously purchased. This allows the generative AI app to compare translated information with the user's past behavioral history and provide highly relevant information preferentially.

[0094] The generative AI app has a translation function, provides translated information by voice, and can customize the content by inferring the user's emotions from the user's tone and speed of speech. For example, the generative AI app provides translated information by voice and infers the user's emotions from the user's tone and speed of speech. For example, if the user is excited, the app provides information in a calm tone. The generative AI app also uses voice analysis technology to customize the translation information according to the user's emotional state. For example, if the user is calm, the app provides detailed information, and if the user is in a hurry, the app provides summary information. The generative AI app also analyzes the user's tone and speed of speech to provide customized translation information based on the user's emotions. For example, if the user is tired, the app provides relaxing content. This allows the generative AI app to provide translated information by voice and customize the content by inferring the user's emotions from the user's tone and speed of speech.

[0095] The generative AI app has a translation function and can support different languages ​​to obtain feedback from an international perspective. The generative AI app, for example, supports different languages ​​and collects feedback from an international perspective. For example, it translates into multiple languages ​​such as English, French, and Chinese. The generative AI app also builds a system that posts translated information on a multilingual platform and obtains feedback from users around the world. The generative AI app also collects advice and suggestions for improvement from an international perspective based on the information translated into different languages, improving the quality of the translation. For example, it reflects feedback that takes cultural and market differences into account. This allows the translation function to support different languages ​​and obtain feedback from an international perspective.

[0096] Generative AI apps have translation functions and can convert translated information into visual notes or mind maps, making it easier to understand visually. For example, generative AI apps can convert translated information into visual notes to visually display the key points of an idea. For example, they can indicate important points with diagrams or icons. Generative AI apps can also convert translated information into mind maps, visually organizing related keywords and concepts. This allows users to understand the overall picture of the information at a glance. Generative AI apps can also develop tools that automatically generate visual notes and mind maps, allowing users to easily display translated information visually. For example, they can provide a function to visualize translated information with drag and drop. This allows translated information to be converted into visual notes or mind maps, making it easier to understand visually.

[0097] The generative AI app has a translation function and uses an emotion estimation function to collect users' emotional reactions to translated information and improve the accuracy of the translation based on that information. The generative AI app, for example, collects users' emotional reactions to translated information in real time and uses that data to improve the accuracy of the translation. For example, it prioritizes translation information with a high number of positive reactions. The generative AI app also uses the emotion estimation function to collect feedback on the translated information and regenerates the translation information if there are a high number of negative reactions. The generative AI app also analyzes users' emotional reaction data and identifies areas for improvement in the translation information based on the results. For example, it makes suggestions to correct parts with low emotion scores. In this way, the generative AI app can collect users' emotional reactions to translated information using the emotion estimation function and improve the accuracy of the translation based on that feedback.

[0098] A generative AI app has a comparison function and can incorporate an emotion estimation function into the compared information to emphasize positive elements. A generative AI app, for example, can incorporate an emotion estimation function into the compared information to emphasize positive elements. For example, in product comparisons, it can emphasize positive reviews. A generative AI app can also use the emotion estimation function to emphasize positive elements of the compared information. For example, in service comparisons, it can emphasize positive feedback. A generative AI app can also incorporate an emotion estimation function into the compared information to emphasize elements that the user has positive emotions about. For example, in comparisons of travel plans, it can emphasize enjoyable experiences. In this way, it is possible to incorporate an emotion estimation function into the compared information to emphasize positive elements.

[0099] The generative AI app has a comparison function and can compare the compared information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generative AI app compares the compared information with the user's past search history and provides highly relevant information preferentially. For example, it provides comparative information related to products the user has searched for in the past. The generative AI app also provides highly relevant comparative information preferentially based on the user's past browsing history. For example, it provides comparative information related to categories that the user frequently browses. The generative AI app also compares the compared information with the user's past behavioral history and provides highly relevant information preferentially. For example, it provides comparative information related to products the user has purchased in the past. This allows the generative AI app to compare the compared information with the user's past behavioral history and provide highly relevant information preferentially.

[0100] The generative AI app has a comparison function, provides the compared information by voice, and can customize the content by inferring the user's emotions from the user's voice tone and speed. For example, the generative AI app provides the compared information by voice and infers the user's emotions from the user's voice tone and speed. For example, if the user is excited, the app provides information in a calm tone. The generative AI app also uses voice analysis technology to customize the comparison information according to the user's emotional state. For example, if the user is calm, the app provides detailed information, and if the user is in a hurry, the app provides summary information. The generative AI app also analyzes the user's voice tone and speed to provide customized comparison information based on emotions. For example, if the user is tired, the app provides content that helps them relax. This allows the generative AI app to provide the compared information by voice and customize the content by inferring the user's emotions from the user's voice tone and speed.

[0101] A generative AI app has a comparison function, and can apply the comparison function to different industries or applications to discover new market needs. For example, a generative AI app can apply the comparison function to different industries to discover new market needs. For example, in the medical field, it can compare treatments and recommend the most suitable treatment. A generative AI app can also apply the comparison function to different applications to discover new market needs. For example, in the education field, it can compare teaching materials and recommend the most suitable teaching materials. A generative AI app can also apply the comparison function to different industries and applications to discover new market needs. For example, in the travel field, it can compare tour packages and recommend the most suitable tour. In this way, the comparison function can be applied to different industries and applications to discover new market needs.

[0102] Generative AI apps have a comparison function and can convert the compared information into visual notes or mind maps, making it easier to understand visually. For example, generative AI apps can convert the compared information into visual notes and visually display the main points of an idea. For example, they can indicate important points with diagrams or icons. Generative AI apps can also convert the compared information into mind map format and visually organize related keywords and concepts. This allows users to understand the overall picture of the information at a glance. Generative AI apps can also develop tools that automatically generate visual notes and mind maps, allowing users to easily display comparative information visually. For example, they can provide a function to visualize comparative information with drag and drop. This allows the compared information to be converted into visual notes or mind maps, making it easier to understand visually.

[0103] The generative AI app has a comparison function and uses an emotion estimation function to collect the user's emotional reactions to the compared information, and can improve the accuracy of the comparison based on that. The generative AI app, for example, collects the user's emotional reactions to the compared information in real time and uses that data to improve the accuracy of the comparison. For example, it prioritizes the adoption of comparison information with a high number of positive reactions. The generative AI app also uses the emotion estimation function to collect feedback on the compared information and regenerates the comparison information if there are a high number of negative reactions. The generative AI app also analyzes the user's emotional reaction data and identifies areas for improvement in the comparison information based on the results. For example, it makes suggestions to correct parts with low emotion scores. In this way, the generative AI app can collect the user's emotional reactions to the compared information using the emotion estimation function and improve the accuracy of the comparison based on that.

[0104] The generative AI app has a function for providing reputation information and can incorporate an emotion estimation function into the reputation information to emphasize positive elements. The generative AI app, for example, incorporates an emotion estimation function into reputation information to emphasize positive elements. For example, in product reviews, it emphasizes positive ratings. The generative AI app also uses the emotion estimation function to emphasize positive elements of reputation information. For example, in service reviews, it emphasizes positive feedback. The generative AI app also incorporates an emotion estimation function into reputation information to emphasize elements about which users have positive emotions. For example, in travel reviews, it emphasizes enjoyable experiences. In this way, the emotion estimation function can be incorporated into reputation information to emphasize positive elements.

[0105] The generation AI app has a function for providing reputation information, and can compare the reputation information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generation AI app compares the reputation information with the user's past search history and provides highly relevant information preferentially. For example, it provides reputation information related to products that the user has searched for in the past. The generation AI app also provides highly relevant reputation information preferentially based on the user's past browsing history. For example, it provides reputation information related to categories that the user frequently browses. The generation AI app also compares the reputation information with the user's past behavioral history and provides highly relevant information preferentially. For example, it provides reputation information related to products that the user has purchased in the past. This allows the generation AI app to compare the reputation information with the user's past behavioral history and provide highly relevant information preferentially.

[0106] The generative AI app has a reputation information provision function, provides reputation information by voice, and can customize the content by inferring the user's emotions from the user's voice tone and speed. The generative AI app, for example, provides reputation information by voice and infers the user's emotions from the user's voice tone and speed. For example, if the user is excited, it provides information in a calm tone. The generative AI app also uses voice analysis technology to customize reputation information according to the user's emotional state. For example, if the user is calm, it provides detailed information, and if the user is in a hurry, it provides summary information. The generative AI app also analyzes the user's voice tone and speed to provide customized reputation information based on emotions. For example, if the user is tired, it provides content that is relaxing. This makes it possible to provide reputation information by voice and customize the content by inferring the user's emotions from the user's voice tone and speed.

[0107] The generative AI app has a function for providing reputation information, and can apply the reputation information to different industries or applications to discover new market needs. For example, the generative AI app applies reputation information to different industries to discover new market needs. For example, in the medical field, it collects reputations of treatments and suggests the most suitable treatment. The generative AI app also applies reputation information to different applications to discover new market needs. For example, in the education field, it collects reputations of teaching materials and suggests the most suitable teaching materials. The generative AI app also applies reputation information to different industries and applications to discover new market needs. For example, in the travel field, it collects reputations of tour packages and suggests the most suitable tour. In this way, reputation information can be applied to different industries and applications to discover new market needs.

[0108] The generative AI app has a function for providing reputation information and can convert it into visual notes or mind maps to make it easier to understand visually. For example, the generative AI app converts reputation information into visual notes to visually display the key points of an idea. For example, it can show important points using diagrams or icons. The generative AI app can also convert reputation information into mind map format to visually organize related keywords and concepts. This allows users to understand the overall picture of the information at a glance. The generative AI app also develops tools that automatically generate visual notes and mind maps, allowing users to easily display reputation information visually. For example, it provides a function for visualizing reputation information using drag and drop. This allows reputation information to be converted into visual notes or mind maps to make it easier to understand visually.

[0109] The generative AI app has a reputation information provision function and uses an emotion estimation function to collect users' emotional reactions to reputation information, and can improve the accuracy of the reputation information based on that. For example, the generative AI app collects users' emotional reactions to reputation information in real time and improves the accuracy of the reputation information based on that data. For example, it prioritizes reputation information with a high number of positive reactions. The generative AI app also uses the emotion estimation function to collect feedback on reputation information and regenerates reputation information if there are a high number of negative reactions. The generative AI app also analyzes users' emotional reaction data and identifies areas for improvement in the reputation information based on the results. For example, it makes suggestions to correct parts with low emotional scores. In this way, the emotion estimation function can be used to collect users' emotional reactions to reputation information, and the accuracy of the reputation information can be improved based on that.

[0110] A generative AI app has a function for providing related information, and can incorporate an emotion estimation function into the related information to emphasize positive elements. For example, a generative AI app can incorporate an emotion estimation function into related information to emphasize positive elements. For example, in related information for a news article, it can emphasize positive events. A generative AI app can also use the emotion estimation function to emphasize positive elements of related information. For example, in related information for product reviews, it can emphasize positive ratings. A generative AI app can also incorporate an emotion estimation function into related information to emphasize elements that users have positive emotions about. For example, in related information for an academic paper, it can emphasize research successes. In this way, an emotion estimation function can be incorporated into related information to emphasize positive elements.

[0111] The generative AI app has a function for providing related information, and can compare related information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generative AI app compares related information with the user's past search history and provides highly relevant information preferentially. For example, it provides information related to topics that the user has previously searched for. The generative AI app also provides highly relevant information preferentially based on the user's past browsing history. For example, it provides information related to categories that the user frequently browses. The generative AI app also compares related information with the user's past behavioral history and provides highly relevant information preferentially. For example, it provides information related to products that the user has previously purchased. This allows the generative AI app to compare related information with the user's past behavioral history and provide highly relevant information preferentially.

[0112] The generative AI app has a function for providing related information, and can provide related information by voice and customize the content by inferring the user's emotions from the user's voice tone and speed. For example, the generative AI app provides related information by voice and infers the user's emotions from the user's voice tone and speed. For example, if the user is excited, the app provides information in a calm tone. The generative AI app also uses voice analysis technology to customize related information according to the user's emotional state. For example, if the user is calm, the app provides detailed information, and if the user is in a hurry, the app provides summary information. The generative AI app also analyzes the user's voice tone and speed to provide customized related information based on emotions. For example, if the user is tired, the app provides content that helps them relax. This allows the app to provide related information by voice and customize the content by inferring the user's emotions from the user's voice tone and speed.

[0113] A generative AI app has the function of providing related information and can apply it to different industries or applications to discover new market needs. For example, a generative AI app can apply related information to different industries to discover new market needs. For example, in the medical field, it can collect related information on treatments and recommend the most appropriate treatment. A generative AI app can also apply related information to different applications to discover new market needs. For example, in the education field, it can collect related information on teaching materials and recommend the most appropriate teaching materials. A generative AI app can also apply related information to different industries and applications to discover new market needs. For example, in the travel field, it can collect related information on tour packages and recommend the most appropriate tour. This allows related information to be applied to different industries and applications to discover new market needs.

[0114] Generative AI apps have the ability to provide related information and convert it into visual notes or mind maps, making it easier to understand visually. For example, generative AI apps convert related information into visual notes to visually display the key points of an idea. For example, they may indicate important points using diagrams or icons. Generative AI apps also convert related information into mind map format, visually organizing related keywords and concepts. This allows users to understand the overall picture of the information at a glance. Generative AI apps also develop tools that automatically generate visual notes and mind maps, allowing users to easily display related information visually. For example, they provide a function to visualize related information using drag and drop. This allows related information to be converted into visual notes or mind maps, making it easier to understand visually.

[0115] The generative AI app has a function for providing related information and uses an emotion estimation function to collect users' emotional reactions to related information, and can improve the accuracy of the related information based on that information. For example, the generative AI app collects users' emotional reactions to related information in real time and uses that data to improve the accuracy of the related information. For example, it prioritizes the adoption of related information with a high number of positive reactions. The generative AI app also uses the emotion estimation function to collect feedback on the related information and regenerates related information if there are a high number of negative reactions. The generative AI app also analyzes users' emotional reaction data and identifies areas for improvement in the related information based on the results. For example, it makes suggestions to correct parts with low emotion scores. In this way, the emotion estimation function can be used to collect users' emotional reactions to related information, and the accuracy of the related information can be improved based on that information.

[0116] A generative AI app has an output function and can incorporate an emotion estimation function into the output information to emphasize positive elements. A generative AI app, for example, can incorporate an emotion estimation function into the output information to emphasize positive elements. For example, in outputting news articles, it can emphasize positive events. A generative AI app can also use the emotion estimation function to emphasize positive elements of the output information. For example, in outputting product reviews, it can emphasize positive ratings. A generative AI app can also incorporate an emotion estimation function into the output information to emphasize elements that users have positive emotions about. For example, in outputting academic papers, it can emphasize successful research points. In this way, it is possible to incorporate an emotion estimation function into the output information to emphasize positive elements.

[0117] The generative AI app has an output function and can compare the output information with the user's past behavioral history and provide highly relevant information preferentially. For example, the generative AI app can compare the output information with the user's past search history and provide highly relevant information preferentially. For example, it can provide information related to topics the user has previously searched for. The generative AI app can also provide highly relevant information preferentially based on the user's past browsing history. For example, it can provide information related to categories that the user frequently browses. The generative AI app can also compare the output information with the user's past behavioral history and provide highly relevant information preferentially. For example, it can provide information related to products the user has previously purchased. This allows the generative AI app to compare the output information with the user's past behavioral history and provide highly relevant information preferentially.

[0118] The generative AI app has an output function, provides output information as audio, and can customize the content by inferring the user's emotions from the user's tone and speed of speech. The generative AI app, for example, provides output information as audio and infers the user's emotions from the user's tone and speed of speech. For example, if the user is excited, it provides information in a calm tone. The generative AI app also uses voice analysis technology to customize the output information according to the user's emotional state. For example, if the user is calm, it provides detailed information, and if the user is in a hurry, it provides summary information. The generative AI app also analyzes the user's tone and speed of speech to provide customized output information based on the user's emotions. For example, if the user is tired, it provides content that helps them relax. This allows the generative AI app to provide output information as audio and customize the content by inferring the user's emotions from the user's tone and speed of speech.

[0119] Generative AI apps have output functions and can support different formats. For example, generative AI apps can support visual notes as output functions to visually display the main points of information. For example, they can show important points using diagrams or icons. Generative AI apps can also support mind map formats as output functions to visually organize related keywords and concepts. This allows users to understand the overall picture of the information at a glance. Generative AI apps can also develop tools that automatically generate visual notes and mind maps, allowing users to easily display output information visually. For example, they can provide a function to visualize output information using drag and drop. This allows the output function to support different formats.

[0120] A generative AI app has an output function and can adapt the output information to different devices. For example, a generative AI app can adapt its output function to a smart speaker, providing information via voice commands. For example, when a user asks a question by voice, the generative AI app can provide summary information. A generative AI app can also adapt its output function to a smart TV, displaying information on a large screen. For example, when a user operates the remote control, the generative AI app displays related information. A generative AI app can also adapt its output function to different devices, allowing users to access it from any device. For example, it can be used on smartphones, tablets, PCs, etc. This allows the output information to be adapted to different devices.

[0121] The generative AI app has an output function and uses an emotion estimation function to collect the user's emotional reactions to the output information, and can improve the accuracy of the output based on that. The generative AI app, for example, collects the user's emotional reactions to the output information in real time and improves the accuracy of the output based on that data. For example, it prioritizes the adoption of output information with a high number of positive reactions. The generative AI app also uses the emotion estimation function to collect feedback on the output information and regenerates the output information if there are a high number of negative reactions. The generative AI app also analyzes the user's emotional reaction data and identifies areas for improvement in the output information based on the results. For example, it makes suggestions to correct parts with low emotion scores. In this way, the generative AI app can collect the user's emotional reactions to the output information using the emotion estimation function and improve the accuracy of the output based on that feedback.

[0122] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0123] Information provision systems can predict future behavior based on a user's behavioral history and provide information in advance. For example, they can provide the latest information related to topics the user has previously searched for in advance. They can also analyze a user's behavioral patterns and predict and provide the information they will need at specific times of the day. For example, they can provide news during the morning commute and relaxing content in the evening. They can also predict future purchasing behavior based on a user's past purchase history and suggest related products and services in advance. For example, they can remind users of products they regularly purchase. This makes it possible to predict future behavior based on a user's past behavioral history and provide information in advance.

[0124] The information provision system can customize information by analyzing a user's voice input and inferring emotions from the tone or speed of the voice. For example, the system analyzes a user's voice input in real time and infers emotions from the tone and speed of the voice. If the user is excited, calm information is provided. Furthermore, voice analysis technology is used to customize information according to the user's emotional state. If the user is calm, detailed information is provided, and if the user is in a hurry, summary information is provided. Furthermore, the system analyzes the user's tone and speed of the voice and provides customized information based on emotions. If the user is tired, content that helps them relax is provided. In this way, emotions can be inferred based on the user's voice input and information can be customized.

[0125] The information provision system can work in conjunction with wearable devices to optimize the information provided based on the user's biometric information. For example, by working in conjunction with a smartwatch, the information provided can be optimized based on the user's heart rate and stress level. If the heart rate is high, information to help relax can be provided. The biometric information obtained from the wearable device can also be analyzed to provide information according to the user's health condition. Nutritional information can be provided after exercise. The information provision system can also work in conjunction with a wearable device to analyze the user's sleep patterns and determine the optimal timing for providing information. News can be provided immediately after waking up. In this way, the information provided can be optimized based on the user's biometric information by working in conjunction with a wearable device.

[0126] Information provision systems can be applied to the field of education to provide customized learning materials according to students' learning progress. For example, by linking with an educational platform, students' learning progress can be analyzed in real time and individually customized learning materials can be provided. Practice questions specific to weak areas can be provided. An optimal learning plan can also be generated and provided based on the student's past learning history. Content that should be focused on before an exam can be suggested. A student's learning style and pace can also be analyzed and learning materials can be provided accordingly. Visual learning materials can be provided to students who are good at visual learning. This allows the system to be applied to the field of education to provide customized learning materials according to students' learning progress.

[0127] The information provision system can estimate a user's emotions in real time and make suggestions that elicit positive emotions. For example, it is equipped with a function that analyzes the user's facial expressions and voice and estimates emotions in real time. It analyzes the user's emotions using a camera and microphone and makes positive suggestions if it detects negative emotions. It also uses the emotion estimation function to provide an interface that elicits positive emotions when the user enters information. It presents encouraging messages and success stories. It also provides feedback in real time based on emotion estimation data when the user enters information, offering advice that will strengthen positive emotions. It displays appropriate encouragement and praise based on the input content. This makes it possible to estimate a user's emotions in real time and make suggestions that elicit positive emotions.

[0128] The information provision system can provide positive information preferentially based on the user's emotion estimation results. For example, information that elicits positive emotions is provided preferentially based on the user's emotion estimation results. If the user is feeling stressed, relaxing content is provided. Furthermore, the emotion estimation results are analyzed and information that the user feels positively is displayed preferentially. If the user is excited, success stories and positive news are provided. Furthermore, the order in which information is presented is dynamically changed depending on the user's emotional state. If the user is sad, encouraging messages and positive information are displayed first. This allows positive information to be provided preferentially based on the user's emotion estimation results.

[0129] Information provision systems can analyze user behavior patterns, predict future behavior, and provide information in advance. For example, they can analyze a user's past search history and browsing history to predict future behavior. They can provide the latest information related to topics that the user frequently searches for in advance. They can also analyze a user's behavior patterns to predict and provide information that will be needed at specific times of the day. They can provide news during the morning commute and relaxing content in the evening. They can also predict future purchasing behavior based on the user's past purchase history and suggest related products and services in advance. They can also remind the user of products that are regularly purchased. This makes it possible to predict future behavior based on a user's behavior patterns and provide information in advance.

[0130] The information provision system can customize information by analyzing a user's voice input and inferring emotions from the tone or speed of the voice. For example, the system analyzes a user's voice input in real time and infers emotions from the tone and speed of the voice. If the user is excited, calm information is provided. Furthermore, voice analysis technology is used to customize information according to the user's emotional state. If the user is calm, detailed information is provided, and if the user is in a hurry, summary information is provided. Furthermore, the system analyzes the user's tone and speed of the voice and provides customized information based on emotions. If the user is tired, content that helps them relax is provided. In this way, emotions can be inferred based on the user's voice input and information can be customized.

[0131] The information provision system can consider applications in different industries or fields based on the results of a user trend analysis. For example, applications in different industries can be considered based on the results of a user trend analysis. In the education field, customized teaching materials can be provided according to learning progress. Applications in different fields can also be considered based on the results of a user trend analysis. In the medical field, customized treatment plans can be provided according to the patient's health condition. Applications in different industries or fields can also be considered based on the results of a user trend analysis. In the marketing field, customized advertisements can be provided according to consumer purchasing behavior. This allows applications in different industries or fields to be considered based on the results of a user trend analysis.

[0132] The information provision system can provide personalized advertisements based on the results of a user's trend analysis. For example, personalized advertisements are provided based on the results of a user's trend analysis. Advertisements related to products that the user has searched for in the past are displayed. Personalized advertisements are also provided based on the user's purchasing history. Advertisements related to products that the user frequently purchases are displayed. Personalized advertisements are also provided by analyzing the user's behavioral patterns. Advertisements related to topics that the user is interested in during specific time periods are displayed. This makes it possible to provide personalized advertisements based on the results of a user's trend analysis.

[0133] The processing flow of the second embodiment will be briefly explained below.

[0134] Step 1: The AI ​​app analyzes the information entered by the user and summarizes, translates, compares, provides reviews, and provides related information, and outputs the necessary information. For example, if a user wants to know about a specific product, it will provide summary information about that product, compare it with other products, and display reviews. It will also provide links to related information. Step 2: The trend analysis unit analyzes the user's usage history and trends using the generated AI app. For example, it suggests new related information and products based on the user's past searches and purchased products. Step 3: The personalization unit personalizes the information based on the trends analyzed by the trend analysis unit, for example, providing customized information based on the user's preferences. Step 4: The monetization department provides the information personalized by the personalization department and aims to monetize it. For example, monetization can be achieved by adopting a revenue model such as a service fee or revenue share.

[0135] 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.

[0136] 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.

[0137] 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.

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

[0139] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0141] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

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

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

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

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

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

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

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

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

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

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

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

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0167] 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.

[0168] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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 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.

[0180] 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.

[0181] 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.

[0182] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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).

[0188] 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.

[0189] 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."

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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]

[0202] 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. Generative AI app and a trend analysis unit that analyzes the user's usage history and trends using the generated AI app; a personalization unit that personalizes information based on the trends analyzed by the trend analysis unit; a profit-making unit that provides the information personalized by the personalization unit and makes profits. A system characterized by:

2. The generative AI app: The emotion of the user is estimated, and the order or content of information presentation is dynamically changed based on the emotion estimation function.

2. The system of claim 1.

3. The generative AI app: Analyzing the user's past behavior history, predicting future behavior, and providing information in advance 2. The system of claim 1.

4. The generative AI app: Analyzing the user's voice input and inferring emotion from voice tone or rate to customize the information.

2. The system of claim 1.

5. The generative AI app: Linking with wearable devices to optimize information provision based on the user's biometric information 2. The system of claim 1.

6. The generative AI app: It is applied to the field of education to provide customized learning materials according to students' learning progress.

2. The system of claim 1.

Images