System

Abstract

An object of the system according to the embodiment is to provide an experience in which a user directly communicates with an influencer or a content holder and to utilize the feedback for the next content creation.SOLUTION: A system according to an embodiment includes a learning unit, a reception unit, a generation unit, a provision unit, and a feedback unit. The learning unit learns the existing content of the content holder or the influencer. The reception unit receives a question or a conversation from a user. The generator generates a response based on the question or the conversation received by the receiver. The providing unit provides the response generated by the generating unit to the user. The feedback unit provides the question or conversation provided by the providing unit to the content holder.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 technology has made it difficult for users to communicate directly with influencers and content holders, and the feedback is not fully utilized in creating future content.

[0005] The system according to the embodiment aims to provide users with the experience of communicating directly with influencers and content holders, and to utilize that feedback in creating the next piece of content. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, a receiving unit, a generating unit, a providing unit, and a feedback unit. The learning unit learns existing content from content holders or influencers. The receiving unit receives questions or conversations from users. The generating unit generates responses based on the questions or conversations received by the receiving unit. The providing unit provides the responses generated by the generating unit to the user. The feedback unit provides the questions or conversations provided by the providing unit to the content holder. [Effects of the Invention]

[0007] The system according to the embodiment provides users with the experience of communicating directly with influencers and content holders, and the feedback can be used to create the next piece of content. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A platform according to an embodiment of the present invention is a system that provides users with unique experiences by utilizing a generation AI that has learned existing content from content holders and influencers. In this system, when a user poses a question or conversation to the generation AI, the generation AI generates a response based on the question or conversation and provides it to the user. The user's questions and conversations are also provided to the content holder to serve as hints for creating future content. For example, the platform trains the generation AI to learn existing content from content holders and influencers. The generation AI analyzes large amounts of text and video data to learn the influencer's characteristic expressions and style. Next, the user poses a question or conversation to the generation AI. For example, the user inputs questions such as "What do you think about recent trends?" or "What movies do you recommend?" The generation AI then generates a response based on the learned influencer style. For example, the system uses phrases and expressions frequently used by influencers to provide natural responses to users. Furthermore, the user's questions and conversations are provided to the content holder. This allows the content holder to understand the user's interests and needs and obtain hints for creating future content. For example, the platform can create the next blog post or video on a topic that users have asked the most about. This allows the platform to provide users with an experience that feels like they are communicating directly with their favorite influencer, and content holders can create new content based on user feedback.

[0029] A platform according to an embodiment includes a learning unit, a receiving unit, a generating unit, a providing unit, and a feedback unit. The learning unit learns existing content from content holders or influencers. For example, the learning unit analyzes text data and video data to learn the influencer's characteristic phrases and style. The learning unit can also use a generation AI to analyze the content of blog articles and videos previously posted by the influencer. The receiving unit receives questions and conversations from users. For example, the receiving unit can receive text-based questions and voice input. The generating unit generates responses based on the questions and conversations received by the receiving unit. The generating unit uses the generation AI to generate responses based on the learned influencer style. For example, the generating unit generates responses using phrases and expressions frequently used by the influencer. The providing unit provides the responses generated by the generating unit to the user. For example, the providing unit can provide responses in real time or via batch processing. The feedback unit provides the questions and conversations provided by the providing unit to the content holder. For example, the feedback unit analyzes questions and conversations from users and provides hints for creating the next content, thereby enabling the platform according to the embodiment to provide users with unique experiences and to provide content holders with hints for creating the next content.

[0030] The learning unit can analyze text data or video data to learn the influencer's characteristic expressions or style. Examples of text data or video data include, but are not limited to, blog posts and YouTube® videos. For example, the learning unit can analyze the influencer's blog posts to learn the influencer's characteristic expressions and style. The learning unit can also analyze the influencer's YouTube videos to learn the influencer's speaking patterns and expressions. Furthermore, the learning unit can analyze the influencer's social media posts to learn specific phrases and styles. This makes it possible to generate responses that capture the influencer's characteristics. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input the influencer's blog posts into the generation AI and cause the generation AI to learn the influencer's characteristic expressions and style.

[0031] The learning unit can analyze the content of blog articles or videos posted by the influencer in the past. The content of the blog articles or videos includes, but is not limited to, the article theme and the video topic. For example, the learning unit analyzes blog articles posted by the influencer in the past and learns their content. The learning unit can also analyze the content of videos posted by the influencer in the past and learn their topics and themes. Furthermore, the learning unit can analyze the content of social media posts posted by the influencer in the past and learn their characteristics. This makes it possible to generate responses based on the influencer's past content. Some or all of the above-mentioned processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input the influencer's past blog articles into the generation AI and have the generation AI analyze the content.

[0032] During learning, the learning unit can optimize the learning algorithm based on reaction data for the influencer's past content. Reaction data includes, but is not limited to, the number of views, comments, and likes. For example, the generation AI analyzes the number of user comments and likes on the influencer's past posts and prioritizes learning content that has received a positive response. The learning unit can also learn content that has attracted viewers' attention by referring to the viewing time and viewing completion rate of the influencer's videos. Furthermore, the learning unit can analyze the number of shares of the influencer's past content and learn content that is likely to be shared. This allows content that has received a positive response to be prioritized. The optimization of the learning algorithm can be performed, for example, by adjusting hyperparameters or implementing a feedback loop. Some or all of the above-described processing in the learning unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the learning unit can input reaction data for the influencer's past content into the generation AI and cause the generation AI to optimize the learning algorithm.

[0033] During learning, the learning unit can integrate the influencer's activities on different platforms to enrich the learning data. Examples of activities on different platforms include, but are not limited to, YouTube, Instagram (registered trademark), and Twitter (registered trademark). For example, the generation AI in the learning unit can integrate the influencer's YouTube videos and Instagram posts to learn, thereby reflecting the influencer's activities on both platforms. The learning unit can also integrate the influencer's Twitter tweets and blog posts to learn, thereby learning both short and long writing styles. Furthermore, the learning unit can integrate the influencer's TikTok videos and Facebook posts to learn, thereby learning content that caters to different audiences. This allows the learning data to be reflected in the learning data. The enrichment of the learning data is performed according to criteria such as data integration methods and data preprocessing methods. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input data on an influencer's activities on different platforms into the generation AI and have the generation AI expand the learning data.

[0034] During learning, the learning unit can analyze trend fluctuations in the influencer's content and adjust the update frequency of the learning data. Trend fluctuations include, but are not limited to, changes over time and popular keywords. For example, if the generation AI detects rapid changes in the influencer's content trend, the learning unit can increase the update frequency of the learning data. Furthermore, if the generation AI detects a stable trend in the influencer's content, the learning unit can decrease the update frequency of the learning data. Furthermore, the learning unit can analyze trends related to specific seasons or events and update the learning data according to those seasons. This allows the update frequency of the learning data to be adjusted according to trends. The update frequency of the learning data is adjusted according to criteria such as periodic updates or real-time updates. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input trend data of the influencer's content into the generation AI and cause the generation AI to adjust the update frequency of the learning data.

[0035] The reception unit can analyze the user's past question history and select the optimal reception method when receiving a question. The question history includes, for example, past question content and question frequency, but is not limited to these examples. For example, the reception unit analyzes questions frequently asked by the user in the past and prioritizes receiving similar questions. The reception unit can also prioritize receiving questions about specific topics from the user's past question history. Furthermore, the reception unit can select the optimal reception method (voice, text, etc.) based on the user's past question history. This makes it possible to provide the optimal reception method based on the user's past question history. The reception method is selected based on criteria such as text-based or voice-based. Some or all of the above-mentioned processing in the reception unit may be performed using or without the generation AI. For example, the reception unit can input the user's past question history data into the generation AI and have the generation AI select the optimal reception method.

[0036] The reception unit may filter questions and conversations based on the user's current areas of interest upon reception. Areas of interest include, but are not limited to, past search history and browsing history. The reception unit may, for example, preferentially receive questions and conversations related to topics in which the user is currently interested. The reception unit may also analyze the user's current areas of interest and filter and receive related questions and conversations. Furthermore, the reception unit may preferentially receive questions and conversations related to specific topics based on the user's current areas of interest. This allows appropriate questions and conversations to be received based on the user's current areas of interest. Filtering may be performed based on criteria such as keyword matching or category-based filtering. Some or all of the above-described processing in the reception unit may be performed using or without the generation AI. For example, the reception unit may input the user's area of ​​interest data into the generation AI and have the generation AI perform filtering of questions and conversations.

[0037] The reception unit can select an appropriate reception means according to the user's input method when receiving the data. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the user uses voice input, the reception unit can use voice recognition technology to receive questions and conversations. Furthermore, if the user uses text input, the reception unit can also use text analysis technology to receive questions and conversations. Furthermore, if the user uses image input, the reception unit can also use image recognition technology to receive questions and conversations. This allows the optimal reception means to be provided according to the user's input method. The selection of the reception means is performed according to criteria such as voice recognition technology or text analysis technology. Some or all of the above-described processing in the reception unit may be performed using or without the generation AI. For example, the reception unit can input the user's input data into the generation AI and have the generation AI select the optimal reception means.

[0038] When generating a response, the generation unit can adjust the level of detail of the response based on the importance of the question. The importance of a question includes, but is not limited to, the content of the question and the user's level of interest. For example, if the question is important, the generation unit generates a response including a detailed explanation. If the question is general, the generation unit can also generate a concise response. Furthermore, if the question is urgent, the generation unit can quickly generate a response and provide detailed information later as needed. This allows a response to be provided with an appropriate level of detail depending on the importance of the question. The adjustment of the level of detail of the response is performed based on criteria such as a detailed explanation or a concise answer. Some or all of the above-mentioned processing in the generation unit may be performed using or without the generation AI. For example, the generation unit can input question importance data into the generation AI and have the generation AI adjust the level of detail of the response.

[0039] When generating a response, the generation unit can apply different response algorithms depending on the question category. Question categories include, but are not limited to, technical questions and general questions. For example, if the question is technical, the generation AI can apply a technical response algorithm to provide detailed technical information. Alternatively, if the question is entertainment-related, the generation AI can apply a response algorithm specialized for entertainment to generate a fun response. Furthermore, if the question is educational, the generation AI can apply an educational response algorithm to provide an easy-to-understand explanation. This allows for providing an appropriate response algorithm depending on the question category. The response algorithm is applied according to criteria such as a rule-based algorithm or a machine learning-based algorithm. Some or all of the above-mentioned processing in the generation unit may be performed using or without the generation AI. For example, the generation unit can input question category data into the generation AI and have the generation AI apply the response algorithm.

[0040] When generating a response, the generation unit can improve the accuracy of the response by referring to the user's past response results. Past response results include, but are not limited to, past response content and user feedback. For example, the generation unit can analyze feedback on responses that the generation AI has received in the past to improve the accuracy of the response. The generation unit can also generate consistent responses by having the generation AI refer to the user's past questions and their responses. Furthermore, the generation unit can adjust the algorithm for the generation AI to generate more appropriate responses based on the user's past response results. This can improve the accuracy of the response based on the user's past response results. The improvement of the response accuracy is performed based on criteria such as accuracy and relevance. Some or all of the above-mentioned processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit can input the user's past response result data into the generation AI and have the generation AI improve the accuracy of the response.

[0041] When providing a response, the providing unit can select an appropriate response delivery method by referring to the user's past operation history. The operation history includes, for example, past operation content and operation frequency, but is not limited to such examples. For example, the providing unit preferentially selects a delivery method (voice, text, etc.) that the user has previously preferred. The providing unit can also analyze the user's past operation history and suggest an optimal delivery method. Furthermore, the providing unit can customize the response delivery method based on the user's past operation history. This makes it possible to provide an optimal delivery method based on the user's past operation history. The delivery method is selected based on criteria such as real-time delivery or batch delivery. Some or all of the above-mentioned processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input the user's operation history data into the generation AI and have the generation AI select the optimal delivery method.

[0042] When providing a response, the providing unit can customize the provided content according to the user's current task. The current task includes, but is not limited to, for example, the user's operation content and the progress of the task. For example, the providing unit can prioritize providing a response related to the task the user is currently performing. The providing unit can also analyze the user's current task and suggest the optimal response content. Furthermore, the providing unit can customize and provide the response content based on the user's current task. This makes it possible to provide appropriate content according to the user's current task. The customization of the provided content is performed, for example, according to criteria such as a method for selecting information according to the user's task. Some or all of the above-mentioned processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input the user's task data into the generation AI and have the generation AI customize the provided content.

[0043] The providing unit can improve the response providing method by reflecting user feedback when providing a response. Examples of feedback include, but are not limited to, user ratings and usage analysis. For example, if a user provides feedback on a provided response, the providing unit can improve the response providing method based on the feedback. The providing unit can also analyze the user feedback and optimize the response providing method. Furthermore, the providing unit can also customize the response providing method by reflecting user feedback. This allows the response providing method to be improved based on user feedback. The improvement of the response providing method is performed according to criteria such as adjusting an algorithm based on feedback. Some or all of the above-described processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input user feedback data into the generation AI and cause the generation AI to improve the response providing method.

[0044] When providing feedback, the feedback unit can select an appropriate feedback delivery method by referring to the user's past feedback history. The feedback history includes, but is not limited to, past feedback content and feedback frequency. For example, the feedback unit selects an optimal feedback delivery method based on feedback previously provided by the user. The feedback unit can also analyze the user's past feedback history and suggest an optimal feedback delivery method. Furthermore, the feedback unit can customize the feedback delivery method based on the user's past feedback history. This allows the optimal feedback delivery method to be provided based on the user's past feedback history. The delivery method is selected based on criteria such as real-time delivery or batch delivery. Some or all of the above-mentioned processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input the user's feedback history data into the generation AI and have the generation AI select the optimal feedback delivery method.

[0045] When providing feedback, the feedback unit can customize the provided content based on the user's current areas of interest. Areas of interest include, but are not limited to, past search history and browsing history. For example, the feedback unit can provide feedback related to topics that the user is currently interested in. The feedback unit can also analyze the user's current areas of interest and prioritize providing related feedback. Furthermore, the feedback unit can customize and provide feedback based on the user's current areas of interest. This allows appropriate feedback to be provided based on the user's current areas of interest. The provided content is customized based on criteria such as a method for selecting information according to the user's areas of interest. Some or all of the above-mentioned processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input the user's area of ​​interest data into the generation AI and have the generation AI customize the provided content.

[0046] When providing feedback, the feedback unit can improve the provision method by reflecting the user's feedback. Examples of feedback include, but are not limited to, user ratings and usage analysis. For example, if a user provides an opinion on the provided feedback, the feedback unit can improve the provision method based on the opinion. The feedback unit can also analyze the user's feedback and optimize the feedback provision method. Furthermore, the feedback unit can also customize the feedback provision method by reflecting the user's feedback. This allows the provision method to be improved based on the user's feedback. The improvement of the provision method is performed according to criteria such as adjusting an algorithm based on the feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input user feedback data into the generation AI and cause the generation AI to improve the provision method.

[0047] When providing feedback, the feedback unit can select an appropriate delivery method based on the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and location-based services. For example, if the user is in a specific area, the feedback unit can prioritize providing feedback related to that area. The feedback unit can also analyze the user's geographical location information and filter and provide highly relevant feedback. Furthermore, the feedback unit can prioritize providing feedback related to a specific area based on the user's geographical location information. This allows optimal feedback to be provided based on the user's geographical location information. The delivery method can be selected based on criteria such as real-time delivery or batch delivery. Some or all of the above-described processing in the feedback unit can be performed using or without the generation AI. For example, the feedback unit can input the user's geographical location information data into the generation AI and cause the generation AI to select the optimal delivery method.

[0048] When providing feedback, the feedback unit may analyze the user's social media activity and provide relevant feedback. Social media activity includes, but is not limited to, the content of posts, the number of likes, and the number of comments. For example, the feedback unit may analyze the content of the user's social media posts and provide relevant feedback preferentially. The feedback unit may also filter and provide relevant feedback based on the user's social media activity history. Furthermore, the feedback unit may also provide relevant feedback preferentially based on the activities of the user's friends on social media. This allows relevant feedback to be provided based on the user's social media activity. The selection of relevant feedback is performed according to criteria such as a method for selecting feedback based on social media activity. Some or all of the above-described processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit may input the user's social media activity data into the generation AI and cause the generation AI to provide relevant feedback.

[0049] When providing feedback, the feedback unit can customize the feedback delivery method by reflecting the user's past feedback. Past feedback includes, but is not limited to, past feedback content and feedback frequency. For example, the feedback unit selects an optimal feedback delivery method based on feedback previously provided by the user. The feedback unit can also analyze the user's past feedback history and suggest an optimal feedback delivery method. Furthermore, the feedback unit can customize the feedback delivery method based on the user's past feedback history. This allows the feedback delivery method to be customized based on the user's past feedback. The customization of the feedback delivery method is performed according to criteria such as adjusting an algorithm based on feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input the user's past feedback data into the generation AI and have the generation AI customize the feedback delivery method.

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

[0051] The learning unit can analyze a user's past behavioral data to infer the user's interests and concerns. For example, the learning unit can analyze the content the user has viewed in the past and the search history to identify topics in which the user is particularly interested. The learning unit can also analyze events the user has previously attended and the list of influencers the user follows to infer the user's interests. Furthermore, the learning unit can analyze the history of products and services the user has previously purchased to understand the user's purchasing trends. This makes it possible to select learning data based on the user's interests and concerns.

[0052] The reception unit can select the optimal method for receiving questions and conversations based on the user's current location information. For example, when the user is in a public place, the reception unit can prioritize receiving text-based questions and conversations. When the user is at home, the reception unit can also prioritize receiving voice input. Furthermore, when the user is on the move, the reception unit can also prioritize receiving concise questions and conversations. This makes it possible to provide an appropriate reception method according to the user's location information.

[0053] The generator can maintain consistency of responses based on the user's past response history. For example, the generator can refer to responses received by the user in the past to generate consistent responses to similar questions. The generator can also analyze the user's past feedback to improve the quality of the responses. Furthermore, the generator can generate responses tailored to the user's preferences based on the user's past response history. This makes it possible to provide consistent responses based on the user's past response history.

[0054] The providing unit can adjust the response providing method depending on the type of device the user is using. For example, if the user is using a smartphone, the providing unit can provide a response in the form of a short text message. If the user is using a tablet, the providing unit can provide a detailed graphical response. Furthermore, if the user is using a desktop computer, the providing unit can provide a response that combines detailed text and images. This makes it possible to provide an optimal response providing method depending on the user's device.

[0055] The feedback unit can analyze the user's social media activity and provide relevant feedback. For example, the feedback unit can analyze content shared by the user on social media and provide feedback based on that content. The feedback unit can also analyze posts by influencers the user follows on social media and provide relevant feedback. Furthermore, the feedback unit can analyze the activities of groups and communities the user participates in on social media and provide relevant feedback. This makes it possible to provide appropriate feedback based on the user's social media activity.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The learning unit studies the existing content of the content holder or influencer. For example, the learning unit analyzes text data and video data to learn the influencer's characteristic phrasing and style. The learning unit can also use generative AI to analyze the content of blog articles and videos posted by the influencer in the past. Step 2: The reception unit receives questions or conversations from the user. For example, the reception unit can receive text-based questions or voice input. Step 3: The generator generates a response based on the questions and conversations received by the receiver. The generator uses a generative AI to generate a response based on the learned influencer style. For example, the generator generates a response using phrases and expressions frequently used by influencers. Step 4: The providing unit provides the response generated by the generating unit to the user. For example, the providing unit can provide the response in real time or by batch processing. Step 5: The feedback unit provides the questions and conversations provided by the providing unit to the content holder. For example, the feedback unit analyzes the questions and conversations from users and provides hints for creating the next content.

[0058] (Example 2) A platform according to an embodiment of the present invention is a system that provides users with unique experiences by utilizing a generation AI that has learned existing content from content holders and influencers. In this system, when a user poses a question or conversation to the generation AI, the generation AI generates a response based on the question or conversation and provides it to the user. The user's questions and conversations are also provided to the content holder to serve as hints for creating future content. For example, the platform trains the generation AI to learn existing content from content holders and influencers. The generation AI analyzes large amounts of text and video data to learn the influencer's characteristic expressions and style. Next, the user poses a question or conversation to the generation AI. For example, the user inputs questions such as "What do you think about recent trends?" or "What movies do you recommend?" The generation AI then generates a response based on the learned influencer style. For example, the system uses phrases and expressions frequently used by influencers to provide natural responses to users. Furthermore, the user's questions and conversations are provided to the content holder. This allows the content holder to understand the user's interests and needs and obtain hints for creating future content. For example, the platform can create the next blog post or video on a topic that users have asked the most about. This allows the platform to provide users with an experience that feels like they are communicating directly with their favorite influencer, and content holders can create new content based on user feedback.

[0059] A platform according to an embodiment includes a learning unit, a receiving unit, a generating unit, a providing unit, and a feedback unit. The learning unit learns existing content from content holders or influencers. For example, the learning unit analyzes text data and video data to learn the influencer's characteristic phrases and style. The learning unit can also use a generation AI to analyze the content of blog articles and videos previously posted by the influencer. The receiving unit receives questions and conversations from users. For example, the receiving unit can receive text-based questions and voice input. The generating unit generates responses based on the questions and conversations received by the receiving unit. The generating unit uses the generation AI to generate responses based on the learned influencer style. For example, the generating unit generates responses using phrases and expressions frequently used by the influencer. The providing unit provides the responses generated by the generating unit to the user. For example, the providing unit can provide responses in real time or via batch processing. The feedback unit provides the questions and conversations provided by the providing unit to the content holder. For example, the feedback unit analyzes questions and conversations from users and provides hints for creating the next content, thereby enabling the platform according to the embodiment to provide users with unique experiences and to provide content holders with hints for creating the next content.

[0060] The learning unit can analyze text data or video data to learn the influencer's characteristic expressions or style. Examples of text data or video data include, but are not limited to, blog posts and YouTube videos. For example, the learning unit can analyze the influencer's blog posts to learn the influencer's characteristic expressions and style. The learning unit can also analyze the influencer's YouTube videos to learn the influencer's speaking patterns and expressions. Furthermore, the learning unit can analyze the influencer's social media posts to learn specific phrases and styles. This makes it possible to generate responses that capture the influencer's characteristics. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input the influencer's blog posts into the generation AI and cause the generation AI to learn the influencer's characteristic expressions and style.

[0061] The learning unit can analyze the content of blog articles or videos posted by the influencer in the past. The content of the blog articles or videos includes, but is not limited to, the article theme and the video topic. For example, the learning unit analyzes blog articles posted by the influencer in the past and learns their content. The learning unit can also analyze the content of videos posted by the influencer in the past and learn their topics and themes. Furthermore, the learning unit can analyze the content of social media posts posted by the influencer in the past and learn their characteristics. This makes it possible to generate responses based on the influencer's past content. Some or all of the above-mentioned processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input the influencer's past blog articles into the generation AI and have the generation AI analyze the content.

[0062] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is excited, the learning unit causes the generation AI to preferentially select energetic content from influencers as training data. Furthermore, if the user is relaxed, the learning unit can also cause the generation AI to select calm-toned content from influencers as training data. Furthermore, if the user is sad, the learning unit can also select content containing encouraging or comforting messages from influencers as training data. This allows appropriate training data to be selected according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit can be performed using the generation AI, or can be performed without the generation AI. For example, the learning unit can input the user's emotion data into the generation AI and have the generation AI select the training data.

[0063] During learning, the learning unit can optimize the learning algorithm based on reaction data for the influencer's past content. Reaction data includes, but is not limited to, the number of views, comments, and likes. For example, the generation AI analyzes the number of user comments and likes on the influencer's past posts and prioritizes learning content that has received a positive response. The learning unit can also learn content that has attracted viewers' attention by referring to the viewing time and viewing completion rate of the influencer's videos. Furthermore, the learning unit can analyze the number of shares of the influencer's past content and learn content that is likely to be shared. This allows content that has received a positive response to be prioritized. The optimization of the learning algorithm can be performed, for example, by adjusting hyperparameters or implementing a feedback loop. Some or all of the above-described processing in the learning unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the learning unit can input reaction data for the influencer's past content into the generation AI and cause the generation AI to optimize the learning algorithm.

[0064] During learning, the learning unit can integrate the influencer's activities on different platforms to enrich the learning data. Examples of activities on different platforms include, but are not limited to, YouTube, Instagram, and Twitter. For example, the learning unit may have the generation AI integrate the influencer's YouTube videos and Instagram posts to learn, thereby reflecting the influencer's activities on both platforms. The learning unit may also integrate the influencer's Twitter tweets and blog posts to learn, thereby learning both short and long writing styles. Furthermore, the learning unit may integrate the influencer's TikTok videos and Facebook posts to learn, thereby learning content that corresponds to different audiences. This allows the learning data to be reflected in the learning data. The enrichment of the learning data is performed according to criteria such as data integration methods and data preprocessing methods. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit may input the influencer's activity data on different platforms into the generation AI and have the generation AI enrich the learning data.

[0065] During learning, the learning unit can analyze trend fluctuations in the influencer's content and adjust the update frequency of the learning data. Trend fluctuations include, but are not limited to, changes over time and popular keywords. For example, if the generation AI detects rapid changes in the influencer's content trend, the learning unit can increase the update frequency of the learning data. Furthermore, if the generation AI detects a stable trend in the influencer's content, the learning unit can decrease the update frequency of the learning data. Furthermore, the learning unit can analyze trends related to specific seasons or events and update the learning data according to those seasons. This allows the update frequency of the learning data to be adjusted according to trends. The update frequency of the learning data is adjusted according to criteria such as periodic updates or real-time updates. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input trend data of the influencer's content into the generation AI and cause the generation AI to adjust the update frequency of the learning data.

[0066] The reception unit can estimate the user's emotions and adjust the timing of accepting questions and conversations based on the estimated user emotions. For example, if the user is excited, the reception unit can speed up the acceptance timing and immediately accept questions and conversations. Furthermore, if the user is relaxed, the reception unit can slow down the acceptance timing and accept questions and conversations at the user's pace. Furthermore, if the user is sad, the reception unit can adjust the acceptance timing and respond in accordance with the user's emotions. This makes it possible to provide appropriate acceptance timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the user's emotion data into the generation AI and have the generation AI adjust the acceptance timing.

[0067] The reception unit can analyze the user's past question history and select the optimal reception method when receiving a question. The question history includes, for example, past question content and question frequency, but is not limited to these examples. For example, the reception unit analyzes questions frequently asked by the user in the past and prioritizes receiving similar questions. The reception unit can also prioritize receiving questions about specific topics from the user's past question history. Furthermore, the reception unit can select the optimal reception method (voice, text, etc.) based on the user's past question history. This makes it possible to provide the optimal reception method based on the user's past question history. The reception method is selected based on criteria such as text-based or voice-based. Some or all of the above-mentioned processing in the reception unit may be performed using or without the generation AI. For example, the reception unit can input the user's past question history data into the generation AI and have the generation AI select the optimal reception method.

[0068] The reception unit may filter questions and conversations based on the user's current areas of interest upon reception. Areas of interest include, but are not limited to, past search history and browsing history. The reception unit may, for example, preferentially receive questions and conversations related to topics in which the user is currently interested. The reception unit may also analyze the user's current areas of interest and filter and receive related questions and conversations. Furthermore, the reception unit may preferentially receive questions and conversations related to specific topics based on the user's current areas of interest. This allows appropriate questions and conversations to be received based on the user's current areas of interest. Filtering may be performed based on criteria such as keyword matching or category-based filtering. Some or all of the above-described processing in the reception unit may be performed using or without the generation AI. For example, the reception unit may input the user's area of ​​interest data into the generation AI and have the generation AI perform filtering of questions and conversations.

[0069] The reception unit can select an appropriate reception means according to the user's input method when receiving the data. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the user uses voice input, the reception unit can use voice recognition technology to receive questions and conversations. Furthermore, if the user uses text input, the reception unit can also use text analysis technology to receive questions and conversations. Furthermore, if the user uses image input, the reception unit can also use image recognition technology to receive questions and conversations. This allows the optimal reception means to be provided according to the user's input method. The selection of the reception means is performed according to criteria such as voice recognition technology or text analysis technology. Some or all of the above-described processing in the reception unit may be performed using or without the generation AI. For example, the reception unit can input the user's input data into the generation AI and have the generation AI select the optimal reception means.

[0070] The generation unit can estimate the user's emotions and adjust the way the response is expressed based on the estimated user's emotions. For example, if the user is excited, the generation AI can generate a response using energetic and positive expressions. Furthermore, if the user is relaxed, the generation unit can generate a response in a calm tone. Furthermore, if the user is sad, the generation unit can generate a response including words of comfort or encouragement. This allows the response to be provided in an appropriate way according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the generation unit can be performed using the generation AI, or can be performed without the generation AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the way the response is expressed.

[0071] When generating a response, the generation unit can adjust the level of detail of the response based on the importance of the question. The importance of a question includes, but is not limited to, the content of the question and the user's level of interest. For example, if the question is important, the generation unit generates a response including a detailed explanation. If the question is general, the generation unit can also generate a concise response. Furthermore, if the question is urgent, the generation unit can quickly generate a response and provide detailed information later as needed. This allows a response to be provided with an appropriate level of detail depending on the importance of the question. The adjustment of the level of detail of the response is performed based on criteria such as a detailed explanation or a concise answer. Some or all of the above-mentioned processing in the generation unit may be performed using or without the generation AI. For example, the generation unit can input question importance data into the generation AI and have the generation AI adjust the level of detail of the response.

[0072] When generating a response, the generation unit can apply different response algorithms depending on the question category. Question categories include, but are not limited to, technical questions and general questions. For example, if the question is technical, the generation AI can apply a technical response algorithm to provide detailed technical information. Alternatively, if the question is entertainment-related, the generation AI can apply a response algorithm specialized for entertainment to generate a fun response. Furthermore, if the question is educational, the generation AI can apply an educational response algorithm to provide an easy-to-understand explanation. This allows for providing an appropriate response algorithm depending on the question category. The response algorithm is applied according to criteria such as a rule-based algorithm or a machine learning-based algorithm. Some or all of the above-mentioned processing in the generation unit may be performed using or without the generation AI. For example, the generation unit can input question category data into the generation AI and have the generation AI apply the response algorithm.

[0073] When generating a response, the generation unit can improve the accuracy of the response by referring to the user's past response results. Past response results include, but are not limited to, past response content and user feedback. For example, the generation unit can analyze feedback on responses that the generation AI has received in the past to improve the accuracy of the response. The generation unit can also generate consistent responses by having the generation AI refer to the user's past questions and their responses. Furthermore, the generation unit can adjust the algorithm for the generation AI to generate more appropriate responses based on the user's past response results. This can improve the accuracy of the response based on the user's past response results. The improvement of the response accuracy is performed based on criteria such as accuracy and relevance. Some or all of the above-mentioned processing in the generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the generation unit can input the user's past response result data into the generation AI and have the generation AI improve the accuracy of the response.

[0074] The providing unit can estimate the user's emotions and adjust the response provision method based on the estimated user emotions. For example, if the user is excited, the providing unit can cause the generation AI to provide a quick response. Furthermore, if the user is relaxed, the providing unit can cause the generation AI to provide a response at a leisurely pace. Furthermore, if the user is sad, the providing unit can cause the generation AI to provide a response including words of comfort or encouragement. This allows the response to be provided in an appropriate manner according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the providing unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the response provision method.

[0075] When providing a response, the providing unit can select an appropriate response delivery method by referring to the user's past operation history. The operation history includes, for example, past operation content and operation frequency, but is not limited to such examples. For example, the providing unit preferentially selects a delivery method (voice, text, etc.) that the user has previously preferred. The providing unit can also analyze the user's past operation history and suggest an optimal delivery method. Furthermore, the providing unit can customize the response delivery method based on the user's past operation history. This makes it possible to provide an optimal delivery method based on the user's past operation history. The delivery method is selected based on criteria such as real-time delivery or batch delivery. Some or all of the above-mentioned processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input the user's operation history data into the generation AI and have the generation AI select the optimal delivery method.

[0076] When providing a response, the providing unit can customize the provided content according to the user's current task. The current task includes, but is not limited to, for example, the user's operation content and the progress of the task. For example, the providing unit can prioritize providing a response related to the task the user is currently performing. The providing unit can also analyze the user's current task and suggest the optimal response content. Furthermore, the providing unit can customize and provide the response content based on the user's current task. This makes it possible to provide appropriate content according to the user's current task. The customization of the provided content is performed, for example, according to criteria such as a method for selecting information according to the user's task. Some or all of the above-mentioned processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input the user's task data into the generation AI and have the generation AI customize the provided content.

[0077] The providing unit can improve the response providing method by reflecting user feedback when providing a response. Examples of feedback include, but are not limited to, user ratings and usage analysis. For example, if a user provides feedback on a provided response, the providing unit can improve the response providing method based on the feedback. The providing unit can also analyze the user feedback and optimize the response providing method. Furthermore, the providing unit can also customize the response providing method by reflecting user feedback. This allows the response providing method to be improved based on user feedback. The improvement of the response providing method is performed according to criteria such as adjusting an algorithm based on feedback. Some or all of the above-described processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input user feedback data into the generation AI and cause the generation AI to improve the response providing method.

[0078] The feedback unit can estimate the user's emotions and adjust the feedback provision method based on the estimated user's emotions. For example, if the user is excited, the feedback unit can provide feedback quickly. Furthermore, if the user is relaxed, the feedback unit can provide feedback at a leisurely pace. Furthermore, if the user is sad, the feedback unit can provide feedback including words of comfort or encouragement. This makes it possible to provide an appropriate feedback provision method according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the feedback unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the feedback provision method.

[0079] When providing feedback, the feedback unit can select an appropriate feedback delivery method by referring to the user's past feedback history. The feedback history includes, but is not limited to, past feedback content and feedback frequency. For example, the feedback unit selects an optimal feedback delivery method based on feedback previously provided by the user. The feedback unit can also analyze the user's past feedback history and suggest an optimal feedback delivery method. Furthermore, the feedback unit can customize the feedback delivery method based on the user's past feedback history. This allows the optimal feedback delivery method to be provided based on the user's past feedback history. The delivery method is selected based on criteria such as real-time delivery or batch delivery. Some or all of the above-mentioned processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input the user's feedback history data into the generation AI and have the generation AI select the optimal feedback delivery method.

[0080] When providing feedback, the feedback unit can customize the provided content based on the user's current areas of interest. Areas of interest include, but are not limited to, past search history and browsing history. For example, the feedback unit can provide feedback related to topics that the user is currently interested in. The feedback unit can also analyze the user's current areas of interest and prioritize providing related feedback. Furthermore, the feedback unit can customize and provide feedback based on the user's current areas of interest. This allows appropriate feedback to be provided based on the user's current areas of interest. The provided content is customized based on criteria such as a method for selecting information according to the user's areas of interest. Some or all of the above-mentioned processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input the user's area of ​​interest data into the generation AI and have the generation AI customize the provided content.

[0081] When providing feedback, the feedback unit can improve the provision method by reflecting the user's feedback. Examples of feedback include, but are not limited to, user ratings and usage analysis. For example, if a user provides an opinion on the provided feedback, the feedback unit can improve the provision method based on the opinion. The feedback unit can also analyze the user's feedback and optimize the feedback provision method. Furthermore, the feedback unit can also customize the feedback provision method by reflecting the user's feedback. This allows the provision method to be improved based on the user's feedback. The improvement of the provision method is performed according to criteria such as adjusting an algorithm based on the feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input user feedback data into the generation AI and cause the generation AI to improve the provision method.

[0082] The feedback unit can estimate the user's emotions and adjust the order in which feedback is provided based on the estimated user's emotions. For example, when the user is excited, the feedback unit can prioritize providing important feedback. Furthermore, when the user is relaxed, the feedback unit can adjust the order in which feedback is provided to match the user's pace. Furthermore, when the user is sad, the feedback unit can prioritize providing feedback containing words of comfort or encouragement. This makes it possible to provide an appropriate order in which feedback is provided according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the feedback unit can be performed using the generation AI, or can be performed without using the generation AI. For example, the feedback unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the order in which feedback is provided.

[0083] When providing feedback, the feedback unit can select an appropriate delivery method based on the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and location-based services. For example, if the user is in a specific area, the feedback unit can prioritize providing feedback related to that area. The feedback unit can also analyze the user's geographical location information and filter and provide highly relevant feedback. Furthermore, the feedback unit can prioritize providing feedback related to a specific area based on the user's geographical location information. This allows optimal feedback to be provided based on the user's geographical location information. The delivery method can be selected based on criteria such as real-time delivery or batch delivery. Some or all of the above-described processing in the feedback unit can be performed using or without the generation AI. For example, the feedback unit can input the user's geographical location information data into the generation AI and cause the generation AI to select the optimal delivery method.

[0084] When providing feedback, the feedback unit may analyze the user's social media activity and provide relevant feedback. Social media activity includes, but is not limited to, the content of posts, the number of likes, and the number of comments. For example, the feedback unit may analyze the content of the user's social media posts and provide relevant feedback preferentially. The feedback unit may also filter and provide relevant feedback based on the user's social media activity history. Furthermore, the feedback unit may also provide relevant feedback preferentially based on the activities of the user's friends on social media. This allows relevant feedback to be provided based on the user's social media activity. The selection of relevant feedback is performed according to criteria such as a method for selecting feedback based on social media activity. Some or all of the above-described processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit may input the user's social media activity data into the generation AI and cause the generation AI to provide relevant feedback.

[0085] When providing feedback, the feedback unit can customize the feedback delivery method by reflecting the user's past feedback. Past feedback includes, but is not limited to, past feedback content and feedback frequency. For example, the feedback unit selects an optimal feedback delivery method based on feedback previously provided by the user. The feedback unit can also analyze the user's past feedback history and suggest an optimal feedback delivery method. Furthermore, the feedback unit can customize the feedback delivery method based on the user's past feedback history. This allows the feedback delivery method to be customized based on the user's past feedback. The customization of the feedback delivery method is performed according to criteria such as adjusting an algorithm based on feedback. Some or all of the above-mentioned processing in the feedback unit may be performed using or without the generation AI. For example, the feedback unit can input the user's past feedback data into the generation AI and have the generation AI customize the feedback delivery method. === Hard Collateral 1-1 === Each of the multiple elements including the learning unit, receiving unit, generating unit, providing unit, and feedback unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes existing content from content holders and influencers. The receiving unit is realized by the control unit 46A of the smart device 14 and receives questions and conversations from users. The generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates responses based on the learned influencer style. The providing unit is realized by the control unit 46A of the smart device 14 and provides the generated responses to the user. The feedback unit is realized by the specific processing unit 290 of the data processing device 12 and provides questions and conversations from users to content holders. === Hard Collateral 1-2 === Each of the multiple elements including the learning unit, receiving unit, generating unit, providing unit, and feedback unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes existing content from content holders and influencers. The receiving unit is realized by the control unit 46A of the smart glasses 214 and receives questions and conversations from users. The generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates responses based on the learned influencer styles. The providing unit is realized by the control unit 46A of the smart glasses 214 and provides the generated responses to the user. The feedback unit is realized by the specific processing unit 290 of the data processing device 12 and provides questions and conversations from users to content holders. === Hard Collateral 1-3 === Each of the multiple elements including the learning unit, receiving unit, generating unit, providing unit, and feedback unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes existing content from content holders and influencers. The receiving unit is realized by the control unit 46A of the headset type terminal 314 and receives questions and conversations from users. The generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates responses based on the learned influencer style. The providing unit is realized by the control unit 46A of the headset type terminal 314 and provides the generated responses to the user. The feedback unit is realized by the specific processing unit 290 of the data processing device 12 and provides questions and conversations from users to content holders. === Hard Collateral 1-4 === Each of the multiple elements including the learning unit, receiving unit, generating unit, providing unit, and feedback unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes existing content from content holders and influencers. The receiving unit is realized by the control unit 46A of the robot 414 and receives questions and conversations from users. The generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates responses based on the learned influencer style. The providing unit is realized by the control unit 46A of the robot 414 and provides the generated responses to the user. The feedback unit is realized by the specific processing unit 290 of the data processing device 12 and provides questions and conversations from users to content holders.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The learning unit can analyze a user's past behavioral data to infer the user's interests and concerns. For example, the learning unit can analyze the content the user has viewed in the past and the search history to identify topics in which the user is particularly interested. The learning unit can also analyze events the user has previously attended and the list of influencers the user follows to infer the user's interests. Furthermore, the learning unit can analyze the history of products and services the user has previously purchased to understand the user's purchasing trends. This makes it possible to select learning data based on the user's interests and concerns.

[0088] The reception unit can select the optimal method for receiving questions and conversations based on the user's current location information. For example, when the user is in a public place, the reception unit can prioritize receiving text-based questions and conversations. When the user is at home, the reception unit can also prioritize receiving voice input. Furthermore, when the user is on the move, the reception unit can also prioritize receiving concise questions and conversations. This makes it possible to provide an appropriate reception method according to the user's location information.

[0089] The generator can maintain consistency of responses based on the user's past response history. For example, the generator can refer to responses received by the user in the past to generate consistent responses to similar questions. The generator can also analyze the user's past feedback to improve the quality of the responses. Furthermore, the generator can generate responses tailored to the user's preferences based on the user's past response history. This makes it possible to provide consistent responses based on the user's past response history.

[0090] The providing unit can adjust the response providing method depending on the type of device the user is using. For example, if the user is using a smartphone, the providing unit can provide a response in the form of a short text message. If the user is using a tablet, the providing unit can provide a detailed graphical response. Furthermore, if the user is using a desktop computer, the providing unit can provide a response that combines detailed text and images. This makes it possible to provide an optimal response providing method depending on the user's device.

[0091] The feedback unit can analyze the user's social media activity and provide relevant feedback. For example, the feedback unit can analyze content shared by the user on social media and provide feedback based on that content. The feedback unit can also analyze posts by influencers the user follows on social media and provide relevant feedback. Furthermore, the feedback unit can analyze the activities of groups and communities the user participates in on social media and provide relevant feedback. This makes it possible to provide appropriate feedback based on the user's social media activity.

[0092] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is excited, the learning unit can cause the generation AI to preferentially select energetic content from influencers as training data. In addition, if the user is relaxed, the learning unit can cause the generation AI to select calm-toned content from influencers as training data. Furthermore, if the user is sad, the learning unit can cause the generation AI to select content containing encouraging or comforting messages from influencers as training data. This makes it possible to select appropriate training data according to the user's emotions.

[0093] The reception unit can estimate the user's emotions and adjust the timing of accepting questions and conversations based on the estimated user emotions. For example, if the user is excited, the reception unit can speed up the reception timing and immediately accept questions and conversations. Also, if the user is relaxed, the reception unit can slow down the reception timing and accept questions and conversations at the user's pace. Furthermore, if the user is sad, the reception unit can adjust the reception timing and respond in accordance with the user's emotions. This makes it possible to provide appropriate reception timing according to the user's emotions.

[0094] The generation unit can estimate the user's emotions and adjust the way the response is expressed based on the estimated user's emotions. For example, if the user is excited, the generation AI can generate a response using energetic and positive expressions. If the user is relaxed, the generation unit can also generate a response in a calm tone. Furthermore, if the user is sad, the generation unit can generate a response including words of comfort and encouragement. This makes it possible to provide a response in an appropriate way according to the user's emotions.

[0095] The providing unit can estimate the user's emotions and adjust the method of providing a response based on the estimated user's emotions. For example, if the user is excited, the providing unit can cause the generation AI to provide a response quickly. Also, if the user is relaxed, the providing unit can cause the generation AI to provide a response at a leisurely pace. Furthermore, if the user is sad, the providing unit can cause the generation AI to provide a response that includes words of comfort or encouragement. This makes it possible to provide a response in an appropriate manner according to the user's emotions.

[0096] The feedback unit can estimate the user's emotion and adjust the feedback providing method based on the estimated user's emotion. For example, the feedback unit can provide feedback quickly when the user is excited. The feedback unit can also provide feedback at a leisurely pace when the user is relaxed. Furthermore, the feedback unit can provide feedback including words of comfort and encouragement when the user is sad. This makes it possible to provide an appropriate feedback providing method according to the user's emotion.

[0097] The processing flow of the second embodiment will be briefly explained below.

[0098] Step 1: The learning unit studies the existing content of the content holder or influencer. For example, the learning unit analyzes text data and video data to learn the influencer's characteristic phrasing and style. The learning unit can also use generative AI to analyze the content of blog articles and videos posted by the influencer in the past. Step 2: The reception unit receives questions or conversations from the user. For example, the reception unit can receive text-based questions or voice input. Step 3: The generator generates a response based on the questions and conversations received by the receiver. The generator uses a generative AI to generate a response based on the learned influencer style. For example, the generator generates a response using phrases and expressions frequently used by influencers. Step 4: The providing unit provides the response generated by the generating unit to the user. For example, the providing unit can provide the response in real time or by batch processing. Step 5: The feedback unit provides the questions and conversations provided by the providing unit to the content holder. For example, the feedback unit analyzes the questions and conversations from users and provides hints for creating the next content.

[0099] 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.

[0100] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0101] 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.

[0102] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0103] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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).

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0119] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0120] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0135] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0136] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] [Explanation of symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A learning department that learns existing content from content holders or influencers; a reception unit that receives questions or conversations from users; a generation unit that generates a response based on the question or conversation received by the reception unit; a providing unit that provides the response generated by the generating unit to a user; a feedback unit that provides the questions or conversations provided by the providing unit to content holders; Equipped with A system characterized by:

2. The learning unit Analyze text or video data to learn the influencer's distinctive phrasing or style 2. The system of claim 1.

3. The learning unit Analyze the content of blog posts or videos previously posted by influencers 2. The system of claim 1.

4. The learning unit Estimate the user's emotions and select training data based on the estimated user emotions.

2. The system of claim 1.

5. The learning unit During learning, the learning algorithm is optimized based on influencer's past content response data.

2. The system of claim 1.

6. The learning unit During learning, we integrate influencers' activities across different platforms to enrich the learning data.

2. The system of claim 1.

7. The learning unit During learning, analyze trend fluctuations in influencer content and adjust the update frequency of learning data.

2. The system of claim 1.

8. The reception unit Estimate the user's emotions and adjust the timing of accepting questions and conversations based on the estimated user emotions.

2. The system of claim 1.

Images