system

Abstract

The system according to this embodiment aims to learn the user's past commenting style and automatically generate personalized comments. [Solution] The system according to the embodiment comprises an analysis unit, a learning unit, a generation unit, and a provision unit. The analysis unit analyzes articles or images posted by the user. The learning unit learns the user's past comment style based on the data analyzed by the analysis unit. The generation unit generates comments for specific posted content based on the results learned by the learning unit. The provision unit provides the comments generated by the generation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, personalized comments reflecting the past comment style of a user have not been sufficiently automatically generated, and there is room for improvement.

[0005] The system according to the embodiment aims to learn the past comment style of a user and automatically generate personalized comments.

Means for Solving the Problems

[0006] <* The system according to this embodiment comprises an analysis unit, a learning unit, a generation unit, and a provision unit. The analysis unit analyzes articles or images posted by users. The learning unit learns the user's past comment style based on the data analyzed by the analysis unit. The generation unit generates comments for specific posted content based on the results learned by the learning unit. The provision unit provides the comments generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can learn the user's past commenting style and automatically generate personalized comments. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An automated social media comment generation system according to an embodiment of the present invention is a system that analyzes user posts and images and automatically generates appropriate comments and reactions. This system analyzes user posts and images, learns the user's past commenting style, and generates personalized comments. It can also provide comments related to trends and topics. For example, it analyzes articles or images posted by a user. The analysis unit extracts features of the text or images contained in the post and analyzes the content and images of the post using image recognition technology or text analysis technology. For example, if the posted image is a landscape photograph, the analysis unit extracts features of the landscape and analyzes the text contained in the post using text analysis technology. Next, it learns the user's past commenting style based on the analyzed data. The learning unit learns the user's past commenting history and learns phrases or expressions that the user uses more frequently than other phrases. For example, if a user frequently uses the phrase "Awesome!", the learning unit learns this phrase and utilizes it in future comment generation. Based on the learned results, it generates comments for specific posted content. The generation unit generates comments related to current trends or topics, estimates the user's sentiment, and generates comments based on the estimated user sentiment. For example, if a post is related to a current trend, the generation unit generates comments related to that trend. Also, if the user is estimated to be happy, the generation unit generates positive comments. Finally, it provides the generated comments. The provision unit provides the generated comments to the user, allowing the user to post those comments. For example, if the generated comment is "What a beautiful view!", the provision unit provides this comment to the user, and the user can post it. This system allows users to automatically receive personalized comments and be provided with comments related to trends and topics. Furthermore, by generating comments based on the user's sentiment, it can provide more appropriate comments.Furthermore, by improving the accuracy of the analysis based on the poster's past posting history, it becomes possible to generate more accurate comments. This allows social media automated comment generation systems to analyze the content and images of users' posts and automatically generate personalized comments.

[0029] The automated social media comment generation system according to this embodiment comprises an analysis unit, a learning unit, a generation unit, and a provision unit. The analysis unit analyzes articles or images posted by users. The analysis unit extracts, for example, the features of text or images contained in the post. The analysis unit analyzes the content and images of the post using image recognition technology or text analysis technology. For example, if the posted image is a landscape photograph, the analysis unit extracts the features of the landscape and analyzes the text contained in the post using text analysis technology. The learning unit learns the user's past comment style based on the data analyzed by the analysis unit. The learning unit learns, for example, the user's past comment history and learns phrases or expressions that the user uses more frequently than other phrases. For example, if the user frequently uses the phrase "Awesome!", the learning unit learns this phrase and utilizes it in future comment generation. The generation unit generates comments for specific posted content based on the results learned by the learning unit. The generation unit generates comments related to current trends or topics, for example. The generation unit estimates the user's emotions and generates comments based on the estimated emotions. For example, if the post is related to a current trend, the generation unit generates a comment related to that trend. Also, if the generation unit estimates that the user is happy, it generates a positive comment. The provision unit provides the comments generated by the generation unit. For example, the provision unit provides the generated comments to the user, allowing the user to post them. For example, if the generated comment is "What a beautiful view!", the provision unit provides this comment to the user, allowing the user to post it. In this way, the automated social media comment generation system according to the embodiment can analyze the user's posts and images and automatically generate personalized comments.

[0030] The analysis unit analyzes articles or images posted by users. For example, the analysis unit extracts features from the text or images contained in the posts. Specifically, it uses image recognition technology to analyze the content of posted images and extract features such as landscapes, people, and objects. For example, in the case of a landscape photograph, it identifies elements such as mountains, rivers, and buildings, and stores each feature in a database. It also uses text analysis technology to analyze the text contained in the posts and extract keywords and sentiments. For example, it uses natural language processing technology to analyze the context and sentiment of the posts and classify them into positive, negative, neutral, etc. Furthermore, the analysis unit also analyzes the metadata of the posts (posting date and time, location information, tags, etc.) to understand the background information of the posts. This allows the analysis unit to analyze the content of posts from multiple angles and extract detailed features. The analysis unit stores these analysis results in a database so that they can be used by subsequent learning and generation units. The analysis unit's processing is performed in real time, and it is designed so that analysis results are obtained immediately after the user posts. This allows the analysis unit to analyze posted content quickly and accurately, improving the overall efficiency of the system.

[0031] The learning unit learns the user's past comment style based on the data analyzed by the analysis unit. Specifically, it collects the user's past comment history and identifies frequently used phrases and expressions. For example, if a user frequently uses phrases like "Great!" or "Beautiful!", the learning unit learns these phrases and utilizes them in future comment generation. The learning unit models the user's comment style using machine learning algorithms. For example, it uses recurrent neural networks (RNNs) or transformer models to learn the user's comment patterns and improve its ability to generate contextually appropriate comments. Furthermore, the learning unit also learns the user's emotions and tone, building a foundation for generating comments that reflect positive, negative, neutral, and other emotions. By regularly incorporating new data and updating its model, the learning unit can always adapt to the latest user comment styles. This enables the learning unit to generate personalized comments that match the user's individual style and preferences.

[0032] The generation unit generates comments for specific posted content based on the results learned by the learning unit. Specifically, to generate comments related to current trends and topics, it collects the latest news and social media trend information and generates comments based on this information. For example, if a post is related to a current trend, it generates comments related to that trend. The generation unit also estimates the user's emotions and generates comments based on the estimated emotions. For example, if a post expresses joy, it generates a positive comment, and if a post expresses sadness, it generates a comforting comment. The generation unit uses natural language generation technology to generate contextually natural comments. For example, it uses a large-scale language model to generate contextually appropriate comments. The generation unit adjusts the generated comments to match the user's style and tone, providing comments that the user finds natural. In this way, the generation unit can generate appropriate comments that match the content and emotions of the user's posts, thereby improving user engagement.

[0033] The provider unit provides comments generated by the generator unit. Specifically, it provides generated comments to users, allowing them to post those comments. For example, if the generated comment is "What a beautiful view!", the provider unit provides this comment to the user, allowing the user to post it. The provider unit displays the generated comments through the user interface, allowing users to review and edit them as needed. Furthermore, the provider unit collects user feedback and evaluates the quality of the generated comments. For example, if a user adopts a generated comment, the provider unit improves the evaluation of that comment and reflects this in future comment generation. The provider unit supports multiple platforms and can post generated comments to different social media platforms. This allows the provider unit to make it easy for users to post comments and improve user engagement. In addition, the provider unit manages the posting history of generated comments and allows users to refer to comments they have previously posted. This allows the provider unit to provide users with a consistent commenting experience and improve the reliability of the entire system.

[0034] The analysis unit can extract features of text or images contained in a post. For example, the analysis unit can extract features of text contained in a post. For example, the analysis unit can extract features of images contained in a post. For example, the analysis unit can extract features of text contained in a post using text analysis techniques. This improves the accuracy of the analysis by extracting features of text or images contained in a post. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can perform text analysis using an AI model to extract features of text contained in a post.

[0035] The learning unit can learn the user's past comment history and learn phrases or expressions that the user uses more frequently than other phrases. For example, if the learning unit learns the user's past comment history and the user frequently uses the phrase "Great!", it will learn this phrase. The learning unit will learn this phrase and utilize it in future comment generation. The learning unit will learn phrases or expressions that the user uses more frequently than other phrases. This allows for the generation of personalized comments by learning the user's past comment history. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's past comment history into an AI model and extract frequently used phrases and expressions.

[0036] The generation unit can generate comments related to current trends or topics. For example, the generation unit generates comments related to current trends. For example, the generation unit generates comments related to current topics. For example, the generation unit generates comments related to current trends or topics. By generating comments related to current trends or topics, it is possible to provide users with useful comments. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can use a generation AI model to generate comments related to current trends.

[0037] The analysis unit can analyze the content or images of a post using image recognition technology or text analysis technology. For example, the analysis unit can analyze the content of a post using image recognition technology. For example, the analysis unit can analyze the content of a post using text analysis technology. For example, the analysis unit can analyze the images of a post using image recognition technology. For example, the analysis unit can analyze the images of a post using text analysis technology. This improves the accuracy of the analysis of the post content by using image recognition technology or text analysis technology. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can perform image analysis using an AI model in order to analyze the content of a post using image recognition technology.

[0038] The analysis unit can improve the accuracy of its analysis based on the poster's past posting history. For example, the analysis unit improves the accuracy of its analysis by referring to the poster's past posting history. For example, the analysis unit improves the accuracy of its analysis by analyzing the poster's past posting history. For example, the analysis unit improves the accuracy of its analysis by utilizing the poster's past posting history. This makes it possible to perform a more accurate analysis by improving the accuracy of the analysis based on the poster's past posting history. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the poster's past posting history into an AI model to improve the accuracy of its analysis.

[0039] The analysis unit can improve the accuracy of its analysis by referring to the poster's past posting history when analyzing the content of a post. For example, the analysis unit may prioritize the analysis of specific phrases that the poster has used in the past. For example, the analysis unit may extract and analyze specific themes or topics from the poster's past posting content. For example, the analysis unit may prioritize the analysis of specific emotional expressions based on the poster's past posting history. This improves the accuracy of the analysis by referring to the poster's past posting history. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit may input the poster's past posting history into an AI model to improve the accuracy of the analysis.

[0040] The analysis unit can adjust its analysis algorithm based on the time of day and day of the week when analyzing the content of posts. For example, the analysis unit might assume that weekday posts are mostly work-related and prioritize analyzing business terminology. For example, it might assume that weekend posts are mostly leisure-related and prioritize analyzing leisure terminology. For example, it might assume that nighttime posts are mostly emotional and prioritize analyzing emotional expressions. By adjusting the analysis algorithm based on the time of day and day of the week, more appropriate analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can use an AI model to perform analysis in order to adjust the analysis algorithm based on the time of day and day of the week.

[0041] The analysis unit can perform analysis of posted content while taking into account the poster's geographical location. For example, if the poster is in a specific region, the analysis unit will prioritize analyzing keywords related to that region. For example, if the poster is traveling, the analysis unit will prioritize analyzing keywords related to the travel destination. For example, if the poster is at home, the analysis unit will prioritize analyzing keywords related to daily life. This allows for more appropriate analysis by considering the poster's geographical location. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without AI. For example, the analysis unit can input the poster's geographical location into an AI model and perform the analysis.

[0042] The analysis unit, when analyzing the content of a post, can analyze the poster's social media activity and prioritize the analysis of relevant posts. For example, if the poster frequently uses a particular hashtag, the analysis unit will prioritize the analysis of content related to that hashtag. For example, if the poster belongs to a particular group, the analysis unit will prioritize the analysis of content related to that group. For example, if the poster participates in a particular event, the analysis unit will prioritize the analysis of content related to that event. In this way, by analyzing the poster's social media activity, it is possible to prioritize the analysis of relevant posts. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the poster's social media activity into an AI model and perform the analysis.

[0043] The learning unit can adjust its learning algorithm by referring to the user's past comment history during training. For example, the learning unit may prioritize learning phrases that the user frequently uses. For example, the learning unit may extract and learn specific themes or topics from the user's past comment history. For example, the learning unit may prioritize learning specific sentiment expressions based on the user's past comment history. In this way, the learning algorithm can be optimized by referring to the user's past comment history. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit may input the user's past comment history into an AI model and adjust the learning algorithm.

[0044] The learning unit can detect changes in the user's comment style during training and update the learning model. For example, if a user starts using a new phrase frequently, the learning unit will learn that phrase. For example, if the user's comment style changes, the learning unit will update the learning model to match the new style. For example, if a user changes their comment style on a particular topic, the learning unit will learn that change. This allows the learning model to be updated by detecting changes in the user's comment style. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit can input changes in the user's comment style into an AI model and update the learning model.

[0045] The learning unit can weight the training data based on the timing of user comment submissions during training. For example, the learning unit may prioritize learning recent comment histories. For example, the learning unit may prioritize learning comments posted during a specific period. For example, the learning unit may adjust the weighting of the training data according to the timing of user comment submissions. This allows for more appropriate learning by weighting the training data based on the timing of user comment submissions. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the timing of user comment submissions into an AI model and weight the training data.

[0046] The learning unit can analyze the user's social media activity during training and prioritize learning relevant comment history. For example, if the user frequently uses a particular hashtag, the learning unit will prioritize learning comments related to that hashtag. For example, if the user belongs to a particular group, the learning unit will prioritize learning comments related to that group. For example, if the user participates in a particular event, the learning unit will prioritize learning comments related to that event. In this way, by analyzing the user's social media activity, it is possible to prioritize learning relevant comment history. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the user's social media activity into an AI model and learn relevant comment history.

[0047] The generation unit can adjust the content of comments based on current trends and topics when generating comments. For example, the generation unit can generate comments that include keywords related to current trends. For example, the generation unit can generate comments related to trending events. For example, the generation unit can generate comments that include popular hashtags. By adjusting the content of comments based on current trends and topics, it is possible to provide more appropriate comments. Some or all of the above processing in the generation unit is performed using generation AI. For example, the generation unit can use a generation AI model to generate comments in order to adjust the content of comments based on current trends and topics.

[0048] The generation unit can apply different generation algorithms depending on the category of the posted content when generating comments. For example, the generation unit uses a nature-related algorithm to generate comments for landscape photos. For example, the generation unit uses a gourmet-related algorithm to generate comments for food photos. For example, the generation unit uses an event-related algorithm to generate comments for event photos. By applying different generation algorithms depending on the category of the posted content, it is possible to provide more appropriate comments. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can use a generation AI model to generate comments in order to apply different generation algorithms depending on the category of the posted content.

[0049] The generation unit can determine the priority of comments based on when the content was submitted. For example, the generation unit may prioritize generating comments on recent posts. For example, the generation unit may prioritize generating comments on content posted within a specific period. For example, the generation unit may adjust the priority of comments according to when the content was submitted. This allows for the provision of more appropriate comments by determining the priority of comments based on when the content was submitted. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can use a generation AI model to generate comments in order to determine the priority of comments based on when the content was submitted.

[0050] The generation unit can adjust the order of comments based on the relevance of the post content when generating comments. For example, the generation unit can prioritize generating comments that contain keywords related to the post content. For example, the generation unit can prioritize generating comments that contain topics related to the post content. For example, the generation unit can prioritize generating comments that contain emotional expressions related to the post content. By adjusting the order of comments based on the relevance of the post content, it is possible to provide more appropriate comments. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can use a generation AI model to generate comments in order to adjust the order of comments based on the relevance of the post content.

[0051] The comment provider can select an appropriate method of providing comments by referring to the user's past comment history. For example, the provider may prioritize providing comment styles that the user has previously preferred. For example, the provider may provide comments related to specific themes or topics from the user's past comment history. For example, the provider may provide comments containing specific emotional expressions based on the user's past comment history. This allows the provider to select the optimal method of providing comments by referring to the user's past comment history. Some or all of the above processing in the comment provider may be performed using AI or not. For example, the provider may input the user's past comment history into an AI model to select an appropriate method of providing comments.

[0052] The comment delivery unit can adjust the timing of comment delivery based on the user's current social media activity. For example, the unit can deliver comments during times when the user is active. For example, if the user is participating in a particular event, the unit can deliver comments related to that event. For example, if the user is active in a particular group, the unit can deliver comments related to that group. By adjusting the timing of delivery based on the user's current social media activity, comments can be delivered at a more appropriate time. Some or all of the above processing in the comment delivery unit may be performed using AI or not. For example, the comment delivery unit can input the user's current social media activity into an AI model to adjust the timing of delivery.

[0053] The service provider can select an appropriate delivery method based on the user's device information when providing comments. For example, if the user is using a smartphone, the service provider will provide comments adapted to the screen size. For example, if the user is using a tablet, the service provider will provide comments optimized for a larger screen. For example, if the user is using a smartwatch, the service provider will provide concise and highly visible comments. This allows the service provider to select the optimal delivery method by considering the user's device information. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's device information into an AI model and select an appropriate delivery method.

[0054] The comment delivery unit can adjust the timing of comment delivery by taking into account the user's geographical location information. For example, if the user is in a specific region, the comment delivery unit will provide comments related to that region. For example, if the user is traveling, the comment delivery unit will provide comments related to their travel destination. For example, if the user is at home, the comment delivery unit will provide comments related to their daily life. By taking into account the user's geographical location information, comments can be delivered at a more appropriate time. Some or all of the above processing in the comment delivery unit may be performed using AI or not. For example, the comment delivery unit can input the user's geographical location information into an AI model to adjust the timing of delivery.

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

[0056] The learning unit can also learn the commenting styles of the user's friends and followers on social media. For example, it can learn phrases and expressions frequently used by the user's friends and use them as a reference to generate comments. This allows it to provide comments that match the user's communication style with their friends and followers. Some or all of the above processing in the learning unit may be performed using AI or not.

[0057] The service provider can adjust how comments are provided based on the battery level of the user's device. For example, if the battery level is low, a short comment is provided to conserve battery power. Conversely, if the battery level is sufficient, a detailed comment is provided. This enables the provision of optimal comments according to the status of the user's device. Some or all of the above processing in the service provider may be performed using AI, or it may not be performed using AI.

[0058] The analysis unit can also analyze background sounds included in user posts. For example, it can analyze background sounds in audio data included in posts to identify the type of ambient sound or music. This allows for a more accurate understanding of the atmosphere and situation of the post, and the generation of appropriate comments. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without AI.

[0059] The comment delivery unit can adjust the frequency of comments based on the user's past comment history. For example, if a user posts comments frequently, the frequency of comments will be increased. Conversely, if a user posts comments infrequently, the frequency will be decreased. This allows for the achievement of an optimal comment delivery frequency that matches the user's comment posting habits. Some or all of the above processing in the comment delivery unit may be performed using AI or not.

[0060] The analysis unit can also analyze the emojis and stamps included in user posts. For example, it can identify the types of emojis and stamps included in a post and estimate the emotions and intentions behind the post based on that. This makes it possible to generate appropriate comments even for posts that contain emojis and stamps. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without using AI.

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

[0062] Step 1: The analysis unit analyzes the article or image posted by the user. The analysis unit extracts the features of the text or image contained in the post and analyzes the content and image of the post using image recognition technology or text analysis technology. For example, if the posted image is a landscape photograph, the analysis unit extracts the features of the landscape and analyzes the text contained in the post using text analysis technology. Step 2: The learning unit learns the user's past comment style based on the data analyzed by the analysis unit. The learning unit learns the user's past comment history and learns phrases or expressions that the user uses frequently. For example, if the user frequently uses the phrase "Great!", this phrase will be learned and used in future comment generation. Step 3: The generation unit generates comments for a specific post based on the results learned by the learning unit. The generation unit generates comments related to current trends or topics and generates comments by estimating the user's sentiment. For example, if the post is related to a current trend, it generates comments related to that trend, and if it is estimated that the user is happy, it generates positive comments. Step 4: The provider unit provides the comment generated by the generator unit. The provider unit provides the generated comment to the user, allowing the user to post the comment. For example, if the generated comment is "What a beautiful view!", this comment is provided to the user, and the user can post the comment.

[0063] (Example of form 2) An automated social media comment generation system according to an embodiment of the present invention is a system that analyzes user posts and images and automatically generates appropriate comments and reactions. This system analyzes user posts and images, learns the user's past commenting style, and generates personalized comments. It can also provide comments related to trends and topics. For example, it analyzes articles or images posted by a user. The analysis unit extracts features of the text or images contained in the post and analyzes the content and images of the post using image recognition technology or text analysis technology. For example, if the posted image is a landscape photograph, the analysis unit extracts features of the landscape and analyzes the text contained in the post using text analysis technology. Next, it learns the user's past commenting style based on the analyzed data. The learning unit learns the user's past commenting history and learns phrases or expressions that the user uses more frequently than other phrases. For example, if a user frequently uses the phrase "Awesome!", the learning unit learns this phrase and utilizes it in future comment generation. Based on the learned results, it generates comments for specific posted content. The generation unit generates comments related to current trends or topics, estimates the user's sentiment, and generates comments based on the estimated user sentiment. For example, if a post is related to a current trend, the generation unit generates comments related to that trend. Also, if the user is estimated to be happy, the generation unit generates positive comments. Finally, it provides the generated comments. The provision unit provides the generated comments to the user, allowing the user to post those comments. For example, if the generated comment is "What a beautiful view!", the provision unit provides this comment to the user, and the user can post it. This system allows users to automatically receive personalized comments and be provided with comments related to trends and topics. Furthermore, by generating comments based on the user's sentiment, it can provide more appropriate comments.Furthermore, by improving the accuracy of the analysis based on the poster's past posting history, it becomes possible to generate more accurate comments. This allows social media automated comment generation systems to analyze the content and images of users' posts and automatically generate personalized comments.

[0064] The automated social media comment generation system according to this embodiment comprises an analysis unit, a learning unit, a generation unit, and a provision unit. The analysis unit analyzes articles or images posted by users. The analysis unit extracts, for example, the features of text or images contained in the post. The analysis unit analyzes the content and images of the post using image recognition technology or text analysis technology. For example, if the posted image is a landscape photograph, the analysis unit extracts the features of the landscape and analyzes the text contained in the post using text analysis technology. The learning unit learns the user's past comment style based on the data analyzed by the analysis unit. The learning unit learns, for example, the user's past comment history and learns phrases or expressions that the user uses more frequently than other phrases. For example, if the user frequently uses the phrase "Awesome!", the learning unit learns this phrase and utilizes it in future comment generation. The generation unit generates comments for specific posted content based on the results learned by the learning unit. The generation unit generates comments related to current trends or topics, for example. The generation unit estimates the user's emotions and generates comments based on the estimated emotions. For example, if the post is related to a current trend, the generation unit generates a comment related to that trend. Also, if the generation unit estimates that the user is happy, it generates a positive comment. The provision unit provides the comments generated by the generation unit. For example, the provision unit provides the generated comments to the user, allowing the user to post them. For example, if the generated comment is "What a beautiful view!", the provision unit provides this comment to the user, allowing the user to post it. In this way, the automated social media comment generation system according to the embodiment can analyze the user's posts and images and automatically generate personalized comments.

[0065] The analysis unit analyzes articles or images posted by users. For example, the analysis unit extracts features from the text or images contained in the posts. Specifically, it uses image recognition technology to analyze the content of posted images and extract features such as landscapes, people, and objects. For example, in the case of a landscape photograph, it identifies elements such as mountains, rivers, and buildings, and stores each feature in a database. It also uses text analysis technology to analyze the text contained in the posts and extract keywords and sentiments. For example, it uses natural language processing technology to analyze the context and sentiment of the posts and classify them into positive, negative, neutral, etc. Furthermore, the analysis unit also analyzes the metadata of the posts (posting date and time, location information, tags, etc.) to understand the background information of the posts. This allows the analysis unit to analyze the content of posts from multiple angles and extract detailed features. The analysis unit stores these analysis results in a database so that they can be used by subsequent learning and generation units. The analysis unit's processing is performed in real time, and it is designed so that analysis results are obtained immediately after the user posts. This allows the analysis unit to analyze posted content quickly and accurately, improving the overall efficiency of the system.

[0066] The learning unit learns the user's past comment style based on the data analyzed by the analysis unit. Specifically, it collects the user's past comment history and identifies frequently used phrases and expressions. For example, if a user frequently uses phrases like "Great!" or "Beautiful!", the learning unit learns these phrases and utilizes them in future comment generation. The learning unit models the user's comment style using machine learning algorithms. For example, it uses recurrent neural networks (RNNs) or transformer models to learn the user's comment patterns and improve its ability to generate contextually appropriate comments. Furthermore, the learning unit also learns the user's emotions and tone, building a foundation for generating comments that reflect positive, negative, neutral, and other emotions. By regularly incorporating new data and updating its model, the learning unit can always adapt to the latest user comment styles. This enables the learning unit to generate personalized comments that match the user's individual style and preferences.

[0067] The generation unit generates comments for specific posted content based on the results learned by the learning unit. Specifically, to generate comments related to current trends and topics, it collects the latest news and social media trend information and generates comments based on this information. For example, if a post is related to a current trend, it generates comments related to that trend. The generation unit also estimates the user's emotions and generates comments based on the estimated emotions. For example, if a post expresses joy, it generates a positive comment, and if a post expresses sadness, it generates a comforting comment. The generation unit uses natural language generation technology to generate contextually natural comments. For example, it uses a large-scale language model to generate contextually appropriate comments. The generation unit adjusts the generated comments to match the user's style and tone, providing comments that the user finds natural. In this way, the generation unit can generate appropriate comments that match the content and emotions of the user's posts, thereby improving user engagement.

[0068] The provider unit provides comments generated by the generator unit. Specifically, it provides generated comments to users, allowing them to post those comments. For example, if the generated comment is "What a beautiful view!", the provider unit provides this comment to the user, allowing the user to post it. The provider unit displays the generated comments through the user interface, allowing users to review and edit them as needed. Furthermore, the provider unit collects user feedback and evaluates the quality of the generated comments. For example, if a user adopts a generated comment, the provider unit improves the evaluation of that comment and reflects this in future comment generation. The provider unit supports multiple platforms and can post generated comments to different social media platforms. This allows the provider unit to make it easy for users to post comments and improve user engagement. In addition, the provider unit manages the posting history of generated comments and allows users to refer to comments they have previously posted. This allows the provider unit to provide users with a consistent commenting experience and improve the reliability of the entire system.

[0069] The analysis unit can extract features of text or images contained in a post. For example, the analysis unit can extract features of text contained in a post. For example, the analysis unit can extract features of images contained in a post. For example, the analysis unit can extract features of text contained in a post using text analysis techniques. This improves the accuracy of the analysis by extracting features of text or images contained in a post. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can perform text analysis using an AI model to extract features of text contained in a post.

[0070] The learning unit can learn the user's past comment history and learn phrases or expressions that the user uses more frequently than other phrases. For example, if the learning unit learns the user's past comment history and the user frequently uses the phrase "Great!", it will learn this phrase. The learning unit will learn this phrase and utilize it in future comment generation. The learning unit will learn phrases or expressions that the user uses more frequently than other phrases. This allows for the generation of personalized comments by learning the user's past comment history. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's past comment history into an AI model and extract frequently used phrases and expressions.

[0071] The generation unit can generate comments related to current trends or topics. For example, the generation unit generates comments related to current trends. For example, the generation unit generates comments related to current topics. For example, the generation unit generates comments related to current trends or topics. By generating comments related to current trends or topics, it is possible to provide users with useful comments. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can use a generation AI model to generate comments related to current trends.

[0072] The analysis unit can analyze the content or images of a post using image recognition technology or text analysis technology. For example, the analysis unit can analyze the content of a post using image recognition technology. For example, the analysis unit can analyze the content of a post using text analysis technology. For example, the analysis unit can analyze the images of a post using image recognition technology. For example, the analysis unit can analyze the images of a post using text analysis technology. This improves the accuracy of the analysis of the post content by using image recognition technology or text analysis technology. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can perform image analysis using an AI model in order to analyze the content of a post using image recognition technology.

[0073] The generation unit can estimate the user's emotions and generate comments based on those estimated emotions. For example, if the generation unit estimates the user's emotions and a positive emotion is estimated, it will generate a positive comment. For example, if the generation unit estimates the user's emotions and a negative emotion is estimated, it will generate a negative comment. For example, if the generation unit estimates the user's emotions and a neutral emotion is estimated, it will generate a neutral comment. This allows for the provision of more appropriate comments by generating comments based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit are performed using a generative AI. For example, the generation unit can estimate the user's emotions and generate comments using a generative AI model.

[0074] The analysis unit can improve the accuracy of its analysis based on the poster's past posting history. For example, the analysis unit improves the accuracy of its analysis by referring to the poster's past posting history. For example, the analysis unit improves the accuracy of its analysis by analyzing the poster's past posting history. For example, the analysis unit improves the accuracy of its analysis by utilizing the poster's past posting history. This makes it possible to perform a more accurate analysis by improving the accuracy of the analysis based on the poster's past posting history. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the poster's past posting history into an AI model to improve the accuracy of its analysis.

[0075] The analysis unit can estimate the user's emotions and adjust the analysis method of the posted content based on the estimated user emotions. For example, if the user is excited, the analysis unit will prioritize positive keywords in its analysis. For example, if the user is sad, the analysis unit will prioritize negative keywords in its analysis. For example, if the user is relaxed, the analysis unit will prioritize neutral keywords in its analysis. By adjusting the analysis method based on the user's emotions, more appropriate analysis becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can estimate the user's emotions and adjust the analysis method using an AI model.

[0076] The analysis unit can improve the accuracy of its analysis by referring to the poster's past posting history when analyzing the content of a post. For example, the analysis unit may prioritize the analysis of specific phrases that the poster has used in the past. For example, the analysis unit may extract and analyze specific themes or topics from the poster's past posting content. For example, the analysis unit may prioritize the analysis of specific emotional expressions based on the poster's past posting history. This improves the accuracy of the analysis by referring to the poster's past posting history. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit may input the poster's past posting history into an AI model to improve the accuracy of the analysis.

[0077] The analysis unit can adjust its analysis algorithm based on the time of day and day of the week when analyzing the content of posts. For example, the analysis unit might assume that weekday posts are mostly work-related and prioritize analyzing business terminology. For example, it might assume that weekend posts are mostly leisure-related and prioritize analyzing leisure terminology. For example, it might assume that nighttime posts are mostly emotional and prioritize analyzing emotional expressions. By adjusting the analysis algorithm based on the time of day and day of the week, more appropriate analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can use an AI model to perform analysis in order to adjust the analysis algorithm based on the time of day and day of the week.

[0078] The analysis unit can estimate the user's emotions and determine the priority of analysis results based on the estimated user emotions. For example, if the user is happy, the analysis unit will prioritize displaying positive analysis results. For example, if the user is angry, the analysis unit will prioritize displaying negative analysis results. For example, if the user is neutral, the analysis unit will display balanced analysis results. In this way, by determining the priority of analysis results based on the user's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can estimate the user's emotions and determine the priority of analysis results using an AI model.

[0079] The analysis unit can perform analysis of posted content while taking into account the poster's geographical location. For example, if the poster is in a specific region, the analysis unit will prioritize analyzing keywords related to that region. For example, if the poster is traveling, the analysis unit will prioritize analyzing keywords related to the travel destination. For example, if the poster is at home, the analysis unit will prioritize analyzing keywords related to daily life. This allows for more appropriate analysis by considering the poster's geographical location. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without AI. For example, the analysis unit can input the poster's geographical location into an AI model and perform the analysis.

[0080] The analysis unit, when analyzing the content of a post, can analyze the poster's social media activity and prioritize the analysis of relevant posts. For example, if the poster frequently uses a particular hashtag, the analysis unit will prioritize the analysis of content related to that hashtag. For example, if the poster belongs to a particular group, the analysis unit will prioritize the analysis of content related to that group. For example, if the poster participates in a particular event, the analysis unit will prioritize the analysis of content related to that event. In this way, by analyzing the poster's social media activity, it is possible to prioritize the analysis of relevant posts. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the poster's social media activity into an AI model and perform the analysis.

[0081] 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 happy, the learning unit will prioritize learning positive comments. For example, if the user is sad, the learning unit will prioritize learning negative comments. For example, if the user is neutral, the learning unit will learn balanced comments. This allows for more appropriate learning by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can estimate the user's emotions and select training data using an AI model.

[0082] The learning unit can adjust its learning algorithm by referring to the user's past comment history during training. For example, the learning unit may prioritize learning phrases that the user frequently uses. For example, the learning unit may extract and learn specific themes or topics from the user's past comment history. For example, the learning unit may prioritize learning specific sentiment expressions based on the user's past comment history. In this way, the learning algorithm can be optimized by referring to the user's past comment history. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit may input the user's past comment history into an AI model and adjust the learning algorithm.

[0083] The learning unit can detect changes in the user's comment style during training and update the learning model. For example, if a user starts using a new phrase frequently, the learning unit will learn that phrase. For example, if the user's comment style changes, the learning unit will update the learning model to match the new style. For example, if a user changes their comment style on a particular topic, the learning unit will learn that change. This allows the learning model to be updated by detecting changes in the user's comment style. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit can input changes in the user's comment style into an AI model and update the learning model.

[0084] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user posts comments frequently, the learning unit will increase the learning frequency. For example, if the user posts comments infrequently, the learning unit will decrease the learning frequency. For example, if the user's emotions change, the learning unit will adjust the learning frequency accordingly. This allows for more appropriate learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can estimate the user's emotions and adjust the learning frequency using an AI model.

[0085] The learning unit can weight the training data based on the timing of user comment submissions during training. For example, the learning unit may prioritize learning recent comment histories. For example, the learning unit may prioritize learning comments posted during a specific period. For example, the learning unit may adjust the weighting of the training data according to the timing of user comment submissions. This allows for more appropriate learning by weighting the training data based on the timing of user comment submissions. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the timing of user comment submissions into an AI model and weight the training data.

[0086] The learning unit can analyze the user's social media activity during training and prioritize learning relevant comment history. For example, if the user frequently uses a particular hashtag, the learning unit will prioritize learning comments related to that hashtag. For example, if the user belongs to a particular group, the learning unit will prioritize learning comments related to that group. For example, if the user participates in a particular event, the learning unit will prioritize learning comments related to that event. In this way, by analyzing the user's social media activity, it is possible to prioritize learning relevant comment history. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the user's social media activity into an AI model and learn relevant comment history.

[0087] The generation unit can estimate the user's emotions and adjust the way comments are expressed based on those emotions. For example, if the user is happy, the generation unit will use positive expressions. For example, if the user is sad, the generation unit will use comforting expressions. For example, if the user is angry, the generation unit will use empathetic expressions. By adjusting the way comments are expressed based on the user's emotions, more appropriate comments can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit is performed using a generative AI. For example, the generation unit can estimate the user's emotions and adjust the way comments are expressed using a generative AI model.

[0088] The generation unit can adjust the content of comments based on current trends and topics when generating comments. For example, the generation unit can generate comments that include keywords related to current trends. For example, the generation unit can generate comments related to trending events. For example, the generation unit can generate comments that include popular hashtags. By adjusting the content of comments based on current trends and topics, it is possible to provide more appropriate comments. Some or all of the above processing in the generation unit is performed using generation AI. For example, the generation unit can use a generation AI model to generate comments in order to adjust the content of comments based on current trends and topics.

[0089] The generation unit can apply different generation algorithms depending on the category of the posted content when generating comments. For example, the generation unit uses a nature-related algorithm to generate comments for landscape photos. For example, the generation unit uses a gourmet-related algorithm to generate comments for food photos. For example, the generation unit uses an event-related algorithm to generate comments for event photos. By applying different generation algorithms depending on the category of the posted content, it is possible to provide more appropriate comments. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can use a generation AI model to generate comments in order to apply different generation algorithms depending on the category of the posted content.

[0090] The generation unit can estimate the user's emotions and adjust the length of comments based on the estimated emotions. For example, if the user is in a hurry, the generation unit will generate a short comment. For example, if the user is relaxed, the generation unit will generate a detailed comment. For example, if the user is excited, the generation unit will generate an emotionally emphasized comment. This allows for the provision of more appropriate comments by adjusting the length of comments based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit is performed using a generative AI. For example, the generation unit can estimate the user's emotions and adjust the length of comments using a generative AI model.

[0091] The generation unit can determine the priority of comments based on when the content was submitted. For example, the generation unit may prioritize generating comments on recent posts. For example, the generation unit may prioritize generating comments on content posted within a specific period. For example, the generation unit may adjust the priority of comments according to when the content was submitted. This allows for the provision of more appropriate comments by determining the priority of comments based on when the content was submitted. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can use a generation AI model to generate comments in order to determine the priority of comments based on when the content was submitted.

[0092] The generation unit can adjust the order of comments based on the relevance of the post content when generating comments. For example, the generation unit can prioritize generating comments that contain keywords related to the post content. For example, the generation unit can prioritize generating comments that contain topics related to the post content. For example, the generation unit can prioritize generating comments that contain emotional expressions related to the post content. By adjusting the order of comments based on the relevance of the post content, it is possible to provide more appropriate comments. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit can use a generation AI model to generate comments in order to adjust the order of comments based on the relevance of the post content.

[0093] The service provider can estimate the user's emotions and adjust how comments are provided based on the estimated emotions. For example, if the user is happy, the service provider will prioritize providing positive comments. For example, if the user is sad, the service provider will prioritize providing comforting comments. For example, if the user is angry, the service provider will prioritize providing empathetic comments. By adjusting how comments are provided based on the user's emotions, more appropriate comments can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can estimate the user's emotions and adjust how comments are provided using an AI model.

[0094] The comment provider can select an appropriate method of providing comments by referring to the user's past comment history. For example, the provider may prioritize providing comment styles that the user has previously preferred. For example, the provider may provide comments related to specific themes or topics from the user's past comment history. For example, the provider may provide comments containing specific emotional expressions based on the user's past comment history. This allows the provider to select the optimal method of providing comments by referring to the user's past comment history. Some or all of the above processing in the comment provider may be performed using AI or not. For example, the provider may input the user's past comment history into an AI model to select an appropriate method of providing comments.

[0095] The comment delivery unit can adjust the timing of comment delivery based on the user's current social media activity. For example, the unit can deliver comments during times when the user is active. For example, if the user is participating in a particular event, the unit can deliver comments related to that event. For example, if the user is active in a particular group, the unit can deliver comments related to that group. By adjusting the timing of delivery based on the user's current social media activity, comments can be delivered at a more appropriate time. Some or all of the above processing in the comment delivery unit may be performed using AI or not. For example, the comment delivery unit can input the user's current social media activity into an AI model to adjust the timing of delivery.

[0096] The service provider can estimate the user's emotions and determine the order in which comments are provided based on the estimated emotions. For example, if the user is happy, the service provider will prioritize providing positive comments. For example, if the user is sad, the service provider will prioritize providing comforting comments. For example, if the user is angry, the service provider will prioritize providing empathetic comments. By determining the order in which comments are provided based on the user's emotions, more appropriate comments can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can estimate the user's emotions and determine the order in which comments are provided using an AI model.

[0097] The service provider can select an appropriate delivery method based on the user's device information when providing comments. For example, if the user is using a smartphone, the service provider will provide comments adapted to the screen size. For example, if the user is using a tablet, the service provider will provide comments optimized for a larger screen. For example, if the user is using a smartwatch, the service provider will provide concise and highly visible comments. This allows the service provider to select the optimal delivery method by considering the user's device information. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's device information into an AI model and select an appropriate delivery method.

[0098] The comment delivery unit can adjust the timing of comment delivery by taking into account the user's geographical location information. For example, if the user is in a specific region, the comment delivery unit will provide comments related to that region. For example, if the user is traveling, the comment delivery unit will provide comments related to their travel destination. For example, if the user is at home, the comment delivery unit will provide comments related to their daily life. By taking into account the user's geographical location information, comments can be delivered at a more appropriate time. Some or all of the above processing in the comment delivery unit may be performed using AI or not. For example, the comment delivery unit can input the user's geographical location information into an AI model to adjust the timing of delivery.

[0099] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0100] The analysis unit can also analyze audio data included in user posts. For example, if a post includes an audio message, the analysis unit uses speech recognition technology to convert the audio data into text and analyze its content. Furthermore, it can analyze the tone and speed of the voice to estimate the user's emotions. This makes it possible to generate appropriate comments even for posts that include audio data. Some or all of the above-described processes in the analysis unit may be performed using AI or not.

[0101] The learning unit can also learn the commenting styles of the user's friends and followers on social media. For example, it can learn phrases and expressions frequently used by the user's friends and use them as a reference to generate comments. This allows it to provide comments that match the user's communication style with their friends and followers. Some or all of the above processing in the learning unit may be performed using AI or not.

[0102] The generation unit can also generate reactions to user posts. For example, it can automatically generate reactions such as "Like!" and "Heart" for posts. Furthermore, it can estimate the user's emotions and generate emotionally appropriate reactions, such as a "Heart" if positive emotions are estimated, or a "Sad Face" if negative emotions are estimated. This allows for richer communication by automatically generating not only comments but also reactions.

[0103] The service provider can adjust how comments are provided based on the battery level of the user's device. For example, if the battery level is low, a short comment is provided to conserve battery power. Conversely, if the battery level is sufficient, a detailed comment is provided. This enables the provision of optimal comments according to the status of the user's device. Some or all of the above processing in the service provider may be performed using AI, or it may not be performed using AI.

[0104] The analysis unit can also analyze background sounds included in user posts. For example, it can analyze background sounds in audio data included in posts to identify the type of ambient sound or music. This allows for a more accurate understanding of the atmosphere and situation of the post, and the generation of appropriate comments. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without AI.

[0105] The learning unit can estimate the user's emotions and filter the training data based on those estimated emotions. For example, if the user has positive emotions, it will prioritize learning positive comments. Conversely, if the user has negative emotions, it will prioritize learning negative comments. This allows for the selection of training data according to the user's emotions, resulting in more appropriate comment generation.

[0106] The generation unit can adjust the tone of comments in response to user posts. For example, it can change the tone of comments according to the content of the post and the user's emotions, such as using a formal tone, a casual tone, or a humorous tone. This makes it possible to provide comments with the tone most appropriate to the user's post. Some or all of the above processing in the generation unit may be performed using AI or not.

[0107] The comment delivery unit can adjust the frequency of comments based on the user's past comment history. For example, if a user posts comments frequently, the frequency of comments will be increased. Conversely, if a user posts comments infrequently, the frequency will be decreased. This allows for the achievement of an optimal comment delivery frequency that matches the user's comment posting habits. Some or all of the above processing in the comment delivery unit may be performed using AI or not.

[0108] The analysis unit can also analyze the emojis and stamps included in user posts. For example, it can identify the types of emojis and stamps included in a post and estimate the emotions and intentions behind the post based on that. This makes it possible to generate appropriate comments even for posts that contain emojis and stamps. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without using AI.

[0109] The generation unit can estimate the user's emotions and select the language of the comment based on the estimated emotions. For example, if the user is relaxed, casual language will be used, and in formal situations, formal language will be used. This allows for the provision of comments in the most appropriate language according to the user's emotions and situation. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0110] The following briefly describes the processing flow for example form 2.

[0111] Step 1: The analysis unit analyzes the article or image posted by the user. The analysis unit extracts the features of the text or image contained in the post and analyzes the content and image of the post using image recognition technology or text analysis technology. For example, if the posted image is a landscape photograph, the analysis unit extracts the features of the landscape and analyzes the text contained in the post using text analysis technology. Step 2: The learning unit learns the user's past comment style based on the data analyzed by the analysis unit. The learning unit learns the user's past comment history and learns phrases or expressions that the user uses frequently. For example, if the user frequently uses the phrase "Great!", this phrase will be learned and used in future comment generation. Step 3: The generation unit generates comments for a specific post based on the results learned by the learning unit. The generation unit generates comments related to current trends or topics and generates comments by estimating the user's sentiment. For example, if the post is related to a current trend, it generates comments related to that trend, and if it is estimated that the user is happy, it generates positive comments. Step 4: The provider unit provides the comment generated by the generator unit. The provider unit provides the generated comment to the user, allowing the user to post the comment. For example, if the generated comment is "What a beautiful view!", this comment is provided to the user, and the user can post the comment.

[0112] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0114] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0115] For example, the analysis unit acquires user posts and images using the camera 42 and microphone 38B of the smart device 14, and analyzes them using the identification processing unit 290 of the data processing device 12. The learning unit learns the user's past comment style using the identification processing unit 290 of the data processing device 12. The generation unit generates comments related to trends and topics using the identification processing unit 290 of the data processing device 12. The provision unit provides the user with the comments generated by the control unit 46A of the smart device 14. The correspondence between each unit and the device and control unit is not limited to the example described above, and various modifications are possible.

[0116] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0117] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0118] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0119] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0120] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0122] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0123] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0124] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0125] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0126] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0127] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0130] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0131] For example, the analysis unit acquires user posts and images using the camera 42 and microphone 238 of the smart glasses 214, and these are analyzed by the specific processing unit 290 of the data processing device 12. The learning unit learns the user's past comment style using the specific processing unit 290 of the data processing device 12. The generation unit generates comments related to trends and topics using the specific processing unit 290 of the data processing device 12. The provision unit provides the user with the comments generated by the control unit 46A of the smart glasses 214. The correspondence between each unit and the device and control unit is not limited to the example described above, and various modifications are possible.

[0132] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0133] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0134] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0135] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0136] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0138] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0139] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0140] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0141] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0142] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0144] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0146] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0147] For example, the analysis unit acquires user posts and images using the camera 42 and microphone 238 of the headset terminal 314, and analyzes them using the specific processing unit 290 of the data processing device 12. The learning unit learns the user's past comment style using the specific processing unit 290 of the data processing device 12. The generation unit generates comments related to trends and topics using the specific processing unit 290 of the data processing device 12. The provision unit provides the generated comments to the user using the control unit 46A of the headset terminal 314. The correspondence between each unit and the device and control unit is not limited to the example described above, and various modifications are possible.

[0148] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0149] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0150] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0151] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0152] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0154] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0155] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0156] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0157] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0158] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0159] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0160] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0161] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0162] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0163] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0164] For example, the analysis unit acquires user posts and images using the camera 42 and microphone 238 of the robot 414, and these are analyzed by the specific processing unit 290 of the data processing device 12. The learning unit learns the user's past comment style using the specific processing unit 290 of the data processing device 12. The generation unit generates comments related to trends and topics using the specific processing unit 290 of the data processing device 12. The provision unit provides the user with the comments generated by the control unit 46A of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0165] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0166] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0167] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0168] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0169] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0170] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0171] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0172] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0173] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0174] 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.

[0175] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0176] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0177] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0178] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0179] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0180] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0181] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0182] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0183] (Note 1) An analysis unit that analyzes articles or images posted by users, Based on the data analyzed by the analysis unit, a learning unit learns the user's past comment style, A generation unit generates comments for specific posted content based on the results learned by the aforementioned learning unit, The system includes a providing unit that provides comments generated by the generation unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Extract text or image features from a post. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned learning unit, Learn from the user's past comment history and identify phrases or expressions that the user uses more frequently than other phrases. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Generate comments related to current trends or topics. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit, The content or images of a post are analyzed using image recognition or text analysis technology. The system described in Appendix 1, characterized by the features described herein. (Note 6) The generating unit is It estimates the user's emotions and generates comments based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, Improve the accuracy of the analysis based on the poster's past posting history. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, We estimate the user's sentiment and adjust the analysis method of the post content based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, When analyzing posted content, the accuracy of the analysis is improved by referring to the poster's past posting history. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, When analyzing posted content, the analysis algorithm is adjusted based on the time of day and day of the week the post was made. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, When analyzing the content of a post, the analysis is performed based on the poster's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, When analyzing post content, the system analyzes the poster's social media activity and prioritizes analyzing relevant posts. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned learning unit, During training, the learning algorithm is adjusted by referring to the user's past comment history. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned learning unit, During training, the system detects changes in the user's comment style and updates the learning model. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned learning unit, During training, the training data is weighted based on when the user submitted their comments. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned learning unit, During training, the system analyzes the user's social media activity and prioritizes learning relevant comment history. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is It estimates the user's emotions and adjusts the way comments are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating comments, adjust the content of the comments based on current trends and topics. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is When generating comments, different generation algorithms are applied depending on the category of the post content. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is It estimates the user's sentiment and adjusts the length of comments based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is When generating comments, the priority of comments is determined based on when the content was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 25) The generating unit is When generating comments, the order of comments is adjusted based on the relevance of the post content. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, It estimates the user's sentiment and adjusts how comments are delivered based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When a user submits a comment, the system will refer to their past comment history to select the most appropriate submission method. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, When submitting comments, the timing of submission will be adjusted based on the user's current social media activity. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, The system estimates the user's sentiment and determines the order in which comments are presented based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When a comment is submitted, the appropriate method of delivery is selected based on the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned supply unit is, When a comment is submitted, the timing of its submission will be adjusted based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0184] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An analysis unit that analyzes articles or images posted by users, Based on the data analyzed by the analysis unit, a learning unit learns the user's past comment style, A generation unit generates comments for specific posted content based on the results learned by the aforementioned learning unit, The system includes a providing unit that provides comments generated by the generation unit. A system characterized by the following features.

2. The aforementioned analysis unit, Extract text or image features from a post. The system according to feature 1.

3. The aforementioned learning unit, The system learns the user's past comment history and learns phrases or expressions that the user uses more frequently than other phrases. The system according to feature 1.

4. The generating unit is Generate comments related to current trends or topics. The system according to feature 1.

5. The aforementioned analysis unit, The content or images of a post are analyzed using image recognition or text analysis technology. The system according to feature 1.

6. The generating unit is The system estimates the user's emotions and generates comments based on the estimated emotions of the user. The system according to feature 1.

7. The aforementioned analysis unit, Improve the accuracy of the analysis based on the poster's past posting history. The system according to feature 1.

8. The aforementioned analysis unit, The system estimates the user's emotions and adjusts the method of analyzing the posted content based on the estimated user emotions. The system according to feature 1.

Images