System

Abstract

An object of a system according to an embodiment is to increase the value of a post on social media and propose a next posting theme.SOLUTION: A system according to an embodiment includes a post optimization unit, a reaction analysis unit, a response suggestion unit, and a multimodal support unit. The post optimizer optimizes the post using the RAG. The reaction analysis part analyzes the contribution contents optimized by the contribution optimization part. The response suggestion unit suggests a next posting theme on the basis of the reaction analyzed by the reaction analysis unit. The multimodal support unit supports multimodal posting based on the next posting theme suggested by the response suggestion unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately optimize social media posts to maximize their value or suggest the next post topic, leaving room for improvement.

[0005] The system according to the embodiment aims to increase the value of posts on social media and suggest the next post theme. [Means for solving the problem]

[0006] The system according to the embodiment includes a post optimization unit, a reaction analysis unit, a response suggestion unit, and a multimodal support unit. The post optimization unit optimizes posts using RAG. The reaction analysis unit analyzes the post content optimized by the post optimization unit. The response suggestion unit suggests a next post theme based on the reactions analyzed by the reaction analysis unit. The multimodal support unit supports multimodal posts based on the next post theme suggested by the response suggestion unit. [Effects of the Invention]

[0007] The system according to the embodiment can increase the value of posts on social media and suggest the next post theme. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) A posting support system according to an embodiment of the present invention is a system that helps individuals and businesses who post on social media increase the value of their posts. This system uses RAG (Search Expansion and Generation) to function as an optimized bouncer for the poster, suggesting better ways to express the content of the post and ways to reduce risks. It also suggests the next posting topic and responses to close the gap with viewers based on viewers' reactions after the post. Furthermore, the system is designed to support not only text-based social media posts, but also multimodal posts such as images, audio, and video. This allows the posting support system to increase the value of posts on social media, enabling individuals and businesses to disseminate information more effectively.

[0029] A posting support system according to an embodiment includes a posting optimization unit, a reaction analysis unit, a response suggestion unit, and a multimodal support unit. The posting optimization unit uses RAG (Search Augmentation and Generation) to suggest optimal ways of expressing content and risk reduction for posts created by posters. For example, if a poster posts a "new product introduction," RAG searches for related information and suggests more effective ways of expressing content and risks to be aware of. The generation AI receives input from a prompt containing instructions on what the poster wants the generation AI to do, and the generation AI generates optimal suggestions based on the prompt. The reaction analysis unit analyzes viewers' reactions (likes, comments, shares, etc.) after posting and suggests the next posting theme based on that data. For example, if a specific post receives many reactions, the generation AI suggests a theme related to that post as the next post. The generation AI receives input from viewers' reaction data, and the generation AI generates the next posting theme based on that data. The response suggestion unit suggests appropriate responses to help the generation AI connect with viewers. For example, in response to a comment from a viewer, the generation AI suggests an appropriate reply, helping the poster respond quickly and effectively. The input to the generation AI is a comment or message from a viewer, and the generation AI generates an appropriate response based on that content. The multimodal support unit supports not only text-based social media posts, but also multimodal posts such as images, audio, and video. For example, in the case of an image post, the generation AI analyzes the image content and suggests optimal captions and tags. Similarly, in the case of audio and video, the generation AI analyzes the content and suggests appropriate ways of expressing the content and risk reduction. The input to the generation AI is image, audio, and video data, and the generation AI generates optimal suggestions based on that data. This allows the posting support system according to the embodiment to increase the value of posts on social media and enable individuals and companies to disseminate information more effectively. For example, a post introducing a new product can reach more viewers and receive positive reactions. It also improves viewer engagement and increases brand credibility and awareness.Additionally, support for multimodal posting allows you to effectively utilize content in a variety of formats.

[0030] The post optimization unit can analyze the poster's past posting history and suggest expressions optimized for each poster. For example, the post optimization unit analyzes the poster's past posting history and extracts characteristics of posts that have received particularly high engagement. For example, it analyzes the frequency of use of specific phrases and keywords and reflects this in the next post. This increases the effectiveness of posts by suggesting optimal expressions based on the poster's past posting history.

[0031] The post optimization unit can incorporate real-time trend information into the post content and suggest ways of expressing it that are in line with the latest trends. For example, the post optimization unit collects real-time trend information and reflects it in the post content. For example, it suggests currently popular hashtags and keywords and incorporates them into the post. In this way, by incorporating real-time trend information, the effectiveness of the post is maximized.

[0032] The post optimization unit can automatically analyze the legal risks associated with the content of posts and make specific suggestions to reduce those risks. For example, the post optimization unit analyzes the content of posts and identifies risks related to copyrights and trademarks. For example, if the images or music used may be infringing copyrights, the unit suggests alternative solutions. This reduces legal risks and increases the safety of posts.

[0033] The post optimization unit can evaluate the cultural and regional suitability of the post content and suggest ways of expression that are suitable for different cultural spheres. For example, the post optimization unit analyzes the post content and evaluates its suitability in different cultural spheres. For example, if consideration for a specific culture or religion is required, it suggests ways of expression that take that into account. In this way, the effectiveness of the post is increased by suggesting ways of expression that are suitable for different cultural spheres.

[0034] The reaction analysis unit can analyze viewer reaction data over time and identify the period during which the effect of a post will last. The reaction analysis unit, for example, analyzes viewer reaction data over time and identifies the period during which the effect of a post will last. For example, it analyzes the timing when the increase in likes and comments reaches its peak. This allows the timing of the next post to be optimized by identifying the period during which the effect of a post will last.

[0035] The reaction analysis unit can perform a detailed analysis of the interests of the poster's followers based on the reaction data and suggest the next posting theme. The reaction analysis unit can perform a detailed analysis of the interests of the poster's followers based on the reaction data, for example. For example, it can analyze reactions to a specific topic or theme and suggest the next posting theme. This allows the next posting theme to be optimized by performing a detailed analysis of the interests of the followers.

[0036] The reaction analysis unit can compare reactions on different social media platforms based on the reaction data and suggest the optimal posting timing. The reaction analysis unit, for example, compares reaction data on different social media platforms and suggests the optimal posting timing. For example, it identifies the peak reaction times on each platform. This makes it possible to suggest the optimal posting timing by comparing reactions on different platforms.

[0037] The reaction analysis unit can analyze the poster's industry and market trends in real time and suggest the next posting theme based on that information. The reaction analysis unit can, for example, analyze the poster's industry and market trends in real time and suggest the next posting theme based on that information. For example, it can reflect the latest technology trends and market needs. This allows the next posting theme to be optimized by analyzing industry and market trends in real time.

[0038] The response suggestion unit can analyze the viewer's comment history and suggest responses optimized for each viewer. The response suggestion unit, for example, analyzes the viewer's comment history and suggests responses optimized for each viewer. For example, it makes personalized replies based on the content of past comments. In this way, by suggesting responses optimized for each viewer, engagement with the viewer is increased.

[0039] The response suggestion unit can suggest personalized responses based on the viewer's profile information. The response suggestion unit, for example, suggests personalized responses based on the viewer's profile information. For example, it provides information related to the viewer's occupation or hobbies. In this way, by suggesting personalized responses based on the viewer's profile information, engagement with the viewer is increased.

[0040] The response suggestion unit can analyze the effects of past responses to viewer comments and suggest the most effective response pattern. The response suggestion unit, for example, analyzes the effects of past responses to viewer comments and suggests the most effective response pattern. For example, the suggestion is made based on responses that have received high engagement in the past. In this way, the most effective response pattern can be suggested by analyzing the effects of past responses.

[0041] The response suggestion unit can suggest related additional information and links based on the content of the viewer's comment, promoting deeper engagement. The response suggestion unit, for example, analyzes the content of the viewer's comment and suggests related additional information and links. For example, it provides links to articles or product pages related to the comment. In this way, by suggesting related additional information and links, engagement with the viewer is deepened.

[0042] The multimodal support unit can perform a detailed analysis of the content of images, audio, and video, and suggest optimal captions and tags for each. The multimodal support unit can, for example, perform a detailed analysis of the content of images, audio, and video, and suggest optimal captions and tags for each. For example, it can recognize objects and scenes within an image and generate captions based on them. This allows the unit to suggest optimal captions and tags by performing a detailed analysis of the content of images, audio, and video.

[0043] The multimodal support unit can combine multimodal data to generate more effective post content. The multimodal support unit can combine, for example, image, audio, and video data to generate more effective post content. For example, a slideshow combining images and audio can be created. In this way, by combining multimodal data, more effective post content can be generated.

[0044] The multimodal support unit can automatically analyze legal risks associated with the content of images, audio, and video, and make specific suggestions to reduce those risks. For example, the multimodal support unit analyzes the content of images to identify risks related to copyright and trademark rights. For example, if an image being used may be infringing copyright, the unit will suggest alternative solutions. This reduces the legal risks associated with the content of images, audio, and video, thereby increasing the safety of posts.

[0045] The multimodal support unit can make suggestions for optimizing multimodal data for posting on different social media platforms. The multimodal support unit makes suggestions for optimizing, for example, image, audio, and video data for different social media platforms. For example, it proposes data conversion to match the formats and specifications of each platform. This improves the effectiveness of posting by optimizing the multimodal data for different social media platforms.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The post optimization unit can analyze a poster's past posting history and suggest expressions optimized for each individual poster. For example, it can analyze a poster's past posting history and extract the characteristics of posts that have received particularly high engagement. It can analyze the frequency of use of specific phrases and keywords and reflect these in the next post. This makes it possible to increase the effectiveness of posts by suggesting the optimal expression based on the poster's past posting history. It can also analyze viewers' reactions to the poster's past posts and suggest expressions that will elicit positive reactions. It can also make suggestions to reduce the risk of negative reactions to the poster's past posts.

[0048] The post optimization unit can incorporate real-time trend information for post content and suggest ways of expressing it that are in line with the latest trends. For example, it can collect real-time trend information and reflect it in post content. It can also suggest currently popular hashtags and keywords and incorporate them into posts. This allows the effectiveness of posts to be maximized by incorporating real-time trend information. It can also provide specific advice for optimizing post content based on trend information. It can also suggest the next topic that the poster should focus on based on trend information.

[0049] The Post Optimization Unit can automatically analyze the legal risks of posted content and make specific suggestions to reduce those risks. For example, it can analyze the content of a post and identify risks related to copyright and trademark rights. If the images or music used may be infringing copyright, it can suggest alternatives. This reduces legal risks and increases the safety of posts. It can also check whether the content of a post violates specific laws or regulations and suggest corrections as necessary. It can also provide specific advice to avoid legal risks.

[0050] The post optimization unit can evaluate the cultural and regional suitability of post content and suggest ways of expressing it that are appropriate for different cultural spheres. For example, it can analyze the content of a post and evaluate its suitability in different cultural spheres. If consideration for a specific culture or religion is required, it can suggest ways of expressing it that take that into account. This can increase the effectiveness of posts by suggesting ways of expressing it that are appropriate for different cultural spheres. It can also suggest ways to reduce risks that take cultural and regional suitability into account. It can also provide specific advice for optimizing post content based on trend information in different cultural spheres.

[0051] The reaction analysis unit can analyze viewer reaction data over time to identify the period during which a post's effectiveness will last. For example, it can analyze viewer reaction data over time to identify the period during which a post's effectiveness will last. It can analyze the timing at which the increase in likes and comments reaches its peak. This identifies the period during which a post's effectiveness will last, allowing the timing of the next post to be optimized. It can also provide specific advice based on the reaction data to extend the period during which a post's effectiveness lasts. It can also suggest the next post theme based on the period during which a post's effectiveness lasts.

[0052] The reaction analysis unit can perform a detailed analysis of the interests of the poster's followers based on the reaction data and suggest the next posting theme. For example, the reaction data can be used to perform a detailed analysis of the interests of the poster's followers. The reaction to a specific topic or theme can be analyzed and the next posting theme can be suggested. This allows the next posting theme to be optimized by analyzing the interests of the followers in detail. It can also provide specific advice for optimizing the content of the post based on the interests of the followers. It can also make risk reduction suggestions that take into account the interests of the followers.

[0053] The reaction analysis unit can compare reactions on different social media platforms based on reaction data and suggest the optimal posting timing. For example, it can compare reaction data on different social media platforms and suggest the optimal posting timing. It can identify the peak reaction times on each platform. This allows it to suggest the optimal posting timing by comparing reactions on different platforms. It can also provide specific advice for optimizing posting content based on differences in reactions on each platform. It can also suggest risk reduction measures that take into account reactions on each platform.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The post optimization unit uses RAG (Search Augmentation Generation) to suggest optimal ways to express content and risk reduction for posts created by posters. For example, if a poster posts an "introduction to a new product," RAG searches for related information and suggests more effective ways to express content and risks to be aware of. The input to the generation AI is a prompt containing instructions on what the poster wants the generation AI to do, and the generation AI generates optimal suggestions based on that prompt. Step 2: After posting, the generation AI analyzes viewer reactions (likes, comments, shares, etc.) and suggests the next post theme based on that data. For example, if a specific post receives many reactions, the generation AI will suggest a theme related to that post as the next post. The input to the generation AI is viewer reaction data, and the generation AI generates the next post theme based on that data. Step 3: In the response suggestion section, the generation AI suggests an appropriate response to close the gap with the viewer. For example, in response to a comment from a viewer, the generation AI suggests an appropriate reply, helping the poster reply quickly and effectively. The input to the generation AI is the comment or message from the viewer, and the generation AI generates an appropriate response based on that content. Step 4: The multimodal support unit supports not only text-based social media posts, but also multimodal posts such as images, audio, and video. For example, when posting an image, the generative AI analyzes the content of the image and suggests optimal captions and tags. Similarly, for audio and video posts, the generative AI analyzes the content and suggests appropriate ways to express it and reduce risks. The input to the generative AI is image, audio, and video data, and the generative AI generates optimal suggestions based on that data.

[0056] (Example 2) A posting support system according to an embodiment of the present invention is a system that helps individuals and businesses who post on social media increase the value of their posts. This system uses RAG (Search Expansion and Generation) to function as an optimized bouncer for the poster, suggesting better ways to express the content of the post and ways to reduce risks. It also suggests the next posting topic and responses to close the gap with viewers based on viewers' reactions after the post. Furthermore, the system is designed to support not only text-based social media posts, but also multimodal posts such as images, audio, and video. This allows the posting support system to increase the value of posts on social media, enabling individuals and businesses to disseminate information more effectively.

[0057] A posting support system according to an embodiment includes a posting optimization unit, a reaction analysis unit, a response suggestion unit, and a multimodal support unit. The posting optimization unit uses RAG (Search Augmentation and Generation) to suggest optimal ways of expressing content and risk reduction for posts created by posters. For example, if a poster posts a "new product introduction," RAG searches for related information and suggests more effective ways of expressing content and risks to be aware of. The generation AI receives input from a prompt containing instructions on what the poster wants the generation AI to do, and the generation AI generates optimal suggestions based on the prompt. The reaction analysis unit analyzes viewers' reactions (likes, comments, shares, etc.) after posting and suggests the next posting theme based on that data. For example, if a specific post receives many reactions, the generation AI suggests a theme related to that post as the next post. The generation AI receives input from viewers' reaction data, and the generation AI generates the next posting theme based on that data. The response suggestion unit suggests appropriate responses to help the generation AI connect with viewers. For example, in response to a comment from a viewer, the generation AI suggests an appropriate reply, helping the poster respond quickly and effectively. The input to the generation AI is a comment or message from a viewer, and the generation AI generates an appropriate response based on that content. The multimodal support unit supports not only text-based social media posts, but also multimodal posts such as images, audio, and video. For example, in the case of an image post, the generation AI analyzes the image content and suggests optimal captions and tags. Similarly, in the case of audio and video, the generation AI analyzes the content and suggests appropriate ways of expressing the content and risk reduction. The input to the generation AI is image, audio, and video data, and the generation AI generates optimal suggestions based on that data. This allows the posting support system according to the embodiment to increase the value of posts on social media and enable individuals and companies to disseminate information more effectively. For example, a post introducing a new product can reach more viewers and receive positive reactions. It also improves viewer engagement and increases brand credibility and awareness.Additionally, support for multimodal posting allows you to effectively utilize content in a variety of formats.

[0058] The post optimization unit can analyze the poster's past posting history and suggest expressions optimized for each poster. For example, the post optimization unit analyzes the poster's past posting history and extracts characteristics of posts that have received particularly high engagement. For example, it analyzes the frequency of use of specific phrases and keywords and reflects this in the next post. This increases the effectiveness of posts by suggesting optimal expressions based on the poster's past posting history.

[0059] The post optimization unit can incorporate real-time trend information into the post content and suggest ways of expressing it that are in line with the latest trends. For example, the post optimization unit collects real-time trend information and reflects it in the post content. For example, it suggests currently popular hashtags and keywords and incorporates them into the post. In this way, by incorporating real-time trend information, the effectiveness of the post is maximized.

[0060] The post optimization unit can use the emotion estimation function to analyze the poster's emotional state and suggest a way of expression that matches that emotion. For example, the post optimization unit analyzes the poster's emotional state in real time and suggests a way of expression that matches that emotion. For example, if the poster is in a positive emotional state, it recommends bright and optimistic expressions. This increases the effectiveness of the post by suggesting a way of expression that matches the poster's emotional state.

[0061] The post optimization unit can automatically analyze the legal risks associated with the content of posts and make specific suggestions to reduce those risks. For example, the post optimization unit analyzes the content of posts and identifies risks related to copyrights and trademarks. For example, if the images or music used may be infringing copyrights, the unit suggests alternative solutions. This reduces legal risks and increases the safety of posts.

[0062] The post optimization unit can evaluate the cultural and regional suitability of the post content and suggest ways of expression that are suitable for different cultural spheres. For example, the post optimization unit analyzes the post content and evaluates its suitability in different cultural spheres. For example, if consideration for a specific culture or religion is required, it suggests ways of expression that take that into account. In this way, the effectiveness of the post is increased by suggesting ways of expression that are suitable for different cultural spheres.

[0063] The post optimization unit can use the emotion estimation function to predict the emotional impact that the post content will have on viewers and suggest a way of expression to maximize that impact. The post optimization unit, for example, uses the emotion estimation function to predict the emotional impact that the post content will have on viewers. For example, it suggests a way of expression to elicit positive emotions. This maximizes the emotional impact on viewers, thereby increasing the effectiveness of the post.

[0064] The reaction analysis unit can analyze viewer reaction data over time and identify the period during which the effect of a post will last. The reaction analysis unit, for example, analyzes viewer reaction data over time and identifies the period during which the effect of a post will last. For example, it analyzes the timing when the increase in likes and comments reaches its peak. This allows the timing of the next post to be optimized by identifying the period during which the effect of a post will last.

[0065] The reaction analysis unit can perform a detailed analysis of the interests of the poster's followers based on the reaction data and suggest the next posting theme. The reaction analysis unit can perform a detailed analysis of the interests of the poster's followers based on the reaction data, for example. For example, it can analyze reactions to a specific topic or theme and suggest the next posting theme. This allows the next posting theme to be optimized by performing a detailed analysis of the interests of the followers.

[0066] The reaction analysis unit can use the emotion estimation function to analyze the viewer's emotional response and suggest the next post theme that will elicit positive emotions. The reaction analysis unit, for example, uses the emotion estimation function to analyze the viewer's emotional response and suggest the next post theme that will elicit positive emotions. For example, it selects a theme that evokes emotion or joy. In this way, by suggesting the next post theme that will elicit positive emotions, viewer engagement can be increased.

[0067] The reaction analysis unit can compare reactions on different social media platforms based on the reaction data and suggest the optimal posting timing. The reaction analysis unit, for example, compares reaction data on different social media platforms and suggests the optimal posting timing. For example, it identifies the peak reaction times on each platform. This makes it possible to suggest the optimal posting timing by comparing reactions on different platforms.

[0068] The reaction analysis unit can analyze the poster's industry and market trends in real time and suggest the next posting theme based on that information. The reaction analysis unit can, for example, analyze the poster's industry and market trends in real time and suggest the next posting theme based on that information. For example, it can reflect the latest technology trends and market needs. This allows the next posting theme to be optimized by analyzing industry and market trends in real time.

[0069] The reaction analysis unit can use the emotion estimation function to track changes in the viewer's emotions and suggest the next posting theme based on those changes. The reaction analysis unit can, for example, use the emotion estimation function to track changes in the viewer's emotions and suggest the next posting theme based on those changes. For example, it can select a theme that matches a period when emotions are high. In this way, by tracking changes in the viewer's emotions, the next posting theme can be optimized.

[0070] The response suggestion unit can analyze the viewer's comment history and suggest responses optimized for each viewer. The response suggestion unit, for example, analyzes the viewer's comment history and suggests responses optimized for each viewer. For example, it makes personalized replies based on the content of past comments. In this way, by suggesting responses optimized for each viewer, engagement with the viewer is increased.

[0071] The response suggestion unit can suggest personalized responses based on the viewer's profile information. The response suggestion unit, for example, suggests personalized responses based on the viewer's profile information. For example, it provides information related to the viewer's occupation or hobbies. In this way, by suggesting personalized responses based on the viewer's profile information, engagement with the viewer is increased.

[0072] The response suggestion unit can use the emotion estimation function to analyze the viewer's emotional state and suggest a response that matches that emotion. For example, the response suggestion unit uses the emotion estimation function to analyze the viewer's emotional state in real time and suggest a response that matches that emotion. For example, if the viewer is in a positive emotional state, words of encouragement or gratitude are used. This allows the response that matches the viewer's emotional state to be suggested, thereby increasing engagement with the viewer.

[0073] The response suggestion unit can analyze the effects of past responses to viewer comments and suggest the most effective response pattern. The response suggestion unit, for example, analyzes the effects of past responses to viewer comments and suggests the most effective response pattern. For example, the suggestion is made based on responses that have received high engagement in the past. In this way, the most effective response pattern can be suggested by analyzing the effects of past responses.

[0074] The response suggestion unit can suggest related additional information and links based on the content of the viewer's comment, promoting deeper engagement. The response suggestion unit, for example, analyzes the content of the viewer's comment and suggests related additional information and links. For example, it provides links to articles or product pages related to the comment. In this way, by suggesting related additional information and links, engagement with the viewer is deepened.

[0075] The response suggestion unit can use the emotion estimation function to identify the viewer's emotional needs and suggest a response that meets those needs. For example, the response suggestion unit uses the emotion estimation function to identify the viewer's emotional needs and suggest a response that meets those needs. For example, if the viewer is emotionally excited, words of congratulation or praise may be used. This increases engagement with the viewer by suggesting a response that meets the viewer's emotional needs.

[0076] The multimodal support unit can perform a detailed analysis of the content of images, audio, and video, and suggest optimal captions and tags for each. The multimodal support unit can, for example, perform a detailed analysis of the content of images, audio, and video, and suggest optimal captions and tags for each. For example, it can recognize objects and scenes within an image and generate captions based on them. This allows the unit to suggest optimal captions and tags by performing a detailed analysis of the content of images, audio, and video.

[0077] The multimodal support unit can combine multimodal data to generate more effective post content. The multimodal support unit can combine, for example, image, audio, and video data to generate more effective post content. For example, a slideshow combining images and audio can be created. In this way, by combining multimodal data, more effective post content can be generated.

[0078] The multimodal support unit can use the emotion estimation function to predict the emotional impact that multimodal data will have on viewers and make suggestions to maximize that impact. For example, the multimodal support unit uses the emotion estimation function to predict the emotional impact that multimodal data will have on viewers. For example, it evaluates whether a combination of image and audio evokes emotion. This maximizes the emotional impact that multimodal data will have on viewers, thereby increasing the effectiveness of posts.

[0079] The multimodal support unit can automatically analyze legal risks associated with the content of images, audio, and video, and make specific suggestions to reduce those risks. For example, the multimodal support unit analyzes the content of images to identify risks related to copyright and trademark rights. For example, if an image being used may be infringing copyright, the unit will suggest alternative solutions. This reduces the legal risks associated with the content of images, audio, and video, thereby increasing the safety of posts.

[0080] The multimodal support unit can make suggestions for optimizing multimodal data for posting on different social media platforms. The multimodal support unit makes suggestions for optimizing, for example, image, audio, and video data for different social media platforms. For example, it proposes data conversion to match the formats and specifications of each platform. This improves the effectiveness of posting by optimizing the multimodal data for different social media platforms.

[0081] The multimodal support unit can use the emotion estimation function to monitor the emotional impact of multimodal data on viewers in real time and make suggestions to maximize that impact. The multimodal support unit, for example, uses the emotion estimation function to monitor the emotional impact of multimodal data on viewers in real time. For example, it analyzes viewers' emotional reactions while a video is being played. This increases the effectiveness of posts by monitoring the emotional impact of multimodal data on viewers in real time.

[0082] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0083] The post optimization unit can analyze a poster's past posting history and suggest expressions optimized for each individual poster. For example, it can analyze a poster's past posting history and extract the characteristics of posts that have received particularly high engagement. It can analyze the frequency of use of specific phrases and keywords and reflect these in the next post. This makes it possible to increase the effectiveness of posts by suggesting the optimal expression based on the poster's past posting history. It can also analyze viewers' reactions to the poster's past posts and suggest expressions that will elicit positive reactions. It can also make suggestions to reduce the risk of negative reactions to the poster's past posts.

[0084] The post optimization unit can incorporate real-time trend information for post content and suggest ways of expressing it that are in line with the latest trends. For example, it can collect real-time trend information and reflect it in post content. It can also suggest currently popular hashtags and keywords and incorporate them into posts. This allows the effectiveness of posts to be maximized by incorporating real-time trend information. It can also provide specific advice for optimizing post content based on trend information. It can also suggest the next topic that the poster should focus on based on trend information.

[0085] The post optimization unit can use the emotion estimation function to analyze the poster's emotional state and suggest a way of expression that matches that emotion. For example, it can analyze the poster's emotional state in real time and suggest a way of expression that matches that emotion. If the poster's emotional state is positive, it can recommend bright and positive expressions. If the poster's emotional state is negative, it can suggest calm and collected expressions. This can increase the effectiveness of posts by suggesting a way of expression that matches the poster's emotional state. It can also adjust the tone and style of the post content based on the emotional state. It can also make suggestions to reduce risks according to the emotional state.

[0086] The Post Optimization Unit can automatically analyze the legal risks of posted content and make specific suggestions to reduce those risks. For example, it can analyze the content of a post and identify risks related to copyright and trademark rights. If the images or music used may be infringing copyright, it can suggest alternatives. This reduces legal risks and increases the safety of posts. It can also check whether the content of a post violates specific laws or regulations and suggest corrections as necessary. It can also provide specific advice to avoid legal risks.

[0087] The post optimization unit can evaluate the cultural and regional suitability of post content and suggest ways of expressing it that are appropriate for different cultural spheres. For example, it can analyze the content of a post and evaluate its suitability in different cultural spheres. If consideration for a specific culture or religion is required, it can suggest ways of expressing it that take that into account. This can increase the effectiveness of posts by suggesting ways of expressing it that are appropriate for different cultural spheres. It can also suggest ways to reduce risks that take cultural and regional suitability into account. It can also provide specific advice for optimizing post content based on trend information in different cultural spheres.

[0088] The post optimization unit can use the emotion estimation function to predict the emotional impact that the content of a post will have on viewers and suggest ways of expressing it to maximize that impact. For example, the emotion estimation function can be used to predict the emotional impact that the content of a post will have on viewers. Expression methods that will elicit positive emotions can be suggested. Risk reduction suggestions can also be made to avoid negative emotions. This can increase the effectiveness of posts by maximizing the emotional impact on viewers. The tone and style of the content of posts can also be adjusted based on the emotional impact. Furthermore, the unit can suggest the next post theme taking the emotional impact into consideration.

[0089] The reaction analysis unit can analyze viewer reaction data over time to identify the period during which a post's effectiveness will last. For example, it can analyze viewer reaction data over time to identify the period during which a post's effectiveness will last. It can analyze the timing at which the increase in likes and comments reaches its peak. This identifies the period during which a post's effectiveness will last, allowing the timing of the next post to be optimized. It can also provide specific advice based on the reaction data to extend the period during which a post's effectiveness lasts. It can also suggest the next post theme based on the period during which a post's effectiveness lasts.

[0090] The reaction analysis unit can perform a detailed analysis of the interests of the poster's followers based on the reaction data and suggest the next posting theme. For example, the reaction data can be used to perform a detailed analysis of the interests of the poster's followers. The reaction to a specific topic or theme can be analyzed and the next posting theme can be suggested. This allows the next posting theme to be optimized by analyzing the interests of the followers in detail. It can also provide specific advice for optimizing the content of the post based on the interests of the followers. It can also make risk reduction suggestions that take into account the interests of the followers.

[0091] The reaction analysis unit can use the emotion estimation function to analyze the viewer's emotional reaction and suggest the next post theme that will elicit positive emotions. For example, the emotion estimation function can be used to analyze the viewer's emotional reaction and suggest the next post theme that will elicit positive emotions. The system selects themes that evoke emotion and joy. This allows the system to increase viewer engagement by suggesting the next post theme that will elicit positive emotions. The system can also adjust the tone and style of the post content based on the emotional reaction. Furthermore, it can also make risk reduction suggestions that take emotional reactions into account.

[0092] The reaction analysis unit can compare reactions on different social media platforms based on reaction data and suggest the optimal posting timing. For example, it can compare reaction data on different social media platforms and suggest the optimal posting timing. It can identify the peak reaction times on each platform. This allows it to suggest the optimal posting timing by comparing reactions on different platforms. It can also provide specific advice for optimizing posting content based on differences in reactions on each platform. It can also suggest risk reduction measures that take into account reactions on each platform.

[0093] The processing flow of the second embodiment will be briefly explained below.

[0094] Step 1: The post optimization unit uses RAG (Search Augmentation Generation) to suggest optimal ways to express content and risk reduction for posts created by posters. For example, if a poster posts an "introduction to a new product," RAG searches for related information and suggests more effective ways to express content and risks to be aware of. The input to the generation AI is a prompt containing instructions on what the poster wants the generation AI to do, and the generation AI generates optimal suggestions based on that prompt. Step 2: After posting, the generation AI analyzes viewer reactions (likes, comments, shares, etc.) and suggests the next post theme based on that data. For example, if a specific post receives many reactions, the generation AI will suggest a theme related to that post as the next post. The input to the generation AI is viewer reaction data, and the generation AI generates the next post theme based on that data. Step 3: In the response suggestion section, the generation AI suggests an appropriate response to close the gap with the viewer. For example, in response to a comment from a viewer, the generation AI suggests an appropriate reply, helping the poster reply quickly and effectively. The input to the generation AI is the comment or message from the viewer, and the generation AI generates an appropriate response based on that content. Step 4: The multimodal support unit supports not only text-based social media posts, but also multimodal posts such as images, audio, and video. For example, when posting an image, the generative AI analyzes the content of the image and suggests optimal captions and tags. Similarly, for audio and video posts, the generative AI analyzes the content and suggests appropriate ways to express it and reduce risks. The input to the generative AI is image, audio, and video data, and the generative AI generates optimal suggestions based on that data.

[0095] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0096] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0097] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0098] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0099] 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.

[0100] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0101] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0102] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0103] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0104] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0105] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0106] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0107] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0108] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0109] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0111] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0112] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0113] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0114] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0115] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0116] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0117] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0119] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0120] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0121] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0123] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0124] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0125] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0127] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0128] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0129] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0130] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0131] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0132] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0134] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0135] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0136] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0137] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0138] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0139] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0140] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0141] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0143] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0144] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0145] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0146] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0147] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0148] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0149] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0150] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0151] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0152] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0153] 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.

[0154] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0155] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0156] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0157] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0158] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0159] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0160] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0161] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0162] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A posting optimization part using RAG, a reaction analysis unit that analyzes the post content optimized by the post optimization unit; a response suggestion unit that suggests a next posting theme based on the reactions analyzed by the reaction analysis unit; a multimodal support unit that supports multimodal posting based on the next posting theme proposed by the response suggestion unit. A system characterized by:

2. The post optimization unit Incorporating real-time trend information into the posted content and suggesting ways to express it in line with the latest trends The system of claim 1 .

3. The reaction analysis unit Analyze viewer reaction data over time to identify how long the effect of the post will last. The system of claim 1 .

4. The response proposal unit Analyzes the viewer's comment history and proposes responses optimized for each viewer The system of claim 1 .

5. The multimodal support section includes: Analyzes the content of images, audio, and videos in detail and suggests the best captions and tags for each. The system of claim 1 .

6. The post optimization unit Using emotion estimation function, we analyze the poster's emotional state and suggest ways to express themselves that match their emotions. The system of claim 1 .

7. The reaction analysis unit Using emotion estimation, the app analyzes viewers' emotional responses and suggests the next post topic that will elicit positive emotions. The system of claim 1 .

8. The multimodal support section includes: Using emotion estimation, the system predicts the emotional impact of the multimodal data on the viewer and makes suggestions to maximize that impact. The system of claim 1 .

Images