system

Abstract

The system according to this embodiment aims to efficiently perform content creation, posting time optimization, engagement prediction, and trend analysis in social media marketing. [Solution] The system according to the embodiment comprises a content generation unit, a post analysis unit, an automatic posting unit, an engagement prediction unit, and a trend analysis unit. The content generation unit generates content. The post analysis unit analyzes the optimal posting time for the content generated by the content generation unit. The automatic posting unit automatically posts based on the results analyzed by the post analysis unit. The engagement prediction unit predicts the engagement of the content posted by the automatic posting unit. The trend analysis unit performs trend analysis and makes suggestions based on the results predicted by the engagement prediction unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that in SNS marketing, optimization of content creation and posting time, engagement prediction, and trend analysis are complicated and difficult to perform efficiently.

[0005] The system according to the embodiment aims to efficiently perform content creation, optimization of posting time, engagement prediction, and trend analysis in SNS marketing.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a content generation unit, a post analysis unit, an automated posting unit, an engagement prediction unit, and a trend analysis unit. The content generation unit generates content. The post analysis unit analyzes the optimal posting time for the content generated by the content generation unit. The automated posting unit automatically posts content based on the results analyzed by the post analysis unit. The engagement prediction unit predicts the engagement of content posted by the automated posting unit. The trend analysis unit performs trend analysis and makes suggestions based on the results predicted by the engagement prediction unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently perform content creation, posting time optimization, engagement prediction, and trend analysis in social media marketing. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the signed communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of 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), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The AI ​​agent system according to an embodiment of the present invention is a system for reducing the burden of content creation in SNS marketing and realizing effective marketing strategies. This AI agent system consists of the following steps. First, the AI ​​agent automatically generates content. In this process, the AI ​​analyzes past posting data and trend information to generate content that is optimal for the target audience. For example, it can automatically create posts tailored to specific events or seasons. This significantly reduces the time and effort required for content creation. Next, the AI ​​analyzes the optimal posting time for the generated content and automatically posts it. The AI ​​analyzes past posting data and engagement data to identify the time of day when the target audience is most active. For example, posting on specific days of the week or at specific times can maximize the engagement rate. This enables the realization of effective marketing strategies. Furthermore, it performs engagement prediction and provides trend analysis and suggestions. The AI ​​analyzes past engagement data and trend information to predict future engagement. For example, it can predict how much engagement a particular post will receive and adjust the content and timing of posts based on the results. It also performs trend analysis and proposes content based on the latest trends, ensuring that the latest information is always disseminated. This system reduces the burden of content creation in social media marketing, enabling the implementation of effective marketing strategies. It can provide effective digital communication to all target audiences using social media, including companies, influencers, marketing professionals, and freelancers. As a result, the AI ​​agent system reduces the burden of content creation in social media marketing, enabling the implementation of effective marketing strategies.

[0029] The AI ​​agent system according to this embodiment comprises a content generation unit, a post analysis unit, an automatic posting unit, an engagement prediction unit, and a trend analysis unit. The content generation unit generates content. The content generation unit, for example, analyzes past posting data and trend information to generate content that is optimal for the target audience. For example, the content generation unit can automatically create posts tailored to specific events or seasons. The content generation unit, for example, can generate content related to specific events. The content generation unit, for example, can generate content related to seasons. The content generation unit, for example, can generate content based on the interests of the target audience. The post analysis unit analyzes the optimal posting time for the generated content. The post analysis unit, for example, analyzes past posting data and engagement data to identify the time of day when the target audience is most active. The post analysis unit, for example, can maximize the engagement rate by posting on specific days of the week or time of day. The post analysis unit, for example, can identify the activity times of the target audience. The post analysis unit, for example, can analyze past engagement data. The post analysis unit can, for example, analyze the behavior patterns of the target audience. The automated posting unit automatically posts based on the results analyzed by the post analysis unit. The automated posting unit can, for example, post on specific days of the week or at specific times. The automated posting unit can, for example, post during the times when the target audience is most active. The automated posting unit can, for example, post to maximize the engagement rate. The automated posting unit can, for example, post in conjunction with specific events. The automated posting unit can, for example, post in conjunction with specific campaigns. The automated posting unit can, for example, post based on the behavior patterns of the target audience. The engagement prediction unit predicts the engagement of content posted by the automated posting unit. The engagement prediction unit can, for example, analyze past engagement data and trend information to predict future engagement. The engagement prediction unit can, for example, predict how much engagement a particular post will receive.The engagement prediction unit provides information for adjusting post content and timing, for example. The engagement prediction unit predicts the target audience's response, for example. The engagement prediction unit provides information for maximizing the engagement rate, for example. The engagement prediction unit analyzes the target audience's behavior patterns, for example. The trend analysis unit performs trend analysis and makes suggestions based on the results predicted by the engagement prediction unit. The trend analysis unit suggests content based on the latest trends, for example. The trend analysis unit suggests content to always provide the latest information, for example. The trend analysis unit suggests content based on the target audience's interests, for example. The trend analysis unit suggests content tailored to specific events or seasons, for example. The trend analysis unit suggests content based on the target audience's behavior patterns, for example. The trend analysis unit suggests content to maximize the engagement rate, for example. As a result, the AI ​​agent system according to the embodiment can reduce the burden of content creation in SNS marketing and realize an effective marketing strategy.

[0030] The content generation unit generates content. For example, it analyzes past posting data and trend information to generate content that is optimal for the target audience. Specifically, the content generation unit uses natural language processing technology to analyze past posting data and learn what kind of content is likely to be well-received by the target audience. For example, it extracts keywords and phrases related to specific events or seasons and generates new content based on them. It can also use image generation technology to create visual content that matches events and seasons. For example, during the Christmas season, it can generate images of Christmas trees and Santa Claus and add related messages to attract the attention of the target audience. Furthermore, the content generation unit can also generate personalized content based on the interests of the target audience. For example, if a particular group of users is interested in sports, it can generate sports-related content for that group. This allows the content generation unit to provide more effective content to the target audience and increase engagement.

[0031] The Post Analysis Department analyzes the optimal posting time for generated content. For example, it analyzes past posting data and engagement data to identify the times when the target audience is most active. Specifically, the Post Analysis Department analyzes past posting data in chronological order to identify when posts receive the most engagement. It also analyzes the behavior patterns of the target audience to understand which days or times have the most active users. For example, if many users are using social media during weekday lunch breaks or evenings, posting during those times can maximize engagement. Furthermore, the Post Analysis Department can adjust the optimal posting time considering the target audience's region and time zone. This allows the Post Analysis Department to deliver content to the target audience at the most effective time, thereby increasing engagement.

[0032] The automated posting unit automatically posts content based on the results analyzed by the post analysis unit. For example, the automated posting unit posts on specific days of the week or at specific times. Specifically, it automatically posts content according to a pre-scheduled schedule based on the optimal posting time provided by the post analysis unit. This eliminates the need for marketing personnel to manually post content. Furthermore, the automated posting unit can maximize engagement rates by posting during the times when the target audience is most active. For example, when posting for a specific event or campaign, the automated posting unit can schedule posts to coincide with the event's start time or the campaign's duration. Additionally, the automated posting unit can adjust post content based on the target audience's behavior patterns. For instance, if a specific user group is active during certain times, posting during those times can increase engagement. This allows the automated posting unit to post efficiently and effectively, supporting the implementation of marketing strategies.

[0033] The engagement prediction unit predicts the engagement of content posted by the automated posting unit. For example, the engagement prediction unit analyzes past engagement data and trend information to predict future engagement. Specifically, the engagement prediction unit uses machine learning algorithms to learn from past posting data and predict how much engagement a particular post will receive. For example, if posts containing certain keywords or hashtags tend to receive high engagement, this information can be used to adjust future posting content. The engagement prediction unit also predicts the target audience's response and provides information to optimize posting content and timing. For example, if a particular user group shows high engagement with a specific piece of content, providing similar content to that group can maximize the engagement rate. In this way, the engagement prediction unit provides important information to enhance the effectiveness of marketing strategies and strengthen relationships with target audiences.

[0034] The Trend Analysis Department performs trend analysis and makes recommendations based on the results predicted by the Engagement Forecasting Department. For example, the Trend Analysis Department proposes content based on the latest trends. Specifically, the Trend Analysis Department monitors the latest trends and topics on social media in real time and makes content recommendations based on that. For example, if a particular hashtag is rapidly gaining popularity, creating content that includes that hashtag can attract the interest of the target audience. The Trend Analysis Department can also propose content based on the interests of the target audience. For example, if a particular user group is interested in a particular topic, suggesting content related to that topic can increase engagement. Furthermore, the Trend Analysis Department can also propose content tailored to specific events or seasons. For example, suggesting content tailored to seasonal events such as Halloween or Christmas can attract the interest of the target audience. In this way, the Trend Analysis Department can always provide content based on the latest information and maximize the effectiveness of marketing strategies.

[0035] The content generation unit can analyze past posting data and trend information to generate content optimized for the target audience. For example, the content generation unit can analyze past posting data and generate content based on the target audience's interests. For example, the content generation unit can analyze trend information and generate content based on the latest trends. For example, the content generation unit can generate content tailored to specific events or seasons. This improves engagement by generating content optimized for the target audience. Some or all of the above processes in the content generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the content generation unit can input past posting data and trend information into a generation AI and have the generation AI generate content optimized for the target audience.

[0036] The post analysis unit can analyze past post data and engagement data to identify the time of day when the target audience is most active. For example, the post analysis unit can analyze past post data to identify the target audience's activity times. For example, the post analysis unit can analyze engagement data to identify the time of day when the target audience is most active. For example, the post analysis unit can analyze the target audience's behavior patterns to identify the optimal posting time. This maximizes the engagement rate by posting during the time of day when the target audience is most active. Some or all of the above processing in the post analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the post analysis unit can input past post data and engagement data into a generative AI and have the generative AI identify the time of day when the target audience is most active.

[0037] The automated posting unit can post on specific days of the week and at specific times. For example, the automated posting unit can post on specific days of the week. For example, the automated posting unit can post at specific times. For example, the automated posting unit can post during the times when the target audience is most active. By posting on specific days of the week and at specific times, engagement rates can be improved. Some or all of the above processes in the automated posting unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the automated posting unit can have a generative AI execute posts on specific days of the week and at specific times.

[0038] The engagement prediction unit can analyze past engagement data and trend information to predict future engagement. For example, the engagement prediction unit can analyze past engagement data to predict future engagement. For example, the engagement prediction unit can analyze trend information to predict future engagement. For example, the engagement prediction unit can predict how much engagement a particular post will receive. This allows for the optimization of post content and timing by predicting future engagement. Some or all of the above-described processes in the engagement prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the engagement prediction unit can input past engagement data and trend information into a generative AI and have the generative AI perform a prediction of future engagement.

[0039] The trend analysis department can propose content based on the latest trends. For example, the trend analysis department can analyze the latest trends and propose content that is best suited to the target audience. For example, the trend analysis department can propose content tailored to specific events or seasons. For example, the trend analysis department can propose content based on the interests of the target audience. This ensures that the latest information is always disseminated by proposing content based on the latest trends. Some or all of the above processes in the trend analysis department may be performed using, for example, a generative AI, or not using a generative AI. For example, the trend analysis department can input the latest trend information into a generative AI and have the generative AI propose content that is best suited to the target audience.

[0040] The content generation unit can automatically select themes that match specific events or seasons. For example, during the Christmas season, the content generation unit generates content with Christmas-related themes. For example, during the summer holidays, the content generation unit generates content with travel and leisure-related themes. For example, during the start of the new school year, the content generation unit generates content with school and education-related themes. This attracts the interest of the target audience by generating content with themes that match specific events or seasons. Some or all of the above-described processes in the content generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the content generation unit can input information about specific events or seasons into the generation AI and have the generation AI perform theme selection.

[0041] The content generation unit can analyze the target audience's past responses and select the most effective content format. For example, the content generation unit may prioritize generating video content that has received high engagement in the past. For example, the content generation unit may generate infographic content that has received many shares in the past. For example, the content generation unit may generate blog content that has received many comments in the past. This improves engagement by selecting the most effective content format based on past responses. Some or all of the above processing in the content generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the content generation unit can input past response data of the target audience into a generation AI and have the generation AI select the most effective content format.

[0042] The content generation unit can generate localized content that takes into account the geographical location of the target audience. For example, if the target audience is in Japan, the content generation unit will generate content related to Japanese culture and events. For example, if the target audience is in the United States, the content generation unit will generate content related to American trends and news. For example, if the target audience is in Europe, the content generation unit will generate content related to European history and tourist destinations. This will attract the interest of the target audience by generating localized content that takes geographical location into account. Some or all of the above processing in the content generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the content generation unit can input the geographical location of the target audience into a generation AI and have the generation AI generate localized content.

[0043] The content generation unit can analyze the social media activity of the target audience and incorporate relevant topics. For example, the content generation unit can generate content based on topics that the target audience frequently shares. For example, the content generation unit can generate content based on topics that the target audience has commented on many times. For example, the content generation unit can generate content based on topics that the target audience has given many "likes" to. In this way, by analyzing the social media activity of the target audience, it is possible to generate content that incorporates relevant topics. Some or all of the above processing in the content generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the content generation unit can input social media activity data of the target audience into a generation AI and have the generation AI perform the incorporation of relevant topics.

[0044] The post analysis unit can identify engagement patterns for specific days of the week and time slots based on past post data. For example, the post analysis unit can identify from past data that high engagement is obtained on Monday mornings. For example, the post analysis unit can identify from past data that high engagement is obtained on Friday evenings. For example, the post analysis unit can identify from past data that high engagement is obtained on Wednesday afternoons. By identifying engagement patterns for specific days of the week and time slots, the optimal posting time can be found. Some or all of the above processing in the post analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the post analysis unit can input past post data into a generative AI and have the generative AI identify engagement patterns for specific days of the week and time slots.

[0045] The post analysis unit can monitor the target audience's online activity time in real time and dynamically adjust the optimal posting time. For example, the post analysis unit can post the moment the target audience comes online. For example, the post analysis unit can post when the target audience's online activity reaches its peak. For example, the post analysis unit can post before the target audience's online activity decreases. In this way, the optimal posting time can be dynamically adjusted by monitoring the target audience's online activity time in real time. Some or all of the above processing in the post analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the post analysis unit can input the target audience's online activity data into a generative AI and have the generative AI perform a dynamic adjustment of the optimal posting time.

[0046] The post analysis unit can determine the optimal posting time by considering the geographical location of the target audience. For example, if the target audience is in Japan, the post analysis unit will post according to Japan Standard Time. For example, if the target audience is in the United States, the post analysis unit will post according to US Standard Time. For example, if the target audience is in Europe, the post analysis unit will post according to European Standard Time. This improves engagement by determining the optimal posting time that takes geographical location into account. Some or all of the above processing in the post analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the post analysis unit can input the geographical location information of the target audience into a generative AI and have the generative AI determine the optimal posting time.

[0047] The post analysis unit can analyze the social media activity of the target audience and identify the optimal posting time. For example, the post analysis unit might post during times when the target audience is frequently online. For example, the post analysis unit might post during times when the target audience is leaving many comments. For example, the post analysis unit might post during times when the target audience is giving many "likes". In this way, the optimal posting time can be identified by analyzing the social media activity of the target audience. Some or all of the above processing in the post analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the post analysis unit can input social media activity data of the target audience into a generative AI and have the generative AI identify the optimal posting time.

[0048] The automated posting function can customize its content to suit specific days of the week and times of day. For example, on Monday mornings, it might post motivational content suitable for the start of the week. On Friday evenings, it might post content suitable for relaxing on the weekend. On holidays, it might post content related to the holiday. By customizing content to suit specific days of the week and times of day, engagement can be improved. Some or all of the above processing in the automated posting function may be performed using, for example, a generative AI, or not. For example, the automated posting function can input information about specific days of the week and times of day into a generative AI and have the generative AI perform the customization of the post content.

[0049] The automated posting unit can optimize post content based on past reactions from the target audience. For example, the automated posting unit can reuse post content that has received high engagement in the past. For example, the automated posting unit can create new posts based on post content that has received many shares in the past. For example, the automated posting unit can create new posts based on post content that has received many comments in the past. This improves engagement by optimizing post content based on past reactions. Some or all of the above processes in the automated posting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the automated posting unit can input past reaction data from the target audience into a generative AI and have the generative AI perform the optimization of post content.

[0050] The automated posting unit can localize post content by taking into account the geographical location of the target audience. For example, if the target audience is in Japan, the automated posting unit will post content related to Japanese culture and events. For example, if the target audience is in the United States, the automated posting unit will post content related to American trends and news. For example, if the target audience is in Europe, the automated posting unit will post content related to European history and tourist destinations. This attracts the interest of the target audience by providing localized post content that takes geographical location into account. Some or all of the above processing in the automated posting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the automated posting unit can input the geographical location information of the target audience into a generative AI and have the generative AI perform the localization of the post content.

[0051] The automated posting unit can analyze the social media activity of the target audience and incorporate relevant topics. For example, the automated posting unit can post based on topics that the target audience frequently shares. For example, the automated posting unit can post based on topics that the target audience has commented on many times. For example, the automated posting unit can post based on topics that the target audience has given many "likes" to. In this way, by analyzing the social media activity of the target audience, it is possible to provide posts that incorporate relevant topics. Some or all of the above processing in the automated posting unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the automated posting unit can input social media activity data of the target audience into a generative AI and have the generative AI perform the incorporation of relevant topics.

[0052] The engagement prediction unit can predict the effectiveness of a specific post format based on past engagement data. For example, the engagement prediction unit can predict the effectiveness of video posts that have received high engagement in the past. For example, the engagement prediction unit can predict the effectiveness of infographic posts that have received many shares in the past. For example, the engagement prediction unit can predict the effectiveness of blog posts that have received many comments in the past. In this way, engagement is improved by predicting the effectiveness of a specific post format based on past engagement data. Some or all of the above processing in the engagement prediction unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the engagement prediction unit can input past engagement data into a generative AI and have the generative AI perform a prediction of the effectiveness of a specific post format.

[0053] The engagement prediction unit can improve prediction accuracy by considering the attribute information of the target audience. For example, the engagement prediction unit performs engagement prediction by considering the age group of the target audience. For example, the engagement prediction unit performs engagement prediction by considering the gender of the target audience. For example, the engagement prediction unit performs engagement prediction by considering the interests of the target audience. In this way, the accuracy of engagement prediction is improved by considering the attribute information of the target audience. Some or all of the above processing in the engagement prediction unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the engagement prediction unit can input the attribute information of the target audience into a generative AI and have the generative AI perform the improvement of prediction accuracy.

[0054] The engagement prediction unit can improve prediction accuracy by considering the geographical location information of the target audience. For example, if the target audience is in Japan, the engagement prediction unit will perform an engagement prediction based on Japan Standard Time. For example, if the target audience is in the United States, the engagement prediction unit will perform an engagement prediction based on US Standard Time. For example, if the target audience is in Europe, the engagement prediction unit will perform an engagement prediction based on European Standard Time. This improves the accuracy of the engagement prediction by considering geographical location information. Some or all of the above processing in the engagement prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the engagement prediction unit can input the geographical location information of the target audience into a generative AI and have the generative AI perform the improvement of prediction accuracy.

[0055] The engagement prediction unit can analyze the social media activity of the target audience and improve prediction accuracy. For example, the engagement prediction unit predicts the engagement of posts that the target audience frequently shares. For example, the engagement prediction unit predicts the engagement of posts that the target audience has left many comments on. For example, the engagement prediction unit predicts the engagement of posts that the target audience has given many "likes" to. In this way, the accuracy of engagement prediction is improved by analyzing the social media activity of the target audience. Some or all of the above processing in the engagement prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the engagement prediction unit can input social media activity data of the target audience into a generative AI and have the generative AI perform the improvement of prediction accuracy.

[0056] The trend analysis unit can predict current trends based on past trend data. For example, the trend analysis unit predicts current trends from past data. For example, the trend analysis unit predicts future trends based on past trend data. For example, the trend analysis unit analyzes past trend data to identify factors that influence current trends. This allows the system to provide content based on the latest trends by predicting current trends based on past trend data. Some or all of the above processes in the trend analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the trend analysis unit can input past trend data into a generative AI and have the generative AI predict current trends.

[0057] The trend analysis unit can improve the accuracy of its analysis by considering the attribute information of the target audience. For example, the trend analysis unit performs trend analysis considering the age group of the target audience. For example, the trend analysis unit performs trend analysis considering the gender of the target audience. For example, the trend analysis unit performs trend analysis considering the interests of the target audience. In this way, the accuracy of the trend analysis is improved by considering the attribute information of the target audience. Some or all of the above processing in the trend analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the trend analysis unit can input the attribute information of the target audience into a generative AI and have the generative AI perform the improvement of the analysis accuracy.

[0058] The trend analysis unit can improve the accuracy of its analysis by considering the geographical location information of the target audience. For example, if the target audience is in Japan, the trend analysis unit will prioritize analyzing trends in Japan. For example, if the target audience is in the United States, the trend analysis unit will prioritize analyzing trends in the United States. For example, if the target audience is in Europe, the trend analysis unit will prioritize analyzing trends in Europe. This improves the accuracy of the trend analysis by considering geographical location information. Some or all of the above processing in the trend analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the trend analysis unit can input the geographical location information of the target audience into a generative AI and have the generative AI perform the improvement of the analysis accuracy.

[0059] The trend analysis unit can analyze the social media activity of the target audience and improve the accuracy of the analysis. For example, the trend analysis unit performs trend analysis based on topics that the target audience frequently shares. For example, the trend analysis unit performs trend analysis based on topics that the target audience has left many comments on. For example, the trend analysis unit performs trend analysis based on topics that the target audience has given many "likes" to. In this way, the accuracy of the trend analysis is improved by analyzing the social media activity of the target audience. Some or all of the above processing in the trend analysis unit may be performed using, for example, generative AI, or not using generative AI. For example, the trend analysis unit can input social media activity data of the target audience into generative AI and have the generative AI perform the improvement of analysis accuracy.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The content generation unit can generate localized content that takes into account the geographical location of the target audience. For example, if the target audience is in Japan, it can generate content related to Japanese culture and events. If the target audience is in the United States, it can generate content related to American trends and news. If the target audience is in Europe, it can generate content related to European history and tourist destinations. By generating localized content that takes geographical location into account, it is possible to attract the interest of the target audience.

[0062] The post analysis department can monitor the target audience's online activity time in real time and dynamically adjust the optimal posting time. For example, it can post the moment the target audience comes online, post when the target audience's online activity reaches its peak, or post before the target audience's online activity declines. In this way, by monitoring the target audience's online activity time in real time, the optimal posting time can be dynamically adjusted.

[0063] The automated posting function can customize post content to suit specific days of the week and times of day. For example, on Monday mornings, it can post motivational content suitable for the start of the week. On Friday evenings, it can post content suitable for relaxing on the weekend. On holidays, it can post content related to the holiday. By customizing post content to suit specific days of the week and times of day, engagement can be improved.

[0064] The engagement prediction unit can improve prediction accuracy by considering the attribute information of the target audience. For example, it can perform engagement predictions by considering the age group of the target audience. It can perform engagement predictions by considering the gender of the target audience. It can perform engagement predictions by considering the interests of the target audience. In this way, the accuracy of engagement predictions can be improved by considering the attribute information of the target audience.

[0065] The Trend Analysis Department can predict current trends based on past trend data. For example, it can predict current trends from past data. It can predict future trends based on past trend data. It can analyze past trend data and identify factors that influence current trends. As a result, by predicting current trends based on past trend data, it can provide content based on the latest trends.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The content generation unit generates content. For example, it analyzes past posting data and trend information to generate content that is optimal for the target audience. It can automatically create posts tailored to specific events or seasons. Step 2: The post analysis team analyzes the optimal posting time for the generated content. For example, they analyze past posting data and engagement data to identify the time slots when the target audience is most active. Step 3: The automated posting unit automatically posts based on the results analyzed by the posting analysis unit. For example, it might post on specific days of the week or at specific times, or post during the time when the target audience is most active. Step 4: The engagement prediction unit predicts the engagement of content posted by the automated posting unit. For example, it analyzes past engagement data and trend information to predict future engagement. Step 5: The Trend Analysis Department conducts trend analysis and makes recommendations based on the results predicted by the Engagement Forecasting Department. For example, they propose content based on the latest trends and content based on the interests of the target audience.

[0068] (Example of form 2) The AI ​​agent system according to an embodiment of the present invention is a system for reducing the burden of content creation in SNS marketing and realizing effective marketing strategies. This AI agent system consists of the following steps. First, the AI ​​agent automatically generates content. In this process, the AI ​​analyzes past posting data and trend information to generate content that is optimal for the target audience. For example, it can automatically create posts tailored to specific events or seasons. This significantly reduces the time and effort required for content creation. Next, the AI ​​analyzes the optimal posting time for the generated content and automatically posts it. The AI ​​analyzes past posting data and engagement data to identify the time of day when the target audience is most active. For example, posting on specific days of the week or at specific times can maximize the engagement rate. This enables the realization of effective marketing strategies. Furthermore, it performs engagement prediction and provides trend analysis and suggestions. The AI ​​analyzes past engagement data and trend information to predict future engagement. For example, it can predict how much engagement a particular post will receive and adjust the content and timing of posts based on the results. It also performs trend analysis and proposes content based on the latest trends, ensuring that the latest information is always disseminated. This system reduces the burden of content creation in social media marketing, enabling the implementation of effective marketing strategies. It can provide effective digital communication to all target audiences using social media, including companies, influencers, marketing professionals, and freelancers. As a result, the AI ​​agent system reduces the burden of content creation in social media marketing, enabling the implementation of effective marketing strategies.

[0069] The AI ​​agent system according to this embodiment comprises a content generation unit, a post analysis unit, an automatic posting unit, an engagement prediction unit, and a trend analysis unit. The content generation unit generates content. The content generation unit, for example, analyzes past posting data and trend information to generate content that is optimal for the target audience. For example, the content generation unit can automatically create posts tailored to specific events or seasons. The content generation unit, for example, can generate content related to specific events. The content generation unit, for example, can generate content related to seasons. The content generation unit, for example, can generate content based on the interests of the target audience. The post analysis unit analyzes the optimal posting time for the generated content. The post analysis unit, for example, analyzes past posting data and engagement data to identify the time of day when the target audience is most active. The post analysis unit, for example, can maximize the engagement rate by posting on specific days of the week or time of day. The post analysis unit, for example, can identify the activity times of the target audience. The post analysis unit, for example, can analyze past engagement data. The post analysis unit can, for example, analyze the behavior patterns of the target audience. The automated posting unit automatically posts based on the results analyzed by the post analysis unit. The automated posting unit can, for example, post on specific days of the week or at specific times. The automated posting unit can, for example, post during the times when the target audience is most active. The automated posting unit can, for example, post to maximize the engagement rate. The automated posting unit can, for example, post in conjunction with specific events. The automated posting unit can, for example, post in conjunction with specific campaigns. The automated posting unit can, for example, post based on the behavior patterns of the target audience. The engagement prediction unit predicts the engagement of content posted by the automated posting unit. The engagement prediction unit can, for example, analyze past engagement data and trend information to predict future engagement. The engagement prediction unit can, for example, predict how much engagement a particular post will receive.The engagement prediction unit provides information for adjusting post content and timing, for example. The engagement prediction unit predicts the target audience's response, for example. The engagement prediction unit provides information for maximizing the engagement rate, for example. The engagement prediction unit analyzes the target audience's behavior patterns, for example. The trend analysis unit performs trend analysis and makes suggestions based on the results predicted by the engagement prediction unit. The trend analysis unit suggests content based on the latest trends, for example. The trend analysis unit suggests content to always provide the latest information, for example. The trend analysis unit suggests content based on the target audience's interests, for example. The trend analysis unit suggests content tailored to specific events or seasons, for example. The trend analysis unit suggests content based on the target audience's behavior patterns, for example. The trend analysis unit suggests content to maximize the engagement rate, for example. As a result, the AI ​​agent system according to the embodiment can reduce the burden of content creation in SNS marketing and realize an effective marketing strategy.

[0070] The content generation unit generates content. For example, it analyzes past posting data and trend information to generate content that is optimal for the target audience. Specifically, the content generation unit uses natural language processing technology to analyze past posting data and learn what kind of content is likely to be well-received by the target audience. For example, it extracts keywords and phrases related to specific events or seasons and generates new content based on them. It can also use image generation technology to create visual content that matches events and seasons. For example, during the Christmas season, it can generate images of Christmas trees and Santa Claus and add related messages to attract the attention of the target audience. Furthermore, the content generation unit can also generate personalized content based on the interests of the target audience. For example, if a particular group of users is interested in sports, it can generate sports-related content for that group. This allows the content generation unit to provide more effective content to the target audience and increase engagement.

[0071] The Post Analysis Department analyzes the optimal posting time for generated content. For example, it analyzes past posting data and engagement data to identify the times when the target audience is most active. Specifically, the Post Analysis Department analyzes past posting data in chronological order to identify when posts receive the most engagement. It also analyzes the behavior patterns of the target audience to understand which days or times have the most active users. For example, if many users are using social media during weekday lunch breaks or evenings, posting during those times can maximize engagement. Furthermore, the Post Analysis Department can adjust the optimal posting time considering the target audience's region and time zone. This allows the Post Analysis Department to deliver content to the target audience at the most effective time, thereby increasing engagement.

[0072] The automated posting unit automatically posts content based on the results analyzed by the post analysis unit. For example, the automated posting unit posts on specific days of the week or at specific times. Specifically, it automatically posts content according to a pre-scheduled schedule based on the optimal posting time provided by the post analysis unit. This eliminates the need for marketing personnel to manually post content. Furthermore, the automated posting unit can maximize engagement rates by posting during the times when the target audience is most active. For example, when posting for a specific event or campaign, the automated posting unit can schedule posts to coincide with the event's start time or the campaign's duration. Additionally, the automated posting unit can adjust post content based on the target audience's behavior patterns. For instance, if a specific user group is active during certain times, posting during those times can increase engagement. This allows the automated posting unit to post efficiently and effectively, supporting the implementation of marketing strategies.

[0073] The engagement prediction unit predicts the engagement of content posted by the automated posting unit. For example, the engagement prediction unit analyzes past engagement data and trend information to predict future engagement. Specifically, the engagement prediction unit uses machine learning algorithms to learn from past posting data and predict how much engagement a particular post will receive. For example, if posts containing certain keywords or hashtags tend to receive high engagement, this information can be used to adjust future posting content. The engagement prediction unit also predicts the target audience's response and provides information to optimize posting content and timing. For example, if a particular user group shows high engagement with a specific piece of content, providing similar content to that group can maximize the engagement rate. In this way, the engagement prediction unit provides important information to enhance the effectiveness of marketing strategies and strengthen relationships with target audiences.

[0074] The Trend Analysis Department performs trend analysis and makes recommendations based on the results predicted by the Engagement Forecasting Department. For example, the Trend Analysis Department proposes content based on the latest trends. Specifically, the Trend Analysis Department monitors the latest trends and topics on social media in real time and makes content recommendations based on that. For example, if a particular hashtag is rapidly gaining popularity, creating content that includes that hashtag can attract the interest of the target audience. The Trend Analysis Department can also propose content based on the interests of the target audience. For example, if a particular user group is interested in a particular topic, suggesting content related to that topic can increase engagement. Furthermore, the Trend Analysis Department can also propose content tailored to specific events or seasons. For example, suggesting content tailored to seasonal events such as Halloween or Christmas can attract the interest of the target audience. In this way, the Trend Analysis Department can always provide content based on the latest information and maximize the effectiveness of marketing strategies.

[0075] The content generation unit can analyze past posting data and trend information to generate content optimized for the target audience. For example, the content generation unit can analyze past posting data and generate content based on the target audience's interests. For example, the content generation unit can analyze trend information and generate content based on the latest trends. For example, the content generation unit can generate content tailored to specific events or seasons. This improves engagement by generating content optimized for the target audience. Some or all of the above processes in the content generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the content generation unit can input past posting data and trend information into a generation AI and have the generation AI generate content optimized for the target audience.

[0076] The post analysis unit can analyze past post data and engagement data to identify the time of day when the target audience is most active. For example, the post analysis unit can analyze past post data to identify the target audience's activity times. For example, the post analysis unit can analyze engagement data to identify the time of day when the target audience is most active. For example, the post analysis unit can analyze the target audience's behavior patterns to identify the optimal posting time. This maximizes the engagement rate by posting during the time of day when the target audience is most active. Some or all of the above processing in the post analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the post analysis unit can input past post data and engagement data into a generative AI and have the generative AI identify the time of day when the target audience is most active.

[0077] The automated posting unit can post on specific days of the week and at specific times. For example, the automated posting unit can post on specific days of the week. For example, the automated posting unit can post at specific times. For example, the automated posting unit can post during the times when the target audience is most active. By posting on specific days of the week and at specific times, engagement rates can be improved. Some or all of the above processes in the automated posting unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the automated posting unit can have a generative AI execute posts on specific days of the week and at specific times.

[0078] The engagement prediction unit can analyze past engagement data and trend information to predict future engagement. For example, the engagement prediction unit can analyze past engagement data to predict future engagement. For example, the engagement prediction unit can analyze trend information to predict future engagement. For example, the engagement prediction unit can predict how much engagement a particular post will receive. This allows for the optimization of post content and timing by predicting future engagement. Some or all of the above-described processes in the engagement prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the engagement prediction unit can input past engagement data and trend information into a generative AI and have the generative AI perform a prediction of future engagement.

[0079] The trend analysis department can propose content based on the latest trends. For example, the trend analysis department can analyze the latest trends and propose content that is best suited to the target audience. For example, the trend analysis department can propose content tailored to specific events or seasons. For example, the trend analysis department can propose content based on the interests of the target audience. This ensures that the latest information is always disseminated by proposing content based on the latest trends. Some or all of the above processes in the trend analysis department may be performed using, for example, a generative AI, or not using a generative AI. For example, the trend analysis department can input the latest trend information into a generative AI and have the generative AI propose content that is best suited to the target audience.

[0080] The content generation unit can estimate the user's emotions and adjust the tone and style of the content based on the estimated emotions. For example, if the user is happy, the content generation unit will generate content with a bright and positive tone. For example, if the user is sad, the content generation unit will generate content with a comforting and encouraging tone. For example, if the user is angry, the content generation unit will generate content with a calm and composed tone. This improves engagement by generating content with a tone and style that matches the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the content generation unit may be performed using a generative AI, or not using a generative AI. For example, the content generation unit can input user emotion data into a generative AI and have the generative AI adjust the tone and style of the content.

[0081] The content generation unit can automatically select themes that match specific events or seasons. For example, during the Christmas season, the content generation unit generates content with Christmas-related themes. For example, during the summer holidays, the content generation unit generates content with travel and leisure-related themes. For example, during the start of the new school year, the content generation unit generates content with school and education-related themes. This attracts the interest of the target audience by generating content with themes that match specific events or seasons. Some or all of the above-described processes in the content generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the content generation unit can input information about specific events or seasons into the generation AI and have the generation AI perform theme selection.

[0082] The content generation unit can analyze the target audience's past responses and select the most effective content format. For example, the content generation unit may prioritize generating video content that has received high engagement in the past. For example, the content generation unit may generate infographic content that has received many shares in the past. For example, the content generation unit may generate blog content that has received many comments in the past. This improves engagement by selecting the most effective content format based on past responses. Some or all of the above processing in the content generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the content generation unit can input past response data of the target audience into a generation AI and have the generation AI select the most effective content format.

[0083] The content generation unit can estimate the user's emotions and adjust the length of the content based on the estimated emotions. For example, if the user is busy, the content generation unit can generate short, concise content. For example, if the user is relaxed, the content generation unit can generate longer content with detailed explanations. For example, if the user is excited, the content generation unit can generate content with visually stimulating effects. This improves engagement by adjusting the length of the content according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the content generation unit may be performed using a generative AI, or not. For example, the content generation unit can input user emotion data into a generative AI and have the generative AI adjust the length of the content.

[0084] The content generation unit can generate localized content that takes into account the geographical location of the target audience. For example, if the target audience is in Japan, the content generation unit will generate content related to Japanese culture and events. For example, if the target audience is in the United States, the content generation unit will generate content related to American trends and news. For example, if the target audience is in Europe, the content generation unit will generate content related to European history and tourist destinations. This will attract the interest of the target audience by generating localized content that takes geographical location into account. Some or all of the above processing in the content generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the content generation unit can input the geographical location of the target audience into a generation AI and have the generation AI generate localized content.

[0085] The content generation unit can analyze the social media activity of the target audience and incorporate relevant topics. For example, the content generation unit can generate content based on topics that the target audience frequently shares. For example, the content generation unit can generate content based on topics that the target audience has commented on many times. For example, the content generation unit can generate content based on topics that the target audience has given many "likes" to. In this way, by analyzing the social media activity of the target audience, it is possible to generate content that incorporates relevant topics. Some or all of the above processing in the content generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the content generation unit can input social media activity data of the target audience into a generation AI and have the generation AI perform the incorporation of relevant topics.

[0086] The post analysis unit can estimate the user's emotions and adjust the optimal posting time based on the estimated emotions. For example, if the user is relaxed, the post analysis unit will post during the evening relaxation time. If the user is busy, the post analysis unit will post during lunchtime or commuting hours. If the user is excited, the post analysis unit will post during the active hours on weekends. This improves engagement by adjusting the optimal posting time according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the post analysis unit may be performed using a generative AI, or not. For example, the post analysis unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the optimal posting time.

[0087] The post analysis unit can identify engagement patterns for specific days of the week and time slots based on past post data. For example, the post analysis unit can identify from past data that high engagement is obtained on Monday mornings. For example, the post analysis unit can identify from past data that high engagement is obtained on Friday evenings. For example, the post analysis unit can identify from past data that high engagement is obtained on Wednesday afternoons. By identifying engagement patterns for specific days of the week and time slots, the optimal posting time can be found. Some or all of the above processing in the post analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the post analysis unit can input past post data into a generative AI and have the generative AI identify engagement patterns for specific days of the week and time slots.

[0088] The post analysis unit can monitor the target audience's online activity time in real time and dynamically adjust the optimal posting time. For example, the post analysis unit can post the moment the target audience comes online. For example, the post analysis unit can post when the target audience's online activity reaches its peak. For example, the post analysis unit can post before the target audience's online activity decreases. In this way, the optimal posting time can be dynamically adjusted by monitoring the target audience's online activity time in real time. Some or all of the above processing in the post analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the post analysis unit can input the target audience's online activity data into a generative AI and have the generative AI perform a dynamic adjustment of the optimal posting time.

[0089] The post analysis unit can estimate the user's emotions and adjust the posting frequency based on the estimated emotions. For example, if the user is relaxed, the post analysis unit will post frequently. If the user is busy, the post analysis unit will reduce the posting frequency. If the user is excited, the post analysis unit will post multiple times in a short period. This improves engagement by adjusting the posting frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the post analysis unit may be performed using a generative AI, or not. For example, the post analysis unit can input user emotion data into a generative AI and have the generative AI adjust the posting frequency.

[0090] The post analysis unit can determine the optimal posting time by considering the geographical location of the target audience. For example, if the target audience is in Japan, the post analysis unit will post according to Japan Standard Time. For example, if the target audience is in the United States, the post analysis unit will post according to US Standard Time. For example, if the target audience is in Europe, the post analysis unit will post according to European Standard Time. This improves engagement by determining the optimal posting time that takes geographical location into account. Some or all of the above processing in the post analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the post analysis unit can input the geographical location information of the target audience into a generative AI and have the generative AI determine the optimal posting time.

[0091] The post analysis unit can analyze the social media activity of the target audience and identify the optimal posting time. For example, the post analysis unit might post during times when the target audience is frequently online. For example, the post analysis unit might post during times when the target audience is leaving many comments. For example, the post analysis unit might post during times when the target audience is giving many "likes". In this way, the optimal posting time can be identified by analyzing the social media activity of the target audience. Some or all of the above processing in the post analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the post analysis unit can input social media activity data of the target audience into a generative AI and have the generative AI identify the optimal posting time.

[0092] The automated posting unit can estimate the user's emotions and adjust how the post content is displayed based on the estimated emotions. For example, if the user is relaxed, the automated posting unit may provide a display method that includes detailed information. If the user is busy, for example, the automated posting unit may provide a display method that gets straight to the point. If the user is excited, for example, the automated posting unit may provide a display method that adds visually stimulating effects. This improves engagement by providing a display method that responds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the automated posting unit may be performed using a generative AI, or not using a generative AI. For example, the automated posting unit can input user emotion data into a generative AI and have the generative AI adjust how the post content is displayed.

[0093] The automated posting function can customize its content to suit specific days of the week and times of day. For example, on Monday mornings, it might post motivational content suitable for the start of the week. On Friday evenings, it might post content suitable for relaxing on the weekend. On holidays, it might post content related to the holiday. By customizing content to suit specific days of the week and times of day, engagement can be improved. Some or all of the above processing in the automated posting function may be performed using, for example, a generative AI, or not. For example, the automated posting function can input information about specific days of the week and times of day into a generative AI and have the generative AI perform the customization of the post content.

[0094] The automated posting unit can optimize post content based on past reactions from the target audience. For example, the automated posting unit can reuse post content that has received high engagement in the past. For example, the automated posting unit can create new posts based on post content that has received many shares in the past. For example, the automated posting unit can create new posts based on post content that has received many comments in the past. This improves engagement by optimizing post content based on past reactions. Some or all of the above processes in the automated posting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the automated posting unit can input past reaction data from the target audience into a generative AI and have the generative AI perform the optimization of post content.

[0095] The automated posting unit can estimate the user's emotions and adjust the order of posts based on the estimated emotions. For example, if the user is relaxed, the automated posting unit will prioritize posts containing detailed information. If the user is busy, the automated posting unit will prioritize posts that get straight to the point. If the user is excited, the automated posting unit will prioritize visually stimulating posts. This improves engagement by adjusting the order of posts according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the automated posting unit may be performed using a generative AI or not. For example, the automated posting unit can input user emotion data into a generative AI and have the generative AI adjust the order of posts.

[0096] The automated posting unit can localize post content by taking into account the geographical location of the target audience. For example, if the target audience is in Japan, the automated posting unit will post content related to Japanese culture and events. For example, if the target audience is in the United States, the automated posting unit will post content related to American trends and news. For example, if the target audience is in Europe, the automated posting unit will post content related to European history and tourist destinations. This attracts the interest of the target audience by providing localized post content that takes geographical location into account. Some or all of the above processing in the automated posting unit may be performed using, for example, a generative AI, or without a generative AI. For example, the automated posting unit can input the geographical location information of the target audience into a generative AI and have the generative AI perform the localization of the post content.

[0097] The automated posting unit can analyze the social media activity of the target audience and incorporate relevant topics. For example, the automated posting unit can post based on topics that the target audience frequently shares. For example, the automated posting unit can post based on topics that the target audience has commented on many times. For example, the automated posting unit can post based on topics that the target audience has given many "likes" to. In this way, by analyzing the social media activity of the target audience, it is possible to provide posts that incorporate relevant topics. Some or all of the above processing in the automated posting unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the automated posting unit can input social media activity data of the target audience into a generative AI and have the generative AI perform the incorporation of relevant topics.

[0098] The engagement prediction unit can estimate the user's emotions and adjust the accuracy of the engagement prediction based on the estimated user emotions. For example, if the user is relaxed, the engagement prediction unit will provide a detailed engagement prediction. If the user is busy, the engagement prediction unit will provide a concise engagement prediction. If the user is excited, the engagement prediction unit will provide a visually stimulating engagement prediction. This improves the accuracy of the prediction by adjusting the accuracy of the engagement prediction according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the engagement prediction unit may be performed using a generative AI, or not using a generative AI. For example, the engagement prediction unit can input user emotion data into a generative AI and have the generative AI adjust the accuracy of the engagement prediction.

[0099] The engagement prediction unit can predict the effectiveness of a specific post format based on past engagement data. For example, the engagement prediction unit can predict the effectiveness of video posts that have received high engagement in the past. For example, the engagement prediction unit can predict the effectiveness of infographic posts that have received many shares in the past. For example, the engagement prediction unit can predict the effectiveness of blog posts that have received many comments in the past. In this way, engagement is improved by predicting the effectiveness of a specific post format based on past engagement data. Some or all of the above processing in the engagement prediction unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the engagement prediction unit can input past engagement data into a generative AI and have the generative AI perform a prediction of the effectiveness of a specific post format.

[0100] The engagement prediction unit can improve prediction accuracy by considering the attribute information of the target audience. For example, the engagement prediction unit performs engagement prediction by considering the age group of the target audience. For example, the engagement prediction unit performs engagement prediction by considering the gender of the target audience. For example, the engagement prediction unit performs engagement prediction by considering the interests of the target audience. In this way, the accuracy of engagement prediction is improved by considering the attribute information of the target audience. Some or all of the above processing in the engagement prediction unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the engagement prediction unit can input the attribute information of the target audience into a generative AI and have the generative AI perform the improvement of prediction accuracy.

[0101] The engagement prediction unit can estimate the user's emotions and adjust the order in which engagement prediction results are displayed based on the estimated user emotions. For example, if the user is relaxed, the engagement prediction unit may prioritize displaying detailed engagement prediction results. For example, if the user is busy, the engagement prediction unit may prioritize displaying concise engagement prediction results. For example, if the user is excited, the engagement prediction unit may prioritize displaying visually stimulating engagement prediction results. This improves engagement by adjusting the display order of engagement prediction results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the engagement prediction unit may be performed using a generative AI, or not using a generative AI. For example, the engagement prediction unit can input user emotion data into the generating AI and have the generating AI adjust the display order of the engagement prediction results.

[0102] The engagement prediction unit can improve prediction accuracy by considering the geographical location information of the target audience. For example, if the target audience is in Japan, the engagement prediction unit will perform an engagement prediction based on Japan Standard Time. For example, if the target audience is in the United States, the engagement prediction unit will perform an engagement prediction based on US Standard Time. For example, if the target audience is in Europe, the engagement prediction unit will perform an engagement prediction based on European Standard Time. This improves the accuracy of the engagement prediction by considering geographical location information. Some or all of the above processing in the engagement prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the engagement prediction unit can input the geographical location information of the target audience into a generative AI and have the generative AI perform the improvement of prediction accuracy.

[0103] The engagement prediction unit can analyze the social media activity of the target audience and improve prediction accuracy. For example, the engagement prediction unit predicts the engagement of posts that the target audience frequently shares. For example, the engagement prediction unit predicts the engagement of posts that the target audience has left many comments on. For example, the engagement prediction unit predicts the engagement of posts that the target audience has given many "likes" to. In this way, the accuracy of engagement prediction is improved by analyzing the social media activity of the target audience. Some or all of the above processing in the engagement prediction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the engagement prediction unit can input social media activity data of the target audience into a generative AI and have the generative AI perform the improvement of prediction accuracy.

[0104] The trend analysis unit can estimate the user's emotions and adjust how the trend analysis results are displayed based on the estimated emotions. For example, if the user is relaxed, the trend analysis unit can display detailed trend analysis results. If the user is busy, the trend analysis unit can display concise trend analysis results. If the user is excited, the trend analysis unit can display visually stimulating trend analysis results. This improves engagement by adjusting how the trend analysis results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the trend analysis unit may be performed using a generative AI, or not. For example, the trend analysis unit can input user emotion data into a generative AI and have the generative AI adjust how the trend analysis results are displayed.

[0105] The trend analysis unit can predict current trends based on past trend data. For example, the trend analysis unit predicts current trends from past data. For example, the trend analysis unit predicts future trends based on past trend data. For example, the trend analysis unit analyzes past trend data to identify factors that influence current trends. This allows the system to provide content based on the latest trends by predicting current trends based on past trend data. Some or all of the above processes in the trend analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the trend analysis unit can input past trend data into a generative AI and have the generative AI predict current trends.

[0106] The trend analysis unit can improve the accuracy of its analysis by considering the attribute information of the target audience. For example, the trend analysis unit performs trend analysis considering the age group of the target audience. For example, the trend analysis unit performs trend analysis considering the gender of the target audience. For example, the trend analysis unit performs trend analysis considering the interests of the target audience. In this way, the accuracy of the trend analysis is improved by considering the attribute information of the target audience. Some or all of the above processing in the trend analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the trend analysis unit can input the attribute information of the target audience into a generative AI and have the generative AI perform the improvement of the analysis accuracy.

[0107] The trend analysis unit can estimate the user's emotions and adjust the order in which the trend analysis results are displayed based on the estimated emotions. For example, if the user is relaxed, the trend analysis unit will prioritize displaying detailed trend analysis results. For example, if the user is busy, the trend analysis unit will prioritize displaying concise trend analysis results. For example, if the user is excited, the trend analysis unit will prioritize displaying visually stimulating trend analysis results. This improves engagement by adjusting the display order of trend analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the trend analysis unit may be performed using a generative AI, or not using a generative AI. For example, the trend analysis unit can input user emotion data into a generative AI and have the generative AI adjust the display order of the trend analysis results.

[0108] The trend analysis unit can improve the accuracy of its analysis by considering the geographical location information of the target audience. For example, if the target audience is in Japan, the trend analysis unit will prioritize analyzing trends in Japan. For example, if the target audience is in the United States, the trend analysis unit will prioritize analyzing trends in the United States. For example, if the target audience is in Europe, the trend analysis unit will prioritize analyzing trends in Europe. This improves the accuracy of the trend analysis by considering geographical location information. Some or all of the above processing in the trend analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the trend analysis unit can input the geographical location information of the target audience into a generative AI and have the generative AI perform the improvement of the analysis accuracy.

[0109] The trend analysis unit can analyze the social media activity of the target audience and improve the accuracy of the analysis. For example, the trend analysis unit performs trend analysis based on topics that the target audience frequently shares. For example, the trend analysis unit performs trend analysis based on topics that the target audience has left many comments on. For example, the trend analysis unit performs trend analysis based on topics that the target audience has given many "likes" to. In this way, the accuracy of the trend analysis is improved by analyzing the social media activity of the target audience. Some or all of the above processing in the trend analysis unit may be performed using, for example, generative AI, or not using generative AI. For example, the trend analysis unit can input social media activity data of the target audience into generative AI and have the generative AI perform the improvement of analysis accuracy.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The content generation unit can estimate the user's emotions and adjust the tone and style of the content based on those emotions. For example, if the user is happy, it can generate content with a bright and positive tone. If the user is sad, it can generate content with a comforting and encouraging tone. If the user is angry, it can generate content with a calm and composed tone. This allows for improved engagement by generating content with a tone and style that matches the user's emotions.

[0112] The post analysis department can estimate user emotions and adjust optimal posting times based on those estimates. For example, if a user is relaxed, posts can be made during their relaxed evening hours. If a user is busy, posts can be made during their lunch break or commute. If a user is excited, posts can be made during their active weekend hours. By adjusting posting times to match user emotions, engagement can be improved.

[0113] The automated posting system can estimate the user's emotions and adjust how the post content is displayed based on those emotions. For example, if the user is relaxed, it can provide a display method that includes detailed information. If the user is busy, it can provide a display method that gets straight to the point. If the user is excited, it can provide a display method that includes visually stimulating effects. By providing a display method that matches the user's emotions, engagement can be improved.

[0114] The engagement prediction unit can estimate the user's emotions and adjust the accuracy of the engagement prediction based on those emotions. For example, if the user is relaxed, a detailed engagement prediction can be made. If the user is busy, a concise engagement prediction can be made. If the user is excited, a visually stimulating engagement prediction can be made. By adjusting the accuracy of the engagement prediction according to the user's emotions, the accuracy of the prediction can be improved.

[0115] The trend analysis unit can estimate the user's emotions and adjust how the trend analysis results are displayed based on those emotions. For example, if the user is relaxed, detailed trend analysis results can be displayed. If the user is busy, concise trend analysis results can be displayed. If the user is excited, visually stimulating trend analysis results can be displayed. By adjusting how trend analysis results are displayed according to the user's emotions, engagement can be improved.

[0116] The content generation unit can generate localized content that takes into account the geographical location of the target audience. For example, if the target audience is in Japan, it can generate content related to Japanese culture and events. If the target audience is in the United States, it can generate content related to American trends and news. If the target audience is in Europe, it can generate content related to European history and tourist destinations. By generating localized content that takes geographical location into account, it is possible to attract the interest of the target audience.

[0117] The post analysis department can monitor the target audience's online activity time in real time and dynamically adjust the optimal posting time. For example, it can post the moment the target audience comes online, post when the target audience's online activity reaches its peak, or post before the target audience's online activity declines. In this way, by monitoring the target audience's online activity time in real time, the optimal posting time can be dynamically adjusted.

[0118] The automated posting function can customize post content to suit specific days of the week and times of day. For example, on Monday mornings, it can post motivational content suitable for the start of the week. On Friday evenings, it can post content suitable for relaxing on the weekend. On holidays, it can post content related to the holiday. By customizing post content to suit specific days of the week and times of day, engagement can be improved.

[0119] The engagement prediction unit can improve prediction accuracy by considering the attribute information of the target audience. For example, it can perform engagement predictions by considering the age group of the target audience. It can perform engagement predictions by considering the gender of the target audience. It can perform engagement predictions by considering the interests of the target audience. In this way, the accuracy of engagement predictions can be improved by considering the attribute information of the target audience.

[0120] The Trend Analysis Department can predict current trends based on past trend data. For example, it can predict current trends from past data. It can predict future trends based on past trend data. It can analyze past trend data and identify factors that influence current trends. As a result, by predicting current trends based on past trend data, it can provide content based on the latest trends.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The content generation unit generates content. For example, it analyzes past posting data and trend information to generate content that is optimal for the target audience. It can automatically create posts tailored to specific events or seasons. Step 2: The post analysis team analyzes the optimal posting time for the generated content. For example, they analyze past posting data and engagement data to identify the time slots when the target audience is most active. Step 3: The automated posting unit automatically posts based on the results analyzed by the posting analysis unit. For example, it might post on specific days of the week or at specific times, or post during the time when the target audience is most active. Step 4: The engagement prediction unit predicts the engagement of content posted by the automated posting unit. For example, it analyzes past engagement data and trend information to predict future engagement. Step 5: The Trend Analysis Department conducts trend analysis and makes recommendations based on the results predicted by the Engagement Forecasting Department. For example, they propose content based on the latest trends and content based on the interests of the target audience.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the content generation unit, post analysis unit, automatic posting unit, engagement prediction unit, and trend analysis unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the content generation unit is implemented by the control unit 46A of the smart device 14 and generates content optimal for the target audience by analyzing past posting data and trend information. The post analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the optimal posting time for the generated content. The automatic posting unit is implemented by the control unit 46A of the smart device 14 and automatically posts based on the analysis results. The engagement prediction unit is implemented by the specific processing unit 290 of the data processing device 12 and predicts the engagement of posted content. The trend analysis unit is implemented by the control unit 46A of the smart device 14 and performs trend analysis and makes suggestions based on the prediction results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the content generation unit, post analysis unit, automatic posting unit, engagement prediction unit, and trend analysis unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the content generation unit is implemented by the control unit 46A of the smart glasses 214 and generates content optimal for the target audience by analyzing past posting data and trend information. The post analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the optimal posting time for the generated content. The automatic posting unit is implemented by the control unit 46A of the smart glasses 214 and automatically posts based on the analysis results. The engagement prediction unit is implemented by the specific processing unit 290 of the data processing device 12 and predicts the engagement of posted content. The trend analysis unit is implemented by the control unit 46A of the smart glasses 214 and performs trend analysis and makes suggestions based on the prediction results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the content generation unit, post analysis unit, automatic posting unit, engagement prediction unit, and trend analysis unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the content generation unit is implemented by the control unit 46A of the headset terminal 314 and generates content optimal for the target audience by analyzing past posting data and trend information. The post analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the optimal posting time for the generated content. The automatic posting unit is implemented by the control unit 46A of the headset terminal 314 and automatically posts based on the analysis results. The engagement prediction unit is implemented by the specific processing unit 290 of the data processing unit 12 and predicts the engagement of posted content. The trend analysis unit is implemented by the control unit 46A of the headset terminal 314 and performs trend analysis and makes suggestions based on the prediction results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the content generation unit, post analysis unit, automatic posting unit, engagement prediction unit, and trend analysis unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the content generation unit is implemented by the control unit 46A of the robot 414 and generates content optimal for the target audience by analyzing past posting data and trend information. The post analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the optimal posting time for the generated content. The automatic posting unit is implemented by, for example, the control unit 46A of the robot 414 and automatically posts based on the analysis results. The engagement prediction unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and predicts the engagement of posted content. The trend analysis unit is implemented by, for example, the control unit 46A of the robot 414 and performs trend analysis and makes suggestions based on the prediction results. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] 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.

[0186] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) A content generation unit that generates content, A post analysis unit analyzes the optimal posting time for content generated by the content generation unit, An automated posting unit that automatically posts based on the results of the post analysis unit, An engagement prediction unit that predicts the engagement of content posted by the aforementioned automated posting unit, The system includes a trend analysis unit that performs trend analysis and makes suggestions based on the results predicted by the engagement prediction unit. A system characterized by the following features. (Note 2) The content generation unit, We analyze past posting data and trend information to generate content that is optimal for the target audience. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned submission analysis department, By analyzing past post data and engagement data, we identify the times when the target audience is most active. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned automated posting unit is Post on specific days of the week or at specific times. The system described in Appendix 1, characterized by the features described herein. (Note 5) The engagement prediction unit is, We analyze past engagement data and trend information to predict future engagement. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned trend analysis department, We propose content based on the latest trends. The system described in Appendix 1, characterized by the features described herein. (Note 7) The content generation unit, It estimates the user's emotions and adjusts the tone and style of the content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The content generation unit, Automatically selects themes tailored to specific events or seasons. The system described in Appendix 1, characterized by the features described herein. (Note 9) The content generation unit, Analyze the target audience's past responses and select the most effective content format. The system described in Appendix 1, characterized by the features described herein. (Note 10) The content generation unit, It estimates the user's emotions and adjusts the length of the content based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The content generation unit, Generate localized content that takes into account the geographical location of the target audience. The system described in Appendix 1, characterized by the features described herein. (Note 12) The content generation unit, Analyze the social media activity of your target audience and incorporate relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned submission analysis department, It estimates user sentiment and adjusts the optimal posting time based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned submission analysis department, Identify engagement patterns for specific days of the week and time slots based on past posting data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned submission analysis department, Monitor your target audience's online activity time in real time and dynamically adjust the optimal posting time. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned submission analysis department, It estimates user sentiment and adjusts the frequency of posts based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned submission analysis department, Identify the optimal posting time by considering the geographical location of your target audience. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned submission analysis department, Analyze the social media activity of your target audience to identify the optimal posting time. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned automated posting unit is It estimates the user's sentiment and adjusts how posts are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned automated posting unit is Customize post content to suit specific days of the week or time slots. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned automated posting unit is Optimize post content based on past reactions from your target audience. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned automated posting unit is It estimates user sentiment and adjusts the order of posts based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned automated posting unit is Localize post content to take into account the geographical location of the target audience. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned automated posting unit is Analyze the social media activity of your target audience and incorporate relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 25) The engagement prediction unit is, It estimates user sentiment and adjusts the accuracy of engagement predictions based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The engagement prediction unit is, Predicting the effectiveness of specific post formats based on past engagement data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The engagement prediction unit is, Improve prediction accuracy by considering the attribute information of the target audience. The system described in Appendix 1, characterized by the features described herein. (Note 28) The engagement prediction unit is, It estimates user sentiment and adjusts the order in which engagement prediction results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The engagement prediction unit is, Improve prediction accuracy by considering the geographical location information of the target audience. The system described in Appendix 1, characterized by the features described herein. (Note 30) The engagement prediction unit is, Analyze the social media activity of your target audience to improve prediction accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned trend analysis department, Adjusting how we estimate user sentiment and display trend analysis results based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned trend analysis department, Predicting current trends based on past trend data The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned trend analysis department, Improve analysis accuracy by considering the attribute information of the target audience. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned trend analysis department, It estimates user sentiment and adjusts the order in which trend analysis results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned trend analysis department, Improve analysis accuracy by considering the geographical location information of the target audience. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned trend analysis department, Analyze the social media activity of your target audience and improve the accuracy of your analysis. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A content generation unit that generates content, A post analysis unit analyzes the optimal posting time for content generated by the content generation unit, An automated posting unit that automatically posts based on the results of the post analysis unit, An engagement prediction unit that predicts the engagement of content posted by the aforementioned automated posting unit, The system includes a trend analysis unit that performs trend analysis and makes suggestions based on the results predicted by the engagement prediction unit. A system characterized by the following features.

2. The content generation unit, We analyze past posting data and trend information to generate content that is optimal for the target audience. The system according to feature 1.

3. The aforementioned submission analysis department, By analyzing past post data and engagement data, we identify the times when the target audience is most active. The system according to feature 1.

4. The aforementioned automated posting unit is Post on specific days of the week or at specific times. The system according to feature 1.

5. The engagement prediction unit is, We analyze past engagement data and trend information to predict future engagement. The system according to feature 1.

6. The aforementioned trend analysis department, We propose content based on the latest trends. The system according to feature 1.

7. The content generation unit, It estimates the user's emotions and adjusts the tone and style of the content based on those estimated emotions. The system according to feature 1.

8. The content generation unit, Automatically selects themes tailored to specific events or seasons. The system according to feature 1.

Images