System

Abstract

An object of a system according to an embodiment is to automatically generate content for social media and efficiently post a schedule.SOLUTION: A system according to an embodiment includes a text generation section, an image generation section, a hashtag suggestion section, a short video generation section, and a schedule posting section. The text generation unit generates a text on the basis of the theme or the keyword designated by the user. The image generation unit generates or selects a related image based on the text generated by the text generation unit. The hashtag proposing section proposes an effective hashtag based on the image generated or selected by the image generating section. The short video generation section generates a short video based on the hashtag suggested by the hashtag suggestion section. The schedule posting section automatically posts the short video generated by the short video generation section at a designated date and time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of making it difficult to generate and schedule social media content effectively and quickly.

[0005] The system according to the embodiment aims to automatically generate content for social media and efficiently schedule posting. [Means for solving the problem]

[0006] The system according to the embodiment includes a text generation unit, an image generation unit, a hashtag suggestion unit, a short video generation unit, and a schedule posting unit. The text generation unit generates text based on a theme or keyword specified by a user. The image generation unit generates or selects related images based on the text generated by the text generation unit. The hashtag suggestion unit suggests effective hashtags based on the images generated or selected by the image generation unit. The short video generation unit generates short videos based on the hashtags suggested by the hashtag suggestion unit. The schedule posting unit automatically posts the short videos generated by the short video generation unit at a specified date and time. [Effects of the Invention]

[0007] The system according to the embodiment can automatically generate content for social media and efficiently schedule posting. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The social media post automatic generation system according to an embodiment of the present invention is a system that allows companies and individuals to automatically generate content for social media and schedule posts using AI. As a result, the social media post automatic generation system can improve online presence and achieve efficient content marketing by providing constant content while saving time and effort.

[0029] A social media post automatic generation system according to an embodiment includes a text generation unit, an image generation unit, a hashtag suggestion unit, a short video generation unit, and a schedule posting unit. The text generation unit generates text based on a theme or keyword specified by a user. For example, if a user specifies the theme "introducing a new product," the generation AI generates "text highlighting the features and benefits of the new product." Furthermore, if a user specifies the theme "summer campaign," the generation AI can generate "text that evokes a summer atmosphere." Furthermore, if a user specifies the theme "announcement of an event," the generation AI can generate "text that explains details of the event and how to participate." The image generation unit generates or selects related images based on the text generated by the text generation unit. For example, the generation AI generates or selects "images of the new product" based on the theme "introducing a new product." Furthermore, the generation AI can generate or select "images that evoke a summer atmosphere" based on the theme "summer campaign." Furthermore, the generation AI can generate or select "poster images for the event" based on the theme "announcement of an event." The hashtag suggestion unit suggests effective hashtags based on images generated or selected by the image generation unit. For example, the generation AI suggests hashtags such as "#newproduct #latesttechnology #recommended" based on the theme "introducing a new product." The generation AI can also suggest hashtags such as "#summer #campaign #sale" based on the theme "summer campaign." The generation AI can also suggest hashtags such as "#event #participation #announcement" based on the theme "event announcement." The short video generation unit generates short videos based on the hashtags suggested by the hashtag suggestion unit. For example, the generation AI can generate a "short video explaining how to use a new product" based on the theme "introducing a new product." The generation AI can also generate a "short video introducing the contents of the campaign" based on the theme "summer campaign."The generation AI can also generate a "short video introducing event highlights" based on the theme "event announcement." The schedule posting unit automatically posts the short video generated by the short video generation unit at a specified date and time. For example, the schedule posting unit automatically posts a "new product introduction video" based on a date and time set by a user. The schedule posting unit can also automatically post a "summer campaign video" at a specified date and time. The schedule posting unit can also automatically post an "event announcement video" at a specified date and time. As a result, the social media post automatic generation system according to the embodiment can collectively generate text, images, hashtags, and short videos based on themes and keywords specified by a user, and post them in a planned manner using the schedule posting function. For example, when running a new product introduction campaign, a user can use the generation AI to collectively generate text, images, hashtags, and short videos, and post them in a planned manner using the schedule posting function. This significantly improves the efficiency of marketing activities.

[0030] The text generation unit can refer to a user's past posting history and automatically apply a consistent tone or style to the generated text. For example, the text generation unit analyzes a user's past posting history and automatically applies a specific tone or style to text generated by the generation AI. For example, if past posts were casual in tone, the generated text is adjusted to a similar tone. The text generation unit also automatically adjusts the writing style and language of the text generated by the generation AI based on the user's past posting history. For example, if past posts were formal in tone, the generated text is also changed to a formal style. The text generation unit also builds a system that refers to a user's past posting history and applies a consistent tone or style to the text generated by the generation AI. For example, if past posts were humorous in tone, the generated text is also adjusted to a humorous tone. This allows a brand image to be maintained by applying a consistent tone and style based on the user's past posting history.

[0031] The text generation unit can reflect real-time user feedback on the generated text and make instant corrections or improvements. For example, the text generation unit builds a system in which a user provides real-time feedback on text generated by a generation AI, and the text is instantly corrected based on that feedback. For example, if a user provides feedback such as "be more specific," the generation AI adds more specific content. The text generation unit also builds a system in which a user provides real-time feedback to the generation AI and instantly improves the generated text based on that feedback. For example, if a user provides feedback such as "make the tone softer," the generation AI adjusts the tone to be softer. The text generation unit also develops a system in which a user's real-time feedback is reflected in the text generated by the generation AI and instantly corrects or improves it. For example, if a user provides feedback such as "make it shorter," the generation AI shortens the text. This allows for quick response to user requests by reflecting real-time feedback.

[0032] The text generation unit simultaneously generates text in different languages ​​when generating text, making it possible to provide content that is suitable for international markets. For example, the text generation unit builds a system in which, when the generation AI generates text, it simultaneously generates text in multiple languages. For example, it simultaneously generates text in English, Japanese, French, etc., to accommodate international markets. Furthermore, by simultaneously generating text in different languages, the generation AI provides content that is suitable for international markets. For example, it generates text in multiple languages ​​based on a theme specified by a user. Furthermore, the text generation unit simultaneously generates text in different languages ​​when the generation AI generates text, making it possible to develop a system that provides content that is suitable for international markets. For example, it automatically translates the generated text and provides it in multiple languages. In this way, by simultaneously generating text in different languages, it is possible to provide content that is suitable for international markets.

[0033] The text generation unit provides the generated text as audio content using speech synthesis technology, making it possible to support podcasts or audio SNS. The text generation unit, for example, builds a system that provides text generated by the generation AI as audio content using speech synthesis technology. For example, the generated text is converted into audio and distributed via podcasts or audio SNS. The text generation unit also converts the text generated by the generation AI into audio content using speech synthesis technology, making it possible for users to use it on podcasts or audio SNS. For example, the generated text is saved as an audio file and distributed. The text generation unit also develops a system that provides the text generated by the generation AI as audio content using speech synthesis technology, making it possible to support podcasts and audio SNS. For example, the generated text is converted into audio in real time and distributed. This allows the generated text to be provided as audio content, making it possible to support podcasts and audio SNS.

[0034] The image generation unit can automatically apply a consistent visual style to the generated image by referencing the user's previously posted images. The image generation unit, for example, analyzes the user's previously posted images to build a system that automatically applies a consistent visual style to images generated by the generation AI. For example, if the previously posted images were bright in color, the generated image is adjusted to a similar color tone. The image generation unit also automatically adjusts the visual style of the image generated by the generation AI based on the user's previously posted images. For example, if the previously posted images were monochrome, the generated image is also changed to monochrome. The image generation unit also develops a system that refers to the user's previously posted images to apply a consistent visual style to the image generated by the generation AI. For example, if the previously posted images were vintage-style, the generated image is also adjusted to a vintage style. This allows the brand image to be maintained by applying a consistent visual style based on the user's previously posted images.

[0035] The image generation unit can reflect real-time user feedback on the generated image and make instant corrections or improvements. For example, the image generation unit will build a system in which a user provides real-time feedback on an image generated by a generation AI, and the image is instantly corrected based on that feedback. For example, if a user provides feedback such as "make it brighter," the generation AI will adjust the brightness of the image. The image generation unit will also provide real-time feedback to the generation AI, and instantly improve the generated image based on that feedback. For example, if a user provides feedback such as "change the background," the generation AI will change the background. The image generation unit will also develop a system in which a user's real-time feedback is reflected in an image generated by the generation AI and the image is instantly corrected or improved. For example, if a user provides feedback such as "make it more vivid," the generation AI will adjust the color of the image. This allows for quick response to user requests by reflecting real-time feedback.

[0036] The image generation unit generates a 3D model or animation when generating an image, allowing for more interactive content. For example, the image generation unit builds a system in which a generation AI simultaneously generates a 3D model or animation when generating an image. For example, a 3D model of a product is generated so that users can rotate and view it. The image generation unit also generates animations when generating images, allowing for more interactive content. For example, an animation of a character moving is generated to provide content that users can enjoy. The image generation unit also develops a system in which a generation AI simultaneously generates a 3D model or animation when generating an image, allowing for more interactive content. For example, an interactive 3D model that can be manipulated by the user is generated. This allows for the generation of 3D models and animations to provide more interactive content.

[0037] The image generation unit can provide content that users can actually experience by overlaying the generated images onto the real world using AR technology. The image generation unit, for example, builds a system that overlays images generated by a generation AI onto the real world using AR technology. For example, the generated images are displayed in the real world through a smartphone camera. The image generation unit also overlays images generated by the generation AI onto the real world using AR technology to provide content that users can actually experience. For example, an image of generated furniture can be placed in a room and viewed. The image generation unit also develops a system that provides content that users can actually experience by overlaying images generated by the generation AI onto the real world using AR technology. For example, a generated character moving in the real world is displayed. This makes it possible to provide content that users can actually experience by overlaying it onto the real world using AR technology.

[0038] The hashtag suggestion unit can refer to hashtags used in the user's past posts and automatically apply consistent tags to the proposed hashtags. The hashtag suggestion unit, for example, analyzes hashtags used in the user's past posts to hashtags proposed by the generation AI and builds a system that automatically applies consistent tags. For example, it prioritizes suggesting hashtags used in past posts. The hashtag suggestion unit also adjusts the hashtags proposed by the generation AI based on the hashtags used in the user's past posts. For example, it suggests tags that are highly related to hashtags used in past posts. The hashtag suggestion unit also develops a system that refers to hashtags used in the user's past posts and applies consistent tags to hashtags proposed by the generation AI. For example, it automatically applies hashtags used in past posts. This allows the brand image to be maintained by applying consistent tags based on the hashtags used in the user's past posts.

[0039] The hashtag suggestion unit can reflect real-time user feedback on proposed hashtags and instantly correct or improve them. The hashtag suggestion unit, for example, builds a system in which users provide real-time feedback on hashtags proposed by a generation AI, and instantly corrects the hashtags based on that feedback. For example, if a user provides feedback such as "be more specific," the generation AI suggests specific hashtags. The hashtag suggestion unit also develops a system in which users provide real-time feedback to the generation AI and instantly improves the generated hashtags based on that feedback. For example, if a user provides feedback such as "follow the trends," the generation AI suggests hashtags that match the trends. The hashtag suggestion unit also develops a system in which users reflect real-time user feedback on hashtags proposed by the generation AI and instantly correct or improve them. For example, if a user provides feedback such as "make it shorter," the generation AI suggests shorter hashtags. This allows for quick response to user requests by reflecting real-time feedback.

[0040] The hashtag suggestion unit, when proposing hashtags, can simultaneously propose them in different languages, thereby providing tags that are compatible with international markets. For example, the hashtag suggestion unit builds a system in which, when a generation AI proposes hashtags, it simultaneously proposes hashtags in multiple languages. For example, hashtags can be simultaneously proposed in English, Japanese, French, etc., to accommodate international markets. Furthermore, by simultaneously proposing in different languages, the generation AI can provide hashtags that are compatible with international markets. For example, it proposes hashtags in multiple languages ​​based on a theme specified by a user. Furthermore, the hashtag suggestion unit develops a system in which, when a generation AI proposes hashtags, it simultaneously proposes them in different languages, thereby providing hashtags that are compatible with international markets. For example, it automatically translates proposed hashtags and provides them in multiple languages. In this way, by simultaneously proposing in different languages, it is possible to provide tags that are compatible with international markets.

[0041] The hashtag suggestion unit can combine hashtags suggested by the generation AI with trend analysis to suggest tags to use at the most effective timing. For example, the hashtag suggestion unit combines hashtags suggested by the generation AI with trend analysis to build a system that suggests tags to use at the most effective timing. For example, it suggests optimal hashtags based on current trends. The hashtag suggestion unit also performs trend analysis and adjusts the hashtags suggested by the generation AI to be used at the most effective timing. For example, it suggests hashtags to match specific events or campaigns. The hashtag suggestion unit also combines hashtags suggested by the generation AI with trend analysis to develop a system that suggests tags to use at the most effective timing. For example, it suggests hashtags based on trend data. This makes it possible to suggest hashtags to use at the most effective timing by combining it with trend analysis.

[0042] The short video generation unit can automatically apply a consistent visual style or tone to the generated short video by referencing the user's previously posted videos. The short video generation unit, for example, analyzes the user's previously posted videos to build a system that automatically applies a consistent visual style and tone to the short video generated by the generation AI. For example, if the previously posted videos have a bright tone, the generated video is adjusted to a similar tone. The short video generation unit also automatically adjusts the visual style and tone of the short video generated by the generation AI based on the user's previously posted videos. For example, if the previously posted videos were black and white, the generated video is also changed to black and white. The short video generation unit also develops a system that refers to the user's previously posted videos to apply a consistent visual style and tone to the short video generated by the generation AI. For example, if the previously posted videos were vintage-style, the generated video is also adjusted to a vintage style. This allows the brand image to be maintained by applying a consistent visual style and tone based on the user's previously posted videos.

[0043] The short video generation unit can reflect real-time user feedback on the generated short videos and make instant corrections or improvements. The short video generation unit, for example, builds a system in which users provide real-time feedback on short videos generated by a generation AI and instantly correct the videos based on that feedback. For example, if a user provides feedback such as "make it brighter," the generation AI adjusts the brightness of the video. The short video generation unit also builds a system in which users provide real-time feedback to the generation AI and instantly improves the generated short videos based on that feedback. For example, if a user provides feedback such as "change the background," the generation AI changes the background. The short video generation unit also develops a system in which users reflect real-time user feedback on short videos generated by the generation AI and instantly correct or improve them. For example, if a user provides feedback such as "make it more vivid," the generation AI adjusts the colors of the video. This allows for quick response to user requests by reflecting real-time feedback.

[0044] The short video generation unit can use VR technology when generating short videos to provide content that users can experience in a virtual space. For example, the short video generation unit builds a system that uses VR technology to provide content that can be experienced in a virtual space when a generation AI generates a short video. For example, the generated video can be viewed on a VR headset. Furthermore, the short video generation unit uses VR technology to provide content that can be experienced in a virtual space when a generation AI generates a short video. For example, it generates a video that a user can interactively operate in a virtual space. Furthermore, the short video generation unit develops a system that uses VR technology to provide content that can be experienced in a virtual space when a generation AI generates a short video. For example, the generated video can be played in a VR environment so that the user can experience it in a virtual space. This makes it possible to provide users with a new experience by providing content that can be experienced in a virtual space using VR technology.

[0045] The short video generation unit can provide a function to combine the generated short videos with live streaming and distribute them in real time. The short video generation unit, for example, builds a system that combines short videos generated by a generation AI with live streaming and distributes them in real time. For example, the generated videos are instantly distributed on a live distribution platform. Furthermore, when generating short videos, the generation AI combines a live streaming function and distributes them in real time. For example, the generated videos are inserted during live distribution. Furthermore, the short video generation unit develops a system that provides a function to combine short videos generated by a generation AI with live streaming and distribute them in real time. For example, the generated videos are edited and distributed in real time during live distribution. This makes it possible to distribute them in real time by combining them with live streaming.

[0046] The schedule posting unit can analyze a user's past posting patterns when posting a schedule and automatically suggest the optimal posting timing. For example, the schedule posting unit builds a system that analyzes a user's past posting patterns when posting a schedule and automatically suggests the optimal posting timing. For example, it identifies the time of day that past posts received the most responses. The schedule posting unit also uses a generation AI to suggest the optimal posting timing based on the user's past posting patterns. For example, posting on a specific day of the week or time of day can achieve maximum engagement. The schedule posting unit also develops a system that analyzes a user's past posting patterns when posting a schedule and automatically suggests the optimal posting timing. For example, it calculates the optimal posting time based on past data. This makes it possible to suggest the optimal posting timing by analyzing a user's past posting patterns.

[0047] The schedule posting unit can reflect real-time feedback from the user when posting a schedule and instantly revise the content or timing of the post. For example, the schedule posting unit builds a system in which, when posting a schedule, the user provides feedback in real time and the post content and timing are instantly revised based on that feedback. For example, if the user provides feedback such as "post earlier," the posting time is changed. The schedule posting unit also provides feedback in real time on the schedule post and instantly improves the post content and timing based on that feedback. For example, if the user provides feedback such as "change the content," the posted content is revised. The schedule posting unit also develops a system in which, when posting a schedule, the user reflects real-time feedback from the user and instantly revise the content or timing of the post. For example, if the user provides feedback such as "post later," the posting time is changed. This makes it possible to quickly respond to user requests by reflecting real-time feedback.

[0048] The schedule posting unit can synchronize the schedule posting function between different SNS platforms, enabling centralized post management. The schedule posting unit, for example, builds a system that synchronizes the schedule posting function between different SNS platforms and enables centralized post management. For example, posts are made simultaneously to multiple platforms, such as Facebook (registered trademark), Twitter (registered trademark), and Instagram (registered trademark). The schedule posting unit also synchronizes schedule posting between different SNS platforms, enabling users to manage posts in bulk. For example, a user sets post content for multiple platforms at once. The schedule posting unit also develops a system that synchronizes the schedule posting function between different SNS platforms and enables centralized post management. For example, a user sets posts for multiple platforms using a single interface. This allows posts to be synchronized between different SNS platforms, enabling centralized post management.

[0049] The schedule posting unit links the schedule posting function with a calendar app and can suggest the optimal posting timing based on the user's schedule. For example, the schedule posting unit links the schedule posting function with a calendar app to build a system that suggests the optimal posting timing based on the user's schedule. For example, the posting time is set to match the user's schedule. The schedule posting unit also links the calendar app with the schedule posting function to suggest the optimal posting timing based on the user's schedule. For example, the user posts at a time that avoids busy times. The schedule posting unit also links the schedule posting function with a calendar app to develop a system that suggests the optimal posting timing based on the user's schedule. For example, the posting content is adjusted to match the user's schedule. In this way, by linking with the calendar app, the optimal posting timing can be suggested based on the user's schedule.

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

[0051] The automatic social media post generation system may further include a voice recognition unit. The voice recognition unit can issue instructions to the text generation unit, image generation unit, hashtag suggestion unit, and short video generation unit by a user giving voice instructions. For example, if a user gives a voice instruction such as "Generate a text introducing a new product," the text generation unit can generate text based on that instruction. Also, if a user gives a voice instruction such as "Generate an image for a summer campaign," the image generation unit can generate an image based on that instruction. Furthermore, if a user gives a voice instruction such as "Generate a video announcing an event," the short video generation unit can generate a short video based on that instruction. This allows a user to easily give instructions by voice, reducing the effort required for operation.

[0052] The social media post automatic generation system may further include a user interface unit. The user interface unit provides an interface that can be operated intuitively by the user, allowing the user to easily use the functions of the text generation unit, image generation unit, hashtag suggestion unit, and short video generation unit. For example, the user may add an image by dragging and dropping, or adjust the length of the text using a slider. The user interface unit also includes a preview function that allows the user to check the generated content in real time. This allows the user to operate the system intuitively and adjust the generated content while checking it.

[0053] The automatic social media post generation system can further include a data analysis unit. The data analysis unit analyzes users' past posting data and engagement data and provides feedback for optimal content generation. For example, it identifies the themes and keywords that received the most responses in past posts and provides feedback to the text generation unit, image generation unit, and hashtag suggestion unit based on that. The data analysis unit can also suggest optimal posting timing and frequency based on engagement data. This enables users to generate and post content effectively based on data.

[0054] The social media post automatic generation system can further include a content translation unit. The content translation unit translates the generated text, images, and short videos into multiple languages ​​to provide content that is suitable for international markets. For example, the generated text can be translated into English, Japanese, French, etc., allowing posts in different languages. In addition, the text contained in images and short videos can also be automatically translated to provide content in different languages. This makes it possible to provide content that is suitable for international markets.

[0055] The automatic social media post generation system can further include a content evaluation unit. The content evaluation unit collects feedback from users and followers on the generated content and improves the content based on that evaluation. For example, users can evaluate generated text, images, and short videos, and the generation AI can improve the content based on that evaluation. The system can also analyze comments and reactions from followers and provide feedback to improve the quality of the content. This allows the quality of the content to be improved based on feedback from users and followers.

[0056] The social media post automatic generation system may further include a content archive unit. The content archive unit automatically stores generated text, images, and short videos so that they can be reused later. For example, previously generated content can be searched for and reused. The content archive unit may also organize generated content by category for easy access. This allows previously generated content to be efficiently managed and reused.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The text generation unit generates text based on themes or keywords specified by the user. For example, if the user specifies the theme "introducing a new product," the generation AI generates "text that highlights the features and benefits of the new product." If the user specifies the theme "summer campaign," the generation AI can also generate "text that evokes a summer atmosphere." If the user specifies the theme "event announcement," the generation AI can also generate "text that explains the details of the event and how to participate." Step 2: The image generation unit generates or selects relevant images based on the text generated by the text generation unit. For example, the generation AI generates or selects "new product images" based on the theme "introducing new products." The generation AI can also generate or select "images that evoke a summer atmosphere" based on the theme "summer campaign." The generation AI can also generate or select "event poster images" based on the theme "event announcement." Step 3: The hashtag suggestion unit suggests effective hashtags based on the images generated or selected by the image generation unit. For example, the generation AI may suggest hashtags such as "#newproduct #latesttechnology #recommended" based on the theme "introducing a new product." The generation AI may also suggest hashtags such as "#summer #campaign #sale" based on the theme "summer campaign." The generation AI may also suggest hashtags such as "#event #participation #announcement" based on the theme "event announcement." Step 4: The short video generation unit generates short videos based on the hashtags suggested by the hashtag suggestion unit. For example, the generation AI generates a "short video explaining how to use a new product" based on the theme "introducing a new product." The generation AI can also generate a "short video introducing the contents of a campaign" based on the theme "summer campaign." The generation AI can also generate a "short video introducing the highlights of an event" based on the theme "event announcement." Step 5: The schedule posting unit automatically posts the short video generated by the short video generation unit at a specified date and time. For example, the schedule posting unit automatically posts a "new product introduction video" based on a date and time set by the user. The schedule posting unit can also automatically post a "summer campaign video" at a specified date and time. The schedule posting unit can also automatically post an "event announcement video" at a specified date and time.

[0059] (Example 2) The social media post automatic generation system according to an embodiment of the present invention is a system that allows companies and individuals to automatically generate content for social media and schedule posts using AI. As a result, the social media post automatic generation system can improve online presence and achieve efficient content marketing by providing constant content while saving time and effort.

[0060] A social media post automatic generation system according to an embodiment includes a text generation unit, an image generation unit, a hashtag suggestion unit, a short video generation unit, and a schedule posting unit. The text generation unit generates text based on a theme or keyword specified by a user. For example, if a user specifies the theme "introducing a new product," the generation AI generates "text highlighting the features and benefits of the new product." Furthermore, if a user specifies the theme "summer campaign," the generation AI can generate "text that evokes a summer atmosphere." Furthermore, if a user specifies the theme "announcement of an event," the generation AI can generate "text that explains details of the event and how to participate." The image generation unit generates or selects related images based on the text generated by the text generation unit. For example, the generation AI generates or selects "images of the new product" based on the theme "introducing a new product." Furthermore, the generation AI can generate or select "images that evoke a summer atmosphere" based on the theme "summer campaign." Furthermore, the generation AI can generate or select "poster images for the event" based on the theme "announcement of an event." The hashtag suggestion unit suggests effective hashtags based on images generated or selected by the image generation unit. For example, the generation AI suggests hashtags such as "#newproduct #latesttechnology #recommended" based on the theme "introducing a new product." The generation AI can also suggest hashtags such as "#summer #campaign #sale" based on the theme "summer campaign." The generation AI can also suggest hashtags such as "#event #participation #announcement" based on the theme "event announcement." The short video generation unit generates short videos based on the hashtags suggested by the hashtag suggestion unit. For example, the generation AI can generate a "short video explaining how to use a new product" based on the theme "introducing a new product." The generation AI can also generate a "short video introducing the contents of the campaign" based on the theme "summer campaign."The generation AI can also generate a "short video introducing event highlights" based on the theme "event announcement." The schedule posting unit automatically posts the short video generated by the short video generation unit at a specified date and time. For example, the schedule posting unit automatically posts a "new product introduction video" based on a date and time set by a user. The schedule posting unit can also automatically post a "summer campaign video" at a specified date and time. The schedule posting unit can also automatically post an "event announcement video" at a specified date and time. As a result, the social media post automatic generation system according to the embodiment can collectively generate text, images, hashtags, and short videos based on themes and keywords specified by a user, and post them in a planned manner using the schedule posting function. For example, when running a new product introduction campaign, a user can use the generation AI to collectively generate text, images, hashtags, and short videos, and post them in a planned manner using the schedule posting function. This significantly improves the efficiency of marketing activities.

[0061] The text generation unit can refer to a user's past posting history and automatically apply a consistent tone or style to the generated text. For example, the text generation unit analyzes a user's past posting history and automatically applies a specific tone or style to text generated by the generation AI. For example, if past posts were casual in tone, the generated text is adjusted to a similar tone. The text generation unit also automatically adjusts the writing style and language of the text generated by the generation AI based on the user's past posting history. For example, if past posts were formal in tone, the generated text is also changed to a formal style. The text generation unit also builds a system that refers to a user's past posting history and applies a consistent tone or style to the text generated by the generation AI. For example, if past posts were humorous in tone, the generated text is also adjusted to a humorous tone. This allows a brand image to be maintained by applying a consistent tone and style based on the user's past posting history.

[0062] The text generation unit can reflect real-time user feedback on the generated text and make instant corrections or improvements. For example, the text generation unit builds a system in which a user provides real-time feedback on text generated by a generation AI, and the text is instantly corrected based on that feedback. For example, if a user provides feedback such as "be more specific," the generation AI adds more specific content. The text generation unit also builds a system in which a user provides real-time feedback to the generation AI and instantly improves the generated text based on that feedback. For example, if a user provides feedback such as "make the tone softer," the generation AI adjusts the tone to be softer. The text generation unit also develops a system in which a user's real-time feedback is reflected in the text generated by the generation AI and instantly corrects or improves it. For example, if a user provides feedback such as "make it shorter," the generation AI shortens the text. This allows for quick response to user requests by reflecting real-time feedback.

[0063] The text generation unit can use the emotion estimation function to adjust the tone or content of the generated text based on the user's current emotional state. For example, the text generation unit uses the emotion estimation function to analyze the user's current emotional state and adjust the tone and content of the text generated by the generation AI based on the results. For example, if the user is in a positive emotional state, the generated text also has a positive tone. The text generation unit also builds a system that estimates the user's emotional state in real time and adjusts the content of the text generated by the generation AI based on the results. For example, if the user is feeling stressed, the generated text has relaxing content. The text generation unit also uses the emotion estimation function to adjust the tone and content of the text generated by the generation AI based on the user's current emotional state. For example, if the user is excited, the generated text also has an energetic tone. This allows the provision of more personalized content by adjusting the tone and content of the text according to the user's emotional state.

[0064] The text generation unit simultaneously generates text in different languages ​​when generating text, making it possible to provide content that is suitable for international markets. For example, the text generation unit builds a system in which, when the generation AI generates text, it simultaneously generates text in multiple languages. For example, it simultaneously generates text in English, Japanese, French, etc., to accommodate international markets. Furthermore, by simultaneously generating text in different languages, the generation AI provides content that is suitable for international markets. For example, it generates text in multiple languages ​​based on a theme specified by a user. Furthermore, the text generation unit simultaneously generates text in different languages ​​when the generation AI generates text, making it possible to develop a system that provides content that is suitable for international markets. For example, it automatically translates the generated text and provides it in multiple languages. In this way, by simultaneously generating text in different languages, it is possible to provide content that is suitable for international markets.

[0065] The text generation unit provides the generated text as audio content using speech synthesis technology, making it possible to support podcasts or audio SNS. The text generation unit, for example, builds a system that provides text generated by the generation AI as audio content using speech synthesis technology. For example, the generated text is converted into audio and distributed via podcasts or audio SNS. The text generation unit also converts the text generated by the generation AI into audio content using speech synthesis technology, making it possible for users to use it on podcasts or audio SNS. For example, the generated text is saved as an audio file and distributed. The text generation unit also develops a system that provides the text generated by the generation AI as audio content using speech synthesis technology, making it possible to support podcasts and audio SNS. For example, the generated text is converted into audio in real time and distributed. This allows the generated text to be provided as audio content, making it possible to support podcasts and audio SNS.

[0066] The text generation unit can use the emotion estimation function to identify a text style to which the user has the most positive reaction and preferentially apply that style. The text generation unit, for example, uses the emotion estimation function to identify a text style to which the user has the most positive reaction and builds a system that preferentially uses that style. For example, it identifies a style or tone to which the user has a positive reaction. The text generation unit also analyzes the user's emotional reaction and identifies a text style to which the user has the most positive reaction. For example, it identifies the user's preferred wording and expressions and preferentially uses that style. The text generation unit also uses the emotion estimation function to identify a text style to which the user has the most positive reaction and preferentially uses that style. For example, it automatically applies a text style to which the user has a positive emotion. In this way, the text generation unit identifies a text style to which the user has the most positive reaction and preferentially uses that style, thereby improving user satisfaction.

[0067] The image generation unit can automatically apply a consistent visual style to the generated image by referencing the user's previously posted images. The image generation unit, for example, analyzes the user's previously posted images to build a system that automatically applies a consistent visual style to images generated by the generation AI. For example, if the previously posted images were bright in color, the generated image is adjusted to a similar color tone. The image generation unit also automatically adjusts the visual style of the image generated by the generation AI based on the user's previously posted images. For example, if the previously posted images were monochrome, the generated image is also changed to monochrome. The image generation unit also develops a system that refers to the user's previously posted images to apply a consistent visual style to the image generated by the generation AI. For example, if the previously posted images were vintage-style, the generated image is also adjusted to a vintage style. This allows the brand image to be maintained by applying a consistent visual style based on the user's previously posted images.

[0068] The image generation unit can reflect real-time user feedback on the generated image and make instant corrections or improvements. For example, the image generation unit will build a system in which a user provides real-time feedback on an image generated by a generation AI, and the image is instantly corrected based on that feedback. For example, if a user provides feedback such as "make it brighter," the generation AI will adjust the brightness of the image. The image generation unit will also provide real-time feedback to the generation AI, and instantly improve the generated image based on that feedback. For example, if a user provides feedback such as "change the background," the generation AI will change the background. The image generation unit will also develop a system in which a user's real-time feedback is reflected in an image generated by the generation AI and the image is instantly corrected or improved. For example, if a user provides feedback such as "make it more vivid," the generation AI will adjust the color of the image. This allows for quick response to user requests by reflecting real-time feedback.

[0069] The image generation unit can use the emotion estimation function to adjust the color tone or composition of the generated image based on the user's current emotional state. For example, the image generation unit uses the emotion estimation function to analyze the user's current emotional state and adjust the color tone and composition of the image generated by the generation AI based on the results. For example, if the user is in a positive emotional state, the generated image will also have a bright color tone. The image generation unit also builds a system that estimates the user's emotional state in real time and adjusts the composition of the image generated by the generation AI based on the results. For example, if the user is relaxed, the generated image will have a calm composition. The image generation unit also uses the emotion estimation function to adjust the color tone and composition of the image generated by the generation AI based on the user's current emotional state. For example, if the user is excited, the generated image will also have a dynamic composition. This makes it possible to provide more personalized content by adjusting the color tone and composition of the image according to the user's emotional state.

[0070] The image generation unit generates a 3D model or animation when generating an image, allowing for more interactive content. For example, the image generation unit builds a system in which a generation AI simultaneously generates a 3D model or animation when generating an image. For example, a 3D model of a product is generated so that users can rotate and view it. The image generation unit also generates animations when generating images, allowing for more interactive content. For example, an animation of a character moving is generated to provide content that users can enjoy. The image generation unit also develops a system in which a generation AI simultaneously generates a 3D model or animation when generating an image, allowing for more interactive content. For example, an interactive 3D model that can be manipulated by the user is generated. This allows for the generation of 3D models and animations to provide more interactive content.

[0071] The image generation unit can provide content that users can actually experience by overlaying the generated images onto the real world using AR technology. The image generation unit, for example, builds a system that overlays images generated by a generation AI onto the real world using AR technology. For example, the generated images are displayed in the real world through a smartphone camera. The image generation unit also overlays images generated by the generation AI onto the real world using AR technology to provide content that users can actually experience. For example, an image of generated furniture can be placed in a room and viewed. The image generation unit also develops a system that provides content that users can actually experience by overlaying images generated by the generation AI onto the real world using AR technology. For example, a generated character moving in the real world is displayed. This makes it possible to provide content that users can actually experience by overlaying it onto the real world using AR technology.

[0072] The image generation unit can use the emotion estimation function to identify a visual style to which the user has the most positive reaction and preferentially apply that style. The image generation unit, for example, uses the emotion estimation function to identify a visual style to which the user has the most positive reaction and builds a system that preferentially uses that style. For example, it identifies a color tone or design to which the user has a positive reaction. The image generation unit also analyzes the user's emotional reaction and identifies a visual style to which the user has the most positive reaction. For example, it identifies a visual effect or layout that the user prefers and preferentially uses that style. The image generation unit also uses the emotion estimation function to identify a visual style to which the user has the most positive reaction and preferentially uses that style. For example, it automatically applies a visual style to which the user has a positive emotion. In this way, the visual style to which the user has the most positive reaction is identified and preferentially used, thereby improving user satisfaction.

[0073] The hashtag suggestion unit can refer to hashtags used in the user's past posts and automatically apply consistent tags to the proposed hashtags. The hashtag suggestion unit, for example, analyzes hashtags used in the user's past posts to hashtags proposed by the generation AI and builds a system that automatically applies consistent tags. For example, it prioritizes suggesting hashtags used in past posts. The hashtag suggestion unit also adjusts the hashtags proposed by the generation AI based on the hashtags used in the user's past posts. For example, it suggests tags that are highly related to hashtags used in past posts. The hashtag suggestion unit also develops a system that refers to hashtags used in the user's past posts and applies consistent tags to hashtags proposed by the generation AI. For example, it automatically applies hashtags used in past posts. This allows the brand image to be maintained by applying consistent tags based on the hashtags used in the user's past posts.

[0074] The hashtag suggestion unit can reflect real-time user feedback on proposed hashtags and instantly correct or improve them. The hashtag suggestion unit, for example, builds a system in which users provide real-time feedback on hashtags proposed by a generation AI, and instantly corrects the hashtags based on that feedback. For example, if a user provides feedback such as "be more specific," the generation AI suggests specific hashtags. The hashtag suggestion unit also develops a system in which users provide real-time feedback to the generation AI and instantly improves the generated hashtags based on that feedback. For example, if a user provides feedback such as "follow the trends," the generation AI suggests hashtags that match the trends. The hashtag suggestion unit also develops a system in which users reflect real-time user feedback on hashtags proposed by the generation AI and instantly correct or improve them. For example, if a user provides feedback such as "make it shorter," the generation AI suggests shorter hashtags. This allows for quick response to user requests by reflecting real-time feedback.

[0075] The hashtag suggestion unit can use the emotion estimation function to select hashtags to be suggested based on the user's current emotional state. For example, the hashtag suggestion unit uses the emotion estimation function to analyze the user's current emotional state and select hashtags to be suggested by the generation AI based on the results. For example, if the user is in a positive emotional state, positive hashtags are suggested. The hashtag suggestion unit also builds a system that estimates the user's emotional state in real time and adjusts the hashtags suggested by the generation AI based on the results. For example, if the user is relaxed, hashtags with a relaxed atmosphere are suggested. The hashtag suggestion unit also uses the emotion estimation function to select hashtags to be suggested by the generation AI based on the user's current emotional state. For example, if the user is excited, energetic hashtags are suggested. This allows for the provision of more personalized content by selecting hashtags according to the user's emotional state.

[0076] The hashtag suggestion unit, when proposing hashtags, can simultaneously propose them in different languages, thereby providing tags that are compatible with international markets. For example, the hashtag suggestion unit builds a system in which, when a generation AI proposes hashtags, it simultaneously proposes hashtags in multiple languages. For example, hashtags can be simultaneously proposed in English, Japanese, French, etc., to accommodate international markets. Furthermore, by simultaneously proposing in different languages, the generation AI can provide hashtags that are compatible with international markets. For example, it proposes hashtags in multiple languages ​​based on a theme specified by a user. Furthermore, the hashtag suggestion unit develops a system in which, when a generation AI proposes hashtags, it simultaneously proposes them in different languages, thereby providing hashtags that are compatible with international markets. For example, it automatically translates proposed hashtags and provides them in multiple languages. In this way, by simultaneously proposing in different languages, it is possible to provide tags that are compatible with international markets.

[0077] The hashtag suggestion unit can combine hashtags suggested by the generation AI with trend analysis to suggest tags to use at the most effective timing. For example, the hashtag suggestion unit combines hashtags suggested by the generation AI with trend analysis to build a system that suggests tags to use at the most effective timing. For example, it suggests optimal hashtags based on current trends. The hashtag suggestion unit also performs trend analysis and adjusts the hashtags suggested by the generation AI to be used at the most effective timing. For example, it suggests hashtags to match specific events or campaigns. The hashtag suggestion unit also combines hashtags suggested by the generation AI with trend analysis to develop a system that suggests tags to use at the most effective timing. For example, it suggests hashtags based on trend data. This makes it possible to suggest hashtags to use at the most effective timing by combining it with trend analysis.

[0078] The hashtag suggestion unit can use the emotion estimation function to identify hashtags to which users have the most positive reactions and prioritize the application of those tags. The hashtag suggestion unit, for example, uses the emotion estimation function to identify hashtags to which users have the most positive reactions and builds a system that prioritizes the use of those tags. For example, it identifies hashtags to which users have a positive reaction. The hashtag suggestion unit also analyzes users' emotional reactions and identifies hashtags to which users have the most positive reactions. For example, it identifies hashtags and trends that users like and prioritizes the use of those tags. The hashtag suggestion unit also uses the emotion estimation function to identify hashtags to which users have the most positive reactions and prioritizes the use of those tags. For example, it automatically applies hashtags to which users have a positive emotion. In this way, it is possible to identify hashtags to which users have the most positive reactions and prioritize the use of those tags, thereby improving user satisfaction.

[0079] The short video generation unit can automatically apply a consistent visual style or tone to the generated short video by referencing the user's previously posted videos. The short video generation unit, for example, analyzes the user's previously posted videos to build a system that automatically applies a consistent visual style and tone to the short video generated by the generation AI. For example, if the previously posted videos have a bright tone, the generated video is adjusted to a similar tone. The short video generation unit also automatically adjusts the visual style and tone of the short video generated by the generation AI based on the user's previously posted videos. For example, if the previously posted videos were black and white, the generated video is also changed to black and white. The short video generation unit also develops a system that refers to the user's previously posted videos to apply a consistent visual style and tone to the short video generated by the generation AI. For example, if the previously posted videos were vintage-style, the generated video is also adjusted to a vintage style. This allows the brand image to be maintained by applying a consistent visual style and tone based on the user's previously posted videos.

[0080] The short video generation unit can reflect real-time user feedback on the generated short videos and make instant corrections or improvements. The short video generation unit, for example, builds a system in which users provide real-time feedback on short videos generated by a generation AI and instantly correct the videos based on that feedback. For example, if a user provides feedback such as "make it brighter," the generation AI adjusts the brightness of the video. The short video generation unit also builds a system in which users provide real-time feedback to the generation AI and instantly improves the generated short videos based on that feedback. For example, if a user provides feedback such as "change the background," the generation AI changes the background. The short video generation unit also develops a system in which users reflect real-time user feedback on short videos generated by the generation AI and instantly correct or improve them. For example, if a user provides feedback such as "make it more vivid," the generation AI adjusts the colors of the video. This allows for quick response to user requests by reflecting real-time feedback.

[0081] The short video generation unit can use the emotion estimation function to adjust the content or presentation of the generated short video based on the user's current emotional state. For example, the short video generation unit uses the emotion estimation function to analyze the user's current emotional state and adjust the content and presentation of the short video generated by the generation AI based on the result. For example, if the user is in a positive emotional state, the generated video will also have positive content. The short video generation unit also builds a system that estimates the user's emotional state in real time and adjusts the presentation of the short video generated by the generation AI based on the result. For example, if the user is relaxed, the presentation of the generated video will be calm. The short video generation unit also uses the emotion estimation function to adjust the content and presentation of the short video generated by the generation AI based on the user's current emotional state. For example, if the user is excited, the generated video will also have a dynamic presentation. This makes it possible to provide more personalized content by adjusting the content and presentation of the video according to the user's emotional state.

[0082] The short video generation unit can use VR technology when generating short videos to provide content that users can experience in a virtual space. For example, the short video generation unit builds a system that uses VR technology to provide content that can be experienced in a virtual space when a generation AI generates a short video. For example, the generated video can be viewed on a VR headset. Furthermore, the short video generation unit uses VR technology to provide content that can be experienced in a virtual space when a generation AI generates a short video. For example, it generates a video that a user can interactively operate in a virtual space. Furthermore, the short video generation unit develops a system that uses VR technology to provide content that can be experienced in a virtual space when a generation AI generates a short video. For example, the generated video can be played in a VR environment so that the user can experience it in a virtual space. This makes it possible to provide users with a new experience by providing content that can be experienced in a virtual space using VR technology.

[0083] The short video generation unit can provide a function to combine the generated short videos with live streaming and distribute them in real time. The short video generation unit, for example, builds a system that combines short videos generated by a generation AI with live streaming and distributes them in real time. For example, the generated videos are instantly distributed on a live distribution platform. Furthermore, when generating short videos, the generation AI combines a live streaming function and distributes them in real time. For example, the generated videos are inserted during live distribution. Furthermore, the short video generation unit develops a system that provides a function to combine short videos generated by a generation AI with live streaming and distribute them in real time. For example, the generated videos are edited and distributed in real time during live distribution. This makes it possible to distribute them in real time by combining them with live streaming.

[0084] The short video generation unit can use the emotion estimation function to identify a video style to which the user has the most positive reaction and preferentially apply that style. The short video generation unit, for example, uses the emotion estimation function to identify a video style to which the user has the most positive reaction and builds a system that preferentially uses that style. For example, it identifies an editing style or effect to which the user has a positive reaction. The short video generation unit also analyzes the user's emotional reaction and identifies a video style to which the user has the most positive reaction. For example, it identifies a camera angle or music that the user prefers and preferentially uses that style. The short video generation unit also uses the emotion estimation function to identify a video style to which the user has the most positive reaction and preferentially uses that style. For example, it automatically applies a video style to which the user has a positive emotion. In this way, the video style to which the user has the most positive reaction is identified and preferentially used, thereby improving user satisfaction.

[0085] The schedule posting unit can analyze a user's past posting patterns when posting a schedule and automatically suggest the optimal posting timing. For example, the schedule posting unit builds a system that analyzes a user's past posting patterns when posting a schedule and automatically suggests the optimal posting timing. For example, it identifies the time of day that past posts received the most responses. The schedule posting unit also uses a generation AI to suggest the optimal posting timing based on the user's past posting patterns. For example, posting on a specific day of the week or time of day can achieve maximum engagement. The schedule posting unit also develops a system that analyzes a user's past posting patterns when posting a schedule and automatically suggests the optimal posting timing. For example, it calculates the optimal posting time based on past data. This makes it possible to suggest the optimal posting timing by analyzing a user's past posting patterns.

[0086] The schedule posting unit can reflect real-time feedback from the user when posting a schedule and instantly revise the content or timing of the post. For example, the schedule posting unit builds a system in which, when posting a schedule, the user provides feedback in real time and the post content and timing are instantly revised based on that feedback. For example, if the user provides feedback such as "post earlier," the posting time is changed. The schedule posting unit also provides feedback in real time on the schedule post and instantly improves the post content and timing based on that feedback. For example, if the user provides feedback such as "change the content," the posted content is revised. The schedule posting unit also develops a system in which, when posting a schedule, the user reflects real-time feedback from the user and instantly revise the content or timing of the post. For example, if the user provides feedback such as "post later," the posting time is changed. This makes it possible to quickly respond to user requests by reflecting real-time feedback.

[0087] The schedule posting unit can use the emotion estimation function to select the optimal posting timing based on the user's current emotional state. The schedule posting unit, for example, uses the emotion estimation function to analyze the user's current emotional state and builds a system that selects the optimal posting timing based on the result. For example, if the user is in a positive emotional state, the schedule posting unit posts at that timing. The schedule posting unit also estimates the user's emotional state in real time and selects the optimal posting timing based on the result. For example, if the user is relaxed, the schedule posting unit posts at that timing. The schedule posting unit also uses the emotion estimation function to select the optimal posting timing based on the user's current emotional state. For example, if the user is excited, the schedule posting unit posts at that timing. This allows for more personalized content to be provided by selecting the optimal posting timing according to the user's emotional state.

[0088] The schedule posting unit can synchronize the schedule posting function between different SNS platforms, enabling centralized post management. The schedule posting unit, for example, builds a system that synchronizes the schedule posting function between different SNS platforms and enables centralized post management. For example, posts are made simultaneously to multiple platforms, such as Facebook (registered trademark), Twitter (registered trademark), and Instagram (registered trademark). The schedule posting unit also synchronizes schedule posting between different SNS platforms, enabling users to manage posts in bulk. For example, a user sets post content for multiple platforms at once. The schedule posting unit also develops a system that synchronizes the schedule posting function between different SNS platforms and enables centralized post management. For example, a user sets posts for multiple platforms using a single interface. This allows posts to be synchronized between different SNS platforms, enabling centralized post management.

[0089] The schedule posting unit links the schedule posting function with a calendar app and can suggest the optimal posting timing based on the user's schedule. For example, the schedule posting unit links the schedule posting function with a calendar app to build a system that suggests the optimal posting timing based on the user's schedule. For example, the posting time is set to match the user's schedule. The schedule posting unit also links the calendar app with the schedule posting function to suggest the optimal posting timing based on the user's schedule. For example, the user posts at a time that avoids busy times. The schedule posting unit also links the schedule posting function with a calendar app to develop a system that suggests the optimal posting timing based on the user's schedule. For example, the posting content is adjusted to match the user's schedule. In this way, by linking with the calendar app, the optimal posting timing can be suggested based on the user's schedule.

[0090] The schedule posting unit can use the emotion estimation function to identify the posting timing when the user will have the most positive reaction and prioritize application of that timing. The schedule posting unit, for example, uses the emotion estimation function to identify the posting timing when the user will have the most positive reaction and builds a system that uses that timing preferentially. For example, it identifies a time period when the user will have a positive reaction. The schedule posting unit also analyzes the user's emotional reaction and identifies the posting timing when the user will have the most positive reaction. For example, it identifies the time period or day of the week that the user prefers and uses that timing preferentially. The schedule posting unit also uses the emotion estimation function to identify the posting timing when the user will have the most positive reaction and uses that timing preferentially. For example, it automatically selects a time period when the user will have a positive emotion. In this way, the posting timing when the user will have the most positive reaction is identified and that timing is used preferentially, thereby improving user satisfaction.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The automatic social media post generation system may further include a voice recognition unit. The voice recognition unit can issue instructions to the text generation unit, image generation unit, hashtag suggestion unit, and short video generation unit by a user giving voice instructions. For example, if a user gives a voice instruction such as "Generate a text introducing a new product," the text generation unit can generate text based on that instruction. Also, if a user gives a voice instruction such as "Generate an image for a summer campaign," the image generation unit can generate an image based on that instruction. Furthermore, if a user gives a voice instruction such as "Generate a video announcing an event," the short video generation unit can generate a short video based on that instruction. This allows a user to easily give instructions by voice, reducing the effort required for operation.

[0093] The social media post automatic generation system may further include a user interface unit. The user interface unit provides an interface that can be operated intuitively by the user, allowing the user to easily use the functions of the text generation unit, image generation unit, hashtag suggestion unit, and short video generation unit. For example, the user may add an image by dragging and dropping, or adjust the length of the text using a slider. The user interface unit also includes a preview function that allows the user to check the generated content in real time. This allows the user to operate the system intuitively and adjust the generated content while checking it.

[0094] The automatic social media post generation system can further include a data analysis unit. The data analysis unit analyzes users' past posting data and engagement data and provides feedback for optimal content generation. For example, it identifies the themes and keywords that received the most responses in past posts and provides feedback to the text generation unit, image generation unit, and hashtag suggestion unit based on that. The data analysis unit can also suggest optimal posting timing and frequency based on engagement data. This enables users to generate and post content effectively based on data.

[0095] The automatic social media post generation system can further use the emotion estimation function to adjust the tone and style of the generated content based on the user's emotional state. For example, if the user is feeling stressed, the tone of the generated text and images can be adjusted to be relaxing. If the user is in a positive emotional state, the generated content can also have a positive tone. Furthermore, if the user is excited, the generated content can be adjusted to have an energetic tone. This makes it possible to provide personalized content according to the user's emotional state.

[0096] The automatic social media post generation system can further use its emotion estimation function to identify the content style to which users have the most positive reactions and prioritize the application of that style. For example, it can identify the text style or image style to which users have a positive reaction and prioritize the use of that style. It can also analyze users' emotional reactions and identify the hashtag or short video style to which users have the most positive reactions. This allows it to identify the content style to which users have the most positive reactions and prioritize the use of that style, thereby improving user satisfaction.

[0097] The social media post automatic generation system can further include a content translation unit. The content translation unit translates the generated text, images, and short videos into multiple languages ​​to provide content that is suitable for international markets. For example, the generated text can be translated into English, Japanese, French, etc., allowing posts in different languages. In addition, the text contained in images and short videos can also be automatically translated to provide content in different languages. This makes it possible to provide content that is suitable for international markets.

[0098] The automatic social media post generation system can further include a content evaluation unit. The content evaluation unit collects feedback from users and followers on the generated content and improves the content based on that evaluation. For example, users can evaluate generated text, images, and short videos, and the generation AI can improve the content based on that evaluation. The system can also analyze comments and reactions from followers and provide feedback to improve the quality of the content. This allows the quality of the content to be improved based on feedback from users and followers.

[0099] The social media post automatic generation system can further use an emotion estimation function to select the optimal posting timing based on the user's emotional state. For example, if the user is in a positive emotional state, the system can post at that timing. Also, if the user is relaxed, the system can post at that timing. Furthermore, if the user is excited, the system can post at that timing. In this way, by selecting the optimal posting timing according to the user's emotional state, more personalized content can be provided.

[0100] The social media post automatic generation system may further include a content archive unit. The content archive unit automatically stores generated text, images, and short videos so that they can be reused later. For example, previously generated content can be searched for and reused. The content archive unit may also organize generated content by category for easy access. This allows previously generated content to be efficiently managed and reused.

[0101] The social media post automatic generation system can further use its emotion estimation function to identify the posting timing that will elicit the most positive response from users and prioritize that timing. For example, it can identify the time of day when users are likely to respond positively and post during that time. It can also analyze users' emotional responses and identify the days of the week and time of day when users are likely to respond most positively. This allows it to identify the posting timing that will elicit the most positive response from users and prioritize that timing, thereby improving user satisfaction.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The text generation unit generates text based on themes or keywords specified by the user. For example, if the user specifies the theme "introducing a new product," the generation AI generates "text that highlights the features and benefits of the new product." If the user specifies the theme "summer campaign," the generation AI can also generate "text that evokes a summer atmosphere." If the user specifies the theme "event announcement," the generation AI can also generate "text that explains the details of the event and how to participate." Step 2: The image generation unit generates or selects relevant images based on the text generated by the text generation unit. For example, the generation AI generates or selects "new product images" based on the theme "introducing new products." The generation AI can also generate or select "images that evoke a summer atmosphere" based on the theme "summer campaign." The generation AI can also generate or select "event poster images" based on the theme "event announcement." Step 3: The hashtag suggestion unit suggests effective hashtags based on the images generated or selected by the image generation unit. For example, the generation AI may suggest hashtags such as "#newproduct #latesttechnology #recommended" based on the theme "introducing a new product." The generation AI may also suggest hashtags such as "#summer #campaign #sale" based on the theme "summer campaign." The generation AI may also suggest hashtags such as "#event #participation #announcement" based on the theme "event announcement." Step 4: The short video generation unit generates short videos based on the hashtags suggested by the hashtag suggestion unit. For example, the generation AI generates a "short video explaining how to use a new product" based on the theme "introducing a new product." The generation AI can also generate a "short video introducing the contents of a campaign" based on the theme "summer campaign." The generation AI can also generate a "short video introducing the highlights of an event" based on the theme "event announcement." Step 5: The schedule posting unit automatically posts the short video generated by the short video generation unit at a specified date and time. For example, the schedule posting unit automatically posts a "new product introduction video" based on a date and time set by the user. The schedule posting unit can also automatically post a "summer campaign video" at a specified date and time. The schedule posting unit can also automatically post an "event announcement video" at a specified date and time.

[0104] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0106] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0110] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0111] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0112] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0114] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0115] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0145] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

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

[0148] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0150] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0152] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0154] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0155] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0156] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0157] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0158] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0159] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0160] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0161] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0162] 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.

[0163] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0164] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0165] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0166] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0167] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0168] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0169] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0170] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

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

Claims

1. a text generator that generates text based on a theme or keyword specified by a user; an image generator that generates or selects a related image based on the text generated by the text generator; a hashtag suggestion unit that suggests effective hashtags based on the images generated or selected by the image generation unit; a short video generation unit that generates short videos based on the hashtags suggested by the hashtag suggestion unit; a schedule posting unit that automatically posts the short video generated by the short video generation unit at a specified date and time. A system characterized by:

2. The text generation unit The generated text is automatically applied with a consistent tone or style based on the user's past posting history.

2. The system of claim 1.

3. The text generation unit The generated text is immediately corrected or improved based on the user's real-time feedback.

2. The system of claim 1.

4. The text generation unit Adjusting the tone or content of the generated text based on the user's current emotional state 2. The system of claim 1.

5. The text generation unit Generate text simultaneously in different languages ​​to provide content suitable for international markets 2. The system of claim 1.

6. The text generation unit The generated text is provided as audio content using speech synthesis technology, and is also compatible with podcasts and audio SNS.

2. The system of claim 1.

Images