system

Abstract

We provide the system. [Solution] Means for obtaining the user's past data, A means for analyzing the data to generate effective posting content, A means of suggesting posting timing and hashtags based on analysis results, A means of notifying users of the generated post content and suggestions, A means of collecting reactions to newly posted content and updating the analysis model, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, information dissemination using social network services (SNS) is an important means for individuals and enterprises to enhance marketing and influence. However, many users have difficulty finding effective and attention-grabbing post content and appropriate posting timings. Also, the selection of hashtags and the lack of content ideas are common problems in SNS operation. In addition to these, there is a problem that it is difficult to optimize based on the lack of a method for accurately analyzing how one's own posts are received and evaluated.

Means for Solving the Problems

[0005] This invention is a system that acquires and analyzes users' past data to maximize the effectiveness of posts on social media, and generates and suggests effective post content, timing, and hashtags based on the results. Specifically, it extracts successful cases from users' past data and identifies trends and effective elements using an analysis algorithm. Then, it provides personalized suggestions to the user. Furthermore, by collecting reactions to new posts and continuously updating the analysis model, the accuracy of the suggestions can be improved. As a result, users can easily strengthen their influence on social media and disseminate information effectively.

[0006] A "user" is an individual or legal entity that uses the system to enhance the effectiveness of their posts on social networking services (SNS).

[0007] "Data" refers to information about a user's past social media posts, reactions from followers, and trend information on social media platforms.

[0008] "Analysis" is the process of using collected data to identify the factors and effective elements of success.

[0009] "Posted content" refers to the content itself, such as text, images, and videos, that is published on social media.

[0010] "Timing" refers to the appropriate time or period for a social media post to be received most effectively.

[0011] A "hashtag" refers to a keyword or phrase used to categorize or tag content on social media.

[0012] "Suggestions" refer to advice provided to users regarding optimized post content and timing, based on analysis results.

[0013] "Data collection" refers to the activity of gathering necessary data from social networking platforms and users.

[0014] "Notification" refers to the act or method of informing users of the generated proposals and submitted content.

[0015] "Reaction" refers to actions such as likes, comments, and shares sent by followers and viewers in response to a user's post.

[0016] "Model" refers to a computational method or algorithm based on machine learning used for data analysis.

Brief Explanation of Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0021] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention is a system for optimizing and increasing the influence of user posts on social networking services (SNS). This system analyzes users' past posting data and trend data, and generates and suggests effective posting content, timing, and hashtags, thereby improving the efficiency of SNS marketing.

[0039] First, users link their social media accounts to the system and grant permission for analysis. This allows the system to collect the user's past posting data. The server then applies machine learning algorithms to analyze the collected data. Through this analysis, effective elements derived from past successes are identified, and posting strategies are formulated.

[0040] Furthermore, the server considers the activity times of the user's followers and trends on social media to determine the optimal posting timing. Based on this, the time of day when the user is most likely to gain engagement is suggested. Subsequently, in selecting hashtags, popular tags and tags related to the user's posting area are suggested.

[0041] For example, if a user tries to post cat-related content, the server will suggest highly relevant hashtags such as "cat" and "cat lover." Regarding posting timing, it will suggest nighttime hours to target the peak activity period of followers.

[0042] Next, the server uses AI to generate posts and related images that are likely to go viral based on this information. For example, it might generate posts that emphasize the cute movements of cats, or images that have trending filters applied.

[0043] The generated content and suggestions are notified to the user's device for review. The user then uses these suggestions to create a post and actually posts it on social media. After posting, the server collects the reactions again and uses this data to update the analysis model. This further improves the accuracy and effectiveness of future suggestions.

[0044] This system reduces the stress and trial-and-error involved in posting, allowing users to effectively increase their presence on social media.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] Users link their social media accounts to the system and grant the necessary permissions for analysis. This linkage allows the server to automatically collect past social media posting data.

[0048] Step 2:

[0049] The server stores the posted data collected via the API into a database, and also retrieves the latest social media trend data and follower activity information. This data is used for subsequent analysis.

[0050] Step 3:

[0051] The server performs data cleansing, removing noise and unnecessary data to prepare it for analysis. This cleansing process ensures that only essential data is fed into the model.

[0052] Step 4:

[0053] The server feeds the cleansed data into a machine learning algorithm to learn the characteristics of successful posts. Natural language processing and clustering techniques are commonly used here.

[0054] Step 5:

[0055] Based on the analysis results, the server generates post content, optimal posting timing, and recommended hashtags suitable for the user. At this time, historical data and trend data are integrated to create a summary of suggestions.

[0056] Step 6:

[0057] The server uses AI technology to automatically generate or select images that match the suggested post. The generated post text is also adjusted to align with the user's theme.

[0058] Step 7:

[0059] The server notifies the user's device of the generated post content and suggestions. The notified information is in a format that the user can easily review. The user then prepares their post based on this information.

[0060] Step 8:

[0061] Users review the proposal, make any necessary modifications or edits, and then post it on the social media platform.

[0062] Step 9:

[0063] The server automatically collects engagement data (such as the number of likes and comments) obtained after a post is made and stores it in a database. This data will be used for future analysis.

[0064] Step 10:

[0065] The server retrains the analysis model using newly collected engagement data, improving the accuracy of subsequent suggestions. This iterative process allows for continuous improvement of the system's effectiveness.

[0066] (Example 1)

[0067] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0068] On social networking services, there is a need to effectively create posts that enhance user influence and engagement. However, it is cumbersome and unpredictable for users to analyze their past posts and determine the optimal content, timing, and hashtags. Therefore, there is a need for a method that automatically generates effective posts and makes that success sustainable.

[0069] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0070] In this invention, the server includes means for acquiring the user's past information, means for analyzing the information to create effective posting content, and means for suggesting posting times and labels based on the analysis results. This enables users to make posts that enhance their presence on social media efficiently and effectively.

[0071] A "user" refers to an individual or group that uses a social networking service.

[0072] "Information" refers to past posts made by users on social networking services, follower activity data, engagement data, and so on.

[0073] "Analysis" refers to the process of deriving effective post content and suggestions based on collected information, and includes the use of machine learning algorithms.

[0074] "Posted content" refers to text, images, videos, and other related data that users upload to social networking services.

[0075] "Creation" refers to the process of generating new post content based on the analyzed data.

[0076] "Suggestions" refer to providing users with recommended posting times and labels (hashtags).

[0077] "Time" refers to time information that has been determined to be effective when posting during a specific time period.

[0078] "Labels" refer to tags and hashtags used to improve the discoverability of posts on social networking services.

[0079] "Notification" refers to the act of informing users of analysis results and generated suggestions.

[0080] "Improvement" refers to updating the analysis model based on newly acquired data to enhance the accuracy and effectiveness of subsequent proposals.

[0081] This invention is a system for effectively optimizing user posts on social networking services and increasing their influence on SNS. This system acquires and analyzes a user's past posting information to suggest posting content, timing, and hashtags. Furthermore, it utilizes a generative AI model to automatically generate creative posts and images. Specific embodiments are described below.

[0082] First, users link their social media accounts to the system and grant permission for data analysis. This allows the system to retrieve the user's past posting information and store it in a database. The server then performs analysis based on this information. The analysis includes data preprocessing using the Python Pandas library and model building using machine learning algorithms with Scikit-learn. This identifies elements of effective posting content and the optimal posting timing.

[0083] Next, the server uses SNS APIs to obtain follower activity times and trend information. Based on this data, it then suggests appropriate posting timings and relevant labels to the user. In this process, a generative AI model is used to automatically generate post text and related images. The generative model used is a general natural language processing and image generation AI, specifically OpenAI's GPT and image generation algorithms.

[0084] The generated content and suggestions are notified to the user via their device. The user can review them, edit them as needed, and post them to social media. After posting, the server collects reaction data in real time and updates the analysis model to further improve the accuracy of future suggestions.

[0085] For example, if a user tries to post content with a "cat" theme, the server suggests popular labels such as "cat" and "cat lover," and recommends that the user post during times when their followers are most active. Furthermore, a generative AI model can be used to generate creative captions that highlight the cuteness of cats, as well as images filtered with trending topics.

[0086] A concrete example of a prompt to the generating AI model would be, "Please suggest popular hashtags and viral post phrases for cat-related social media posts." In this way, the present invention helps users optimize their social media activities to a high degree, enabling them to exert greater influence.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] Users link their social media accounts to the system and grant permission to retrieve data. Based on this input, the system collects the user's past posting information via an API. This information includes text, media, and engagement counts. As output, this information is stored in a database. Specifically, the user clicks the link button on the system interface and grants the necessary permissions.

[0090] Step 2:

[0091] The server receives the collected posting information and performs analysis. The input is the user's past posting data. The analysis includes data preprocessing (cleaning, normalization) and the application of a machine learning model. This model extracts the factors that contribute to a successful post. As output, the elements of an effective post are identified. Specifically, the server preprocesses the data using Python's Pandas library and performs analysis using Scikit-learn.

[0092] Step 3:

[0093] The server uses social media APIs to collect trend information and follower activity data. Inputs include real-time trend information obtained from social media and access times from follower logs. This allows the server to calculate the optimal posting timing and associated labels. The output generates recommended time slots and tags. The server periodically retrieves data via social media APIs and feeds this information into the algorithm.

[0094] Step 4:

[0095] The server automatically generates posts and images using a generative AI model. Inputs include user posting themes and insights from past data. The output is creative text and images. Specifically, the server prompts the generative AI, which then generates content using GPT and image generation algorithms.

[0096] Step 5:

[0097] The device notifies the user of the generated post content and suggestions. The input is the generated content and suggestion information transferred from the server. As output, the user who receives the notification can review the content and edit the post. Specifically, the device conveys the information to the user via push notification or email.

[0098] Step 6:

[0099] Users use the suggestions as a reference and post to social media. The input is generated content that the user can edit or use as is. The output is the real-time post on social media, and engagement data is obtained. The server then collects this reaction data and uses it to update the model. Specifically, the server continuously tracks post engagement through the social media API.

[0100] (Application Example 1)

[0101] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0102] To effectively deliver advertisements and content on online social platforms, there is a need for a system that can generate and suggest appropriate content in real time based on users' past data and visual environment. However, conventional systems struggle to quickly and accurately reflect users' interests and visual environment in their posts. In particular, there are challenges in optimizing advertisements, such as timing and generating highly relevant visual data to maximize their effectiveness.

[0103] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0104] In this invention, the server includes a device for acquiring the user's past data, a device for analyzing the data to generate effective content, and a device for generating relevant advertising materials in real time based on the environment the user sees through their visual device. This enables the generation of optimal posts based on the user's visual environment and past activities, and the suggestion of advertising materials in real time.

[0105] A "user" is an individual or legal entity that uses the system to post content or optimize advertisements on online social platforms.

[0106] "Past data" refers to information that includes posts, reactions, and associated metadata previously created and published by users.

[0107] "Device" refers to a combination of hardware and software that enables the acquisition, analysis, generation, proposal, and distribution of digital data.

[0108] An "analytical model" is an algorithm based on mathematical or AI technology used to extract regularities or patterns from collected data.

[0109] "Identifier" is a term that refers to tags or keywords used to identify topics or categories within social media.

[0110] "Visual devices" refer to electronic devices that allow users to obtain information about their surroundings by wearing or using them, and which include elements of augmented reality.

[0111] "Advertising materials" are visual or text content generated for promotional purposes that are customized in real time based on user interests and behavior.

[0112] "Real-time" refers to a state with virtually no delay, where information processing is performed immediately and results are provided on the spot.

[0113] This invention provides a system that allows users to maximize the effectiveness of their posts and advertisements on social media. The system mainly consists of a server and user terminals, and it proposes appropriate content and timing to users through data collection, analysis, and generation.

[0114] The server first retrieves the user's past posting data from their social media account. This data includes metadata such as the content of the post, the time of posting, and related reactions. Next, the server applies machine learning algorithms to analyze this data and build an analytical model to identify the success factors of the user's posts.

[0115] Subsequently, the server suggests appropriate posting timings and identifiers, taking into account the activity times and trend data of the user's social media followers. Furthermore, if the user is using a visual aid, it generates advertising material in real time based on that visual information. In this process, image data captured by the visual aid is analyzed, and relevant advertisements and identifiers are shown to the user.

[0116] The generated content and suggestions are notified to the user's device (such as a smartphone or smart glasses). The user then posts content to social media, taking these suggestions into consideration. After posting, the server collects the responses again and updates the analysis model to improve the accuracy of future suggestions.

[0117] As a concrete example, a user wearing smart glasses in a cafe could have advertisements related to the cafe's topics and products automatically generated and posted to social media. An example of a prompt would be, "Please explain the process for generating social media posts related to the object the user is currently viewing."

[0118] This invention enables optimal social media activities based on users' real-time situations and past behavior, thereby efficiently improving marketing effectiveness.

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The server connects with the user's social media account and collects past posting data. Specifically, it obtains the user's post content, posting time, and reaction data via an API. This input data is used to build a dataset. The output is a structured dataset for future analysis.

[0122] Step 2:

[0123] The server applies machine learning algorithms to analyze the collected data. Specifically, it inputs the dataset into a classification algorithm to extract features that generate high engagement. This analysis generates a model that shows the trends of effective posts. The output is this model along with a list of success factors.

[0124] Step 3:

[0125] The server collects trend data and follower activity times, analyzes this data, and proposes optimal posting timings and associated identifiers. Specifically, it uses an analytical model to identify peak activity times and associated topics, taking real-time trend API and user behavior data as input. The output is a list of proposed posting times and identifiers.

[0126] Step 4:

[0127] If a user is using a visual aid, the device captures their visual data and sends it to the server. The server analyzes this data and generates advertising material relevant to the user's visual environment. Specifically, it uses an image recognition algorithm to analyze the visual information and generate relevant advertisements or identifiers. The output is advertising material tailored to the user's visual environment.

[0128] Step 5:

[0129] The server notifies the user's terminal of the generated content and suggestions. The terminal presents the user with optimized content suggestions and encourages the user to review and submit the content. The output is a notification message for the user to review.

[0130] Step 6:

[0131] When a user posts a suggested content to social media, the server collects reaction data for that post again. Specifically, it retrieves engagement data via an API and updates the previously built analysis model. This feedback loop improves the accuracy of future suggestions. The output is the updated analysis model.

[0132] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0133] This invention is a system for optimizing and increasing the influence of user posts on social networking services (SNS), incorporating an emotion engine that recognizes user emotions. This makes it possible not only to advise on the optimal posting timing and hashtags, but also to suggest personalized post content that corresponds to the user's emotional state.

[0134] First, the user links their social media account to the system. At this time, the user authorizes the emotion engine to run and begins collecting emotional data. The device uses the emotion engine to analyze the user's facial expressions, voice tone, etc., to determine the user's current emotional state.

[0135] Next, the server generates optimal post content based on the user's past posting data and collected sentiment data. Here, posts are created that are tailored to the user's emotions; for example, posts with a positive tone are suggested if the user is happy, and posts containing encouraging messages are suggested if the user is feeling down.

[0136] Furthermore, the server utilizes information from the emotion engine to select or generate images that match the user's emotions. This image selection process might involve techniques such as selecting images with calm tones when the user is in a calm mood, or generating bright and lively images when the user is excited.

[0137] The generated post content and images are notified to the user's device for review. Based on the system's suggestions, the user posts on social media. The server then analyzes the engagement results of the post and updates the database to use the findings for future suggestions.

[0138] For example, if the emotion engine detects a user's emotions while watching a match, the server generates a post expressing the excitement related to the match and suggests an image that represents the atmosphere of the stadium. In this way, it is possible to support information dissemination in a manner that best suits the user's emotions and improve their engagement on social media.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] Users link their social media accounts to the system and authorize the collection of emotional data. In doing so, users consent to the system using an emotion recognition engine, enabling the system to analyze their emotions.

[0142] Step 2:

[0143] The device captures the user's facial expressions and voice through its camera and microphone, and inputs them into an emotion engine. This allows the engine to analyze and identify the user's real-time emotional state. For example, if the user is smiling, it recognizes "joy," and if they have a dejected expression, it recognizes "sadness."

[0144] Step 3:

[0145] In addition to sentiment data, the server collects the user's past posting data and follower reaction data. This data is stored in a database and serves as the basis for analysis.

[0146] Step 4:

[0147] The server uses machine learning algorithms to analyze collected data and generate posts optimized for the user's emotions. This results in posts with a tone and theme that matches the user's current feelings.

[0148] Step 5:

[0149] The server selects or generates relevant images based on the emotions determined by the emotion engine. Specifically, it provides bright and colorful images to users who are feeling happy, ensuring consistency with their emotions.

[0150] Step 6:

[0151] The server sends the generated post content and images to the user's device as suggestions based on their emotions. This process aims to present information in a format that is easily understandable to the user.

[0152] Step 7:

[0153] Users review the suggestions they receive on their devices and edit or modify them as needed. Once finished, they post the final content to social media.

[0154] Step 8:

[0155] The server automatically collects engagement data (e.g., number of likes, number of comments) obtained after a post is made and updates the database for analysis in conjunction with sentiment data.

[0156] Step 9:

[0157] The server uses the collected feedback data to retrain the sentiment engine and machine learning models, improving the accuracy and relevance of future suggestions. This feedback loop allows the system to continuously improve.

[0158] (Example 2)

[0159] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0160] Traditional social networking service posting systems could only suggest fixed timings and content without considering the user's emotional state. Therefore, they were unable to select the most appropriate content and images based on the user's current emotions, posing a challenge to maximizing engagement.

[0161] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0162] In this invention, the server includes means for acquiring past information of the user, means for analyzing the information and generating optimal post content based on the user's emotional state, and means for selecting or generating and suggesting posting timing, hashtags, and images appropriate to the emotion based on the analysis results. This makes it possible to generate optimal post content and images according to the user's emotional state.

[0163] "Users" refer to individuals or groups who use the system, and are primarily those who engage in posting activities on social networking services.

[0164] "Information" refers to all data that shows a user's past behavior and current emotional state, and this includes text, images, audio, etc.

[0165] "Analysis" refers to the process of analyzing acquired information to determine the user's emotional state and the most suitable content for posting.

[0166] An "emotion engine" refers to a technology that uses facial recognition and voice analysis to identify a user's emotional state in real time.

[0167] "Posted content" refers to messages and images that users send to other users on social networking services.

[0168] "Engagement" refers to the level of reaction and involvement from other users to a post, and includes likes, comments, shares, and so on.

[0169] "Image generation AI" refers to technology that automatically generates new images based on the user's emotional state and the content of their posts.

[0170] "Suggestions" refer to specific advice aimed at optimizing users' social networking activities, such as posting timing and hashtags.

[0171] One embodiment of this invention is a system for optimizing user posts on social networking services. This system utilizes an emotion engine that recognizes the user's emotions.

[0172] First, users link their social networking service accounts to the system. This grants permission for the emotion engine to operate, and the collection of emotion data begins. The device uses a camera and microphone to capture the user's face and voice, and the emotion engine analyzes this data. Facial recognition and voice analysis technologies are used to identify the user's emotional state.

[0173] Next, the server generates appropriate content based on the user's past posts and real-time sentiment data. A generative AI model is used to generate messages and hashtags optimized for the user's current emotions. For example, if the user is happy, a positive message will be suggested.

[0174] Furthermore, the server selects or generates images that correspond to the emotion. For this purpose, it's possible to use image generation AI to create new images. Specifically, images with calm color tones are selected for calm emotions.

[0175] The generated post content and images are sent to the user's device, making them available for review. The user then actually posts the content on social media based on the suggestions.

[0176] Once a post is submitted, the server analyzes the engagement with that post. This analysis is recorded in a database to improve the accuracy of future suggestions.

[0177] As a concrete example, consider a situation where a user is excited during an event. When the emotion engine detects this emotion, the server suggests a fun message that reflects the excitement, along with an image that represents the atmosphere of the event. In this way, users can communicate information in a manner that best suits their emotions.

[0178] An example of a prompt message would be: "The user is excited about the sporting event they are watching. Generate social media posts and images that match this emotion."

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] Users link their social networking service accounts to the system. This linkage allows the system to input the user's profile information and past posting data. Based on this information, the system extracts posting trends and past engagement data.

[0182] Step 2:

[0183] The device captures the user's facial expressions and voice using its camera and microphone. This information is used as input for the emotion engine. The emotion engine identifies the user's emotional state by analyzing facial expressions using image processing technology and voice tone using voice analysis technology. As output, specific data is obtained indicating the user's current emotional state.

[0184] Step 3:

[0185] The server uses the past posting data collected in Step 1 and the sentiment data obtained in Step 2 as input. The generative AI model analyzes this data and generates posting content and recommended hashtags optimized for the user's sentiment. As output, customized text corresponding to the user's sentiment is obtained.

[0186] Step 4:

[0187] The server selects or generates images appropriate to the sentiment based on the post content provided by the generative AI model. Considering the output data from the sentiment engine, it uses an image generation AI to generate appropriate visual materials. The output of this step is visual data to be attached to the post.

[0188] Step 5:

[0189] The generated post content and images are notified to the user's device for review. The user reviews the suggested content on their device and edits it as needed. In this step, the final post content is determined once the user's consent is obtained.

[0190] Step 6:

[0191] The user posts the confirmed content to the social networking service. The server collects engagement data (likes, comments, shares, etc.) for that post. This data is recorded in a database to help with future analysis and suggestions. As an output of the step, the engagement results are stored in data storage.

[0192] (Application Example 2)

[0193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0194] In today's information dissemination platforms, it is not easy for users to disseminate emotionally relevant and influential information, and achieving effective engagement is a challenge. Furthermore, the lack of personalized information delivery that responds to the emotional state of individual users often diminishes the quality of information and its impact on recipients.

[0195] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0196] In this invention, the server includes means for recognizing the user's emotional state and personalizing the information content, means for selecting or generating visual data that matches the emotional state, and means for collecting responses to newly transmitted information and updating the analysis model. This enables personalized information transmission according to the user's emotional state, thereby improving the quality and impact of the information.

[0197] "User's past information" refers to information and related data that a user has previously shared.

[0198] "Means of acquisition" refers to functions for collecting information via databases or networks.

[0199] "Means for analyzing and generating optimal information content" refers to a function that analyzes collected information and creates information that is beneficial and influential to the user.

[0200] "A means of suggesting the timing and tags for information dissemination based on analysis results" refers to a function that indicates the optimal time and associated identifiers for disseminating information based on the analysis results.

[0201] "Means of notification" refers to communication functions for informing users of generated information and suggestions.

[0202] "Means for collecting responses to newly disseminated information and updating the analysis model" refers to a function that collects and analyzes the responses of recipients to disseminated information and improves the analysis system based on the results.

[0203] "Means for recognizing a user's emotional state and personalizing information content according to that emotional state" refers to a function that detects a user's emotions and generates unique information based on that information.

[0204] "Means for selecting or generating visual data" refers to functions for selecting or creating images or videos that match the user's emotional state.

[0205] The server operates in a cloud environment to analyze historical information and emotional data collected from the user's smart device. At startup, the user imports their information into the system via their smart device. This includes biometric information to identify past information history and current emotional state. The emotion engine utilizes, for example, OpenAI's GPT model or Microsoft® Azure®'s emotion recognition API. This allows for the analysis of emotions from the user's voice tone and facial expressions.

[0206] The device analyzes the emotional state in real time and uses the results to create prompts for the generative AI model. An example of a prompt might be, "If the user is feeling calm and peaceful, suggest the most appropriate effects and text from past calm posts." The generative AI model generates the most appropriate information and tags in response to this prompt and utilizes image processing software (e.g., Adobe Photoshop API) for visual data selection. This automatically selects or generates visual data that matches the emotion.

[0207] Users review the suggestions notified from their devices and share them as information on social media. Response data from recipients of the shared information is fed back to the server and used to update the analysis model. This feedback loop allows the system to self-improve so that future information dissemination is even more effective.

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] Users provide information to the system using their smart devices. This input includes past information history and current biometric data (facial expressions and voice tone). The device collects this data and sends it to a server for processing. As output of this data, a basic information profile of the user is formed.

[0211] Step 2:

[0212] The server uses the received biometric data to perform analysis with its emotion engine. Here, it uses Microsoft Azure's emotion recognition API to identify the user's current emotional state. The input data is biometric information, and the output is a label for the identified emotional state. Based on the analysis, specific actions are taken, such as determining that the user's emotional state is "calm."

[0213] Step 3:

[0214] The server generates a prompt for the AI ​​model. This prompt asks for the most appropriate suggestion based on past information history. The input is the identified emotional state and past data profile, and the output is the generated prompt. Specifically, the server generates a sentence such as, "If the user is feeling calm and peaceful, suggest the most appropriate effect and text based on past calm posting data."

[0215] Step 4:

[0216] The generative AI model generates information content and tags based on prompt text. The input data is the prompt text, and the output is the generated post content and optimal tag suggestions. Specific operations include text analysis and generating positive messages that match the sentiment.

[0217] Step 5:

[0218] The server selects or generates visual data based on the generated information content. The input is the generated information content and emotional state, and the output is the corresponding visual data. This includes specific actions such as applying appropriate filters to images using the Adobe Photoshop API.

[0219] Step 6:

[0220] The terminal notifies the user of the generated information and visual data. The input is generated data from the server, and the output is notification information that the user can confirm. This also includes specific actions such as user confirmation of the notification.

[0221] Step 7:

[0222] The user checks the notified post content and shares the information on social media. After sharing, the device collects reaction data and sends it to the server. The input is the user's sharing action, and the output is the reaction data. This specifically illustrates how the information receives reactions such as "likes" and comments.

[0223] Step 8:

[0224] The server updates the analysis model based on the collected reaction data. The input is reaction data from social media, and the output is the updated analysis model. Specific actions such as retraining the model are then performed to improve the accuracy of the next information generation algorithm.

[0225] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0226] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0227] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0228] [Second Embodiment]

[0229] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0230] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0231] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0232] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0233] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0234] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0235] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0236] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0237] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0238] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0239] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0240] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0241] This invention is a system for optimizing and increasing the influence of user posts on social networking services (SNS). This system analyzes users' past posting data and trend data, and generates and suggests effective posting content, timing, and hashtags, thereby improving the efficiency of SNS marketing.

[0242] First, users link their social media accounts to the system and grant permission for analysis. This allows the system to collect the user's past posting data. The server then applies machine learning algorithms to analyze the collected data. Through this analysis, effective elements derived from past successes are identified, and posting strategies are formulated.

[0243] Furthermore, the server considers the activity times of the user's followers and trends on social media to determine the optimal posting timing. Based on this, the time of day when the user is most likely to gain engagement is suggested. Subsequently, in selecting hashtags, popular tags and tags related to the user's posting area are suggested.

[0244] For example, if a user tries to post cat-related content, the server will suggest highly relevant hashtags such as "cat" and "cat lover." Regarding posting timing, it will suggest nighttime hours to target the peak activity period of followers.

[0245] Next, the server uses AI to generate posts and related images that are likely to go viral based on this information. For example, it might generate posts that emphasize the cute movements of cats, or images that have trending filters applied.

[0246] The generated content and suggestions are notified to the user's device for review. The user then uses these suggestions to create a post and actually posts it on social media. After posting, the server collects the reactions again and uses this data to update the analysis model. This further improves the accuracy and effectiveness of future suggestions.

[0247] This system reduces the stress and trial-and-error involved in posting, allowing users to effectively increase their presence on social media.

[0248] The following describes the processing flow.

[0249] Step 1:

[0250] Users link their social media accounts to the system and grant the necessary permissions for analysis. This linkage allows the server to automatically collect past social media posting data.

[0251] Step 2:

[0252] The server stores the posted data collected via the API into a database, and also retrieves the latest social media trend data and follower activity information. This data is used for subsequent analysis.

[0253] Step 3:

[0254] The server performs data cleansing, removing noise and unnecessary data to prepare it for analysis. This cleansing process ensures that only essential data is fed into the model.

[0255] Step 4:

[0256] The server feeds the cleansed data into a machine learning algorithm to learn the characteristics of successful posts. Natural language processing and clustering techniques are commonly used here.

[0257] Step 5:

[0258] Based on the analysis results, the server generates post content, optimal posting timing, and recommended hashtags suitable for the user. At this time, historical data and trend data are integrated to create a summary of suggestions.

[0259] Step 6:

[0260] The server uses AI technology to automatically generate or select images that match the suggested post. The generated post text is also adjusted to align with the user's theme.

[0261] Step 7:

[0262] The server notifies the user's device of the generated post content and suggestions. The notified information is in a format that the user can easily review. The user then prepares their post based on this information.

[0263] Step 8:

[0264] Users review the proposal, make any necessary modifications or edits, and then post it on the social media platform.

[0265] Step 9:

[0266] The server automatically collects engagement data (such as the number of likes and comments) obtained after a post is made and stores it in a database. This data will be used for future analysis.

[0267] Step 10:

[0268] The server retrains the analysis model using newly collected engagement data, improving the accuracy of subsequent suggestions. This iterative process allows for continuous improvement of the system's effectiveness.

[0269] (Example 1)

[0270] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0271] On social networking services, there is a need to effectively create posts that enhance user influence and engagement. However, it is cumbersome and unpredictable for users to analyze their past posts and determine the optimal content, timing, and hashtags. Therefore, there is a need for a method that automatically generates effective posts and makes that success sustainable.

[0272] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0273] In this invention, the server includes means for acquiring the user's past information, means for analyzing the information to create effective posting content, and means for suggesting posting times and labels based on the analysis results. This enables users to make posts that enhance their presence on social media efficiently and effectively.

[0274] A "user" refers to an individual or group that uses a social networking service.

[0275] "Information" refers to past posts made by users on social networking services, follower activity data, engagement data, and so on.

[0276] "Analysis" refers to the process of deriving effective post content and suggestions based on collected information, and includes the use of machine learning algorithms.

[0277] "Posted content" refers to text, images, videos, and other related data that users upload to social networking services.

[0278] "Creation" refers to the process of generating new post content based on the analyzed data.

[0279] "Suggestions" refer to providing users with recommended posting times and labels (hashtags).

[0280] "Time" refers to time information that has been determined to be effective when posting during a specific time period.

[0281] "Labels" refer to tags and hashtags used to improve the discoverability of posts on social networking services.

[0282] "Notification" refers to the act of notifying the user of the analysis results and the generated proposals.

[0283] "Improvement" refers to updating the analysis model based on the newly obtained data to improve the accuracy and effectiveness of the next proposal.

[0284] This invention is a system for effectively optimizing user posts in social network services and enhancing influence on SNS. This system obtains and analyzes the user's past post information to propose post content, timing, and hashtags. Furthermore, it utilizes a generative AI model to automatically generate creative post texts and images. Specific embodiments will be described below.

[0285] First, the user links their SNS account to the system and grants permission for data analysis. Thereby, the system obtains the user's past post information and stores it in the database. The server performs analysis based on this information. The analysis includes data preprocessing using the Pandas library in Python and model construction using machine learning algorithms in Scikit-learn. This identifies effective elements of post content and optimal posting timings.

[0286] Next, the server uses the SNS API to obtain follower activity times and trend information. Then, based on this data, it proposes appropriate posting timings and relevant labels to the user. In the process, it uses a generative AI model to automatically generate post texts and related images. The generative models used are general natural language processing and image generation AIs. Specifically, OpenAI's GPT and image generation algorithms are used.

[0287] The generated content and proposals are notified to the user via the terminal. The user can view this, edit it as necessary, and post it on SNS. After posting, the server collects real-time response data and updates the analysis model to further improve the accuracy of the next proposal.

[0288] For example, if a user tries to post content with a "cat" theme, the server suggests popular labels such as "cat" and "cat lover," and recommends that the user post during times when their followers are most active. Furthermore, a generative AI model can be used to generate creative captions that highlight the cuteness of cats, as well as images filtered with trending topics.

[0289] A concrete example of a prompt to the generating AI model would be, "Please suggest popular hashtags and viral post phrases for cat-related social media posts." In this way, the present invention helps users optimize their social media activities to a high degree, enabling them to exert greater influence.

[0290] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0291] Step 1:

[0292] Users link their social media accounts to the system and grant permission to retrieve data. Based on this input, the system collects the user's past posting information via an API. This information includes text, media, and engagement counts. As output, this information is stored in a database. Specifically, the user clicks the link button on the system interface and grants the necessary permissions.

[0293] Step 2:

[0294] The server receives the collected posting information and performs analysis. The input is the user's past posting data. The analysis includes data preprocessing (cleaning, normalization) and the application of a machine learning model. This model extracts the factors that contribute to a successful post. As output, the elements of an effective post are identified. Specifically, the server preprocesses the data using Python's Pandas library and performs analysis using Scikit-learn.

[0295] Step 3:

[0296] The server uses social media APIs to collect trend information and follower activity data. Inputs include real-time trend information obtained from social media and access times from follower logs. This allows the server to calculate the optimal posting timing and associated labels. The output generates recommended time slots and tags. The server periodically retrieves data via social media APIs and feeds this information into the algorithm.

[0297] Step 4:

[0298] The server automatically generates posts and images using a generative AI model. Inputs include user posting themes and insights from past data. The output is creative text and images. Specifically, the server prompts the generative AI, which then generates content using GPT and image generation algorithms.

[0299] Step 5:

[0300] The device notifies the user of the generated post content and suggestions. The input is the generated content and suggestion information transferred from the server. As output, the user who receives the notification can review the content and edit the post. Specifically, the device conveys the information to the user via push notification or email.

[0301] Step 6:

[0302] Users use the suggestions as a reference and post to social media. The input is generated content that the user can edit or use as is. The output is the real-time post on social media, and engagement data is obtained. The server then collects this reaction data and uses it to update the model. Specifically, the server continuously tracks post engagement through the social media API.

[0303] (Application Example 1)

[0304] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0305] In order to realize effective distribution of advertisements and content on an online social platform, there is a demand for a system that can generate and propose appropriate content in real time based on a user's past data and visual environment. However, in conventional systems, it is difficult to make posts that quickly and accurately reflect a user's interests and visual environment. In particular, in the optimization of advertisements, there are problems in the timing for maximizing the effect and in generating highly relevant visual data.

[0306] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0307] In this invention, the server includes a device that acquires a user's past data, a device that analyzes the data to generate effective content, and a device that generates relevant advertisement materials in real time based on the environment that the user has viewed through a visual device. As a result, it becomes possible to generate optimal posts based on the user's visual environment and past activities, and to propose real-time advertisement materials.

[0308] A "user" is an individual or a corporation that uses the system to make posts and optimize advertisements on an online social platform.

[0309] "Past data" is information that refers to posts, reactions, and their related metadata that have been previously created and publicly released by a user.

[0310] A "device" refers to a combination of hardware and software that enables acquisition, analysis, generation, proposal, and distribution of digital data.

[0311] An "analytical model" is an algorithm based on mathematical or AI technology used to extract regularities or patterns from collected data.

[0312] "Identifier" is a term that refers to tags or keywords used to identify topics or categories within social media.

[0313] "Visual devices" refer to electronic devices that allow users to obtain information about their surroundings by wearing or using them, and which include elements of augmented reality.

[0314] "Advertising materials" are visual or text content generated for promotional purposes that are customized in real time based on user interests and behavior.

[0315] "Real-time" refers to a state with virtually no delay, where information processing is performed immediately and results are provided on the spot.

[0316] This invention provides a system that allows users to maximize the effectiveness of their posts and advertisements on social media. The system mainly consists of a server and user terminals, and it proposes appropriate content and timing to users through data collection, analysis, and generation.

[0317] The server first retrieves the user's past posting data from their social media account. This data includes metadata such as the content of the post, the time of posting, and related reactions. Next, the server applies machine learning algorithms to analyze this data and build an analytical model to identify the success factors of the user's posts.

[0318] Subsequently, the server suggests appropriate posting timings and identifiers, taking into account the activity times and trend data of the user's social media followers. Furthermore, if the user is using a visual aid, it generates advertising material in real time based on that visual information. In this process, image data captured by the visual aid is analyzed, and relevant advertisements and identifiers are shown to the user.

[0319] The generated content and suggestions are notified to the user's device (such as a smartphone or smart glasses). The user then posts content to social media, taking these suggestions into consideration. After posting, the server collects the responses again and updates the analysis model to improve the accuracy of future suggestions.

[0320] As a concrete example, a user wearing smart glasses in a cafe could have advertisements related to the cafe's topics and products automatically generated and posted to social media. An example of a prompt would be, "Please explain the process for generating social media posts related to the object the user is currently viewing."

[0321] This invention enables optimal social media activities based on users' real-time situations and past behavior, thereby efficiently improving marketing effectiveness.

[0322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0323] Step 1:

[0324] The server connects with the user's social media account and collects past posting data. Specifically, it obtains the user's post content, posting time, and reaction data via an API. This input data is used to build a dataset. The output is a structured dataset for future analysis.

[0325] Step 2:

[0326] The server applies machine learning algorithms to analyze the collected data. Specifically, it inputs the dataset into a classification algorithm to extract features that generate high engagement. This analysis generates a model that shows the trends of effective posts. The output is this model along with a list of success factors.

[0327] Step 3:

[0328] The server collects trend data and follower activity times, analyzes this data, and proposes optimal posting timings and associated identifiers. Specifically, it uses an analytical model to identify peak activity times and associated topics, taking real-time trend API and user behavior data as input. The output is a list of proposed posting times and identifiers.

[0329] Step 4:

[0330] If a user is using a visual aid, the device captures their visual data and sends it to the server. The server analyzes this data and generates advertising material relevant to the user's visual environment. Specifically, it uses an image recognition algorithm to analyze the visual information and generate relevant advertisements or identifiers. The output is advertising material tailored to the user's visual environment.

[0331] Step 5:

[0332] The server notifies the user's terminal of the generated content and suggestions. The terminal presents the user with optimized content suggestions and encourages the user to review and submit the content. The output is a notification message for the user to review.

[0333] Step 6:

[0334] When a user posts a suggested content to social media, the server collects reaction data for that post again. Specifically, it retrieves engagement data via an API and updates the previously built analysis model. This feedback loop improves the accuracy of future suggestions. The output is the updated analysis model.

[0335] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0336] This invention is a system for optimizing and increasing the influence of user posts on social networking services (SNS), incorporating an emotion engine that recognizes user emotions. This makes it possible not only to advise on the optimal posting timing and hashtags, but also to suggest personalized post content that corresponds to the user's emotional state.

[0337] First, the user links their social media account to the system. At this time, the user authorizes the emotion engine to run and begins collecting emotional data. The device uses the emotion engine to analyze the user's facial expressions, voice tone, etc., to determine the user's current emotional state.

[0338] Next, the server generates optimal post content based on the user's past posting data and collected sentiment data. Here, posts are created that are tailored to the user's emotions; for example, posts with a positive tone are suggested if the user is happy, and posts containing encouraging messages are suggested if the user is feeling down.

[0339] Furthermore, the server utilizes information from the emotion engine to select or generate images that match the user's emotions. This image selection process might involve techniques such as selecting images with calm tones when the user is in a calm mood, or generating bright and lively images when the user is excited.

[0340] The generated post content and images are notified to the user's device for review. Based on the system's suggestions, the user posts on social media. The server then analyzes the engagement results of the post and updates the database to use the findings for future suggestions.

[0341] For example, if the emotion engine detects a user's emotions while watching a match, the server generates a post expressing the excitement related to the match and suggests an image that represents the atmosphere of the stadium. In this way, it is possible to support information dissemination in a manner that best suits the user's emotions and improve their engagement on social media.

[0342] The following describes the processing flow.

[0343] Step 1:

[0344] Users link their social media accounts to the system and authorize the collection of emotional data. In doing so, users consent to the system using an emotion recognition engine, enabling the system to analyze their emotions.

[0345] Step 2:

[0346] The device captures the user's facial expressions and voice through its camera and microphone, and inputs them into an emotion engine. This allows the engine to analyze and identify the user's real-time emotional state. For example, if the user is smiling, it recognizes "joy," and if they have a dejected expression, it recognizes "sadness."

[0347] Step 3:

[0348] In addition to sentiment data, the server collects the user's past posting data and follower reaction data. This data is stored in a database and serves as the basis for analysis.

[0349] Step 4:

[0350] The server uses machine learning algorithms to analyze collected data and generate posts optimized for the user's emotions. This results in posts with a tone and theme that matches the user's current feelings.

[0351] Step 5:

[0352] The server selects or generates relevant images based on the emotions determined by the emotion engine. Specifically, it provides bright and colorful images to users who are feeling happy, ensuring consistency with their emotions.

[0353] Step 6:

[0354] The server sends the generated post content and images to the user's device as suggestions based on their emotions. This process aims to present information in a format that is easily understandable to the user.

[0355] Step 7:

[0356] Users review the suggestions they receive on their devices and edit or modify them as needed. Once finished, they post the final content to social media.

[0357] Step 8:

[0358] The server automatically collects engagement data (e.g., number of likes, number of comments) obtained after a post is made and updates the database for analysis in conjunction with sentiment data.

[0359] Step 9:

[0360] The server uses the collected feedback data to retrain the sentiment engine and machine learning models, improving the accuracy and relevance of future suggestions. This feedback loop allows the system to continuously improve.

[0361] (Example 2)

[0362] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0363] Traditional social networking service posting systems could only suggest fixed timings and content without considering the user's emotional state. Therefore, they were unable to select the most appropriate content and images based on the user's current emotions, posing a challenge to maximizing engagement.

[0364] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0365] In this invention, the server includes means for acquiring past information of the user, means for analyzing the information and generating optimal post content based on the user's emotional state, and means for selecting or generating and suggesting posting timing, hashtags, and images appropriate to the emotion based on the analysis results. This makes it possible to generate optimal post content and images according to the user's emotional state.

[0366] "Users" refer to individuals or groups who use the system, and are primarily those who engage in posting activities on social networking services.

[0367] "Information" refers to all data that shows a user's past behavior and current emotional state, and this includes text, images, audio, etc.

[0368] "Analysis" refers to the process of analyzing acquired information to determine the user's emotional state and the most suitable content for posting.

[0369] An "emotion engine" refers to a technology that uses facial recognition and voice analysis to identify a user's emotional state in real time.

[0370] "Posted content" refers to messages and images that users send to other users on social networking services.

[0371] "Engagement" refers to the level of reaction and involvement from other users to a post, and includes likes, comments, shares, and so on.

[0372] "Image generation AI" refers to technology that automatically generates new images based on the user's emotional state and the content of their posts.

[0373] "Suggestions" refer to specific advice aimed at optimizing users' social networking activities, such as posting timing and hashtags.

[0374] One embodiment of this invention is a system for optimizing user posts on social networking services. This system utilizes an emotion engine that recognizes the user's emotions.

[0375] First, users link their social networking service accounts to the system. This grants permission for the emotion engine to operate, and the collection of emotion data begins. The device uses a camera and microphone to capture the user's face and voice, and the emotion engine analyzes this data. Facial recognition and voice analysis technologies are used to identify the user's emotional state.

[0376] Next, the server generates appropriate content based on the user's past posts and real-time sentiment data. A generative AI model is used to generate messages and hashtags optimized for the user's current emotions. For example, if the user is happy, a positive message will be suggested.

[0377] Furthermore, the server selects or generates images that correspond to the emotion. For this purpose, it's possible to use image generation AI to create new images. Specifically, images with calm color tones are selected for calm emotions.

[0378] The generated post content and images are sent to the user's device, making them available for review. The user then actually posts the content on social media based on the suggestions.

[0379] Once a post is submitted, the server analyzes the engagement with that post. This analysis is recorded in a database to improve the accuracy of future suggestions.

[0380] As a concrete example, consider a situation where a user is excited during an event. When the emotion engine detects this emotion, the server suggests a fun message that reflects the excitement, along with an image that represents the atmosphere of the event. In this way, users can communicate information in a manner that best suits their emotions.

[0381] An example of a prompt message would be: "The user is excited about the sporting event they are watching. Generate social media posts and images that match this emotion."

[0382] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0383] Step 1:

[0384] Users link their social networking service accounts to the system. This linkage allows the system to input the user's profile information and past posting data. Based on this information, the system extracts posting trends and past engagement data.

[0385] Step 2:

[0386] The device captures the user's facial expressions and voice using its camera and microphone. This information is used as input for the emotion engine. The emotion engine identifies the user's emotional state by analyzing facial expressions using image processing technology and voice tone using voice analysis technology. As output, specific data is obtained indicating the user's current emotional state.

[0387] Step 3:

[0388] The server uses the past posting data collected in Step 1 and the sentiment data obtained in Step 2 as input. The generative AI model analyzes this data and generates posting content and recommended hashtags optimized for the user's sentiment. As output, customized text corresponding to the user's sentiment is obtained.

[0389] Step 4:

[0390] The server selects or generates images appropriate to the sentiment based on the post content provided by the generative AI model. Considering the output data from the sentiment engine, it uses an image generation AI to generate appropriate visual materials. The output of this step is visual data to be attached to the post.

[0391] Step 5:

[0392] The generated post content and images are notified to the user's device for review. The user reviews the suggested content on their device and edits it as needed. In this step, the final post content is determined once the user's consent is obtained.

[0393] Step 6:

[0394] The user posts the confirmed content to the social networking service. The server collects engagement data (likes, comments, shares, etc.) for that post. This data is recorded in a database to help with future analysis and suggestions. As an output of the step, the engagement results are stored in data storage.

[0395] (Application Example 2)

[0396] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0397] In today's information dissemination platforms, it is not easy for users to disseminate emotionally relevant and influential information, and achieving effective engagement is a challenge. Furthermore, the lack of personalized information delivery that responds to the emotional state of individual users often diminishes the quality of information and its impact on recipients.

[0398] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0399] In this invention, the server includes means for recognizing the user's emotional state and personalizing the information content, means for selecting or generating visual data that matches the emotional state, and means for collecting responses to newly transmitted information and updating the analysis model. This enables personalized information transmission according to the user's emotional state, thereby improving the quality and impact of the information.

[0400] "User's past information" refers to information and related data that a user has previously shared.

[0401] "Means of acquisition" refers to functions for collecting information via databases or networks.

[0402] "Means for analyzing and generating optimal information content" refers to a function that analyzes collected information and creates information that is beneficial and influential to the user.

[0403] "A means of suggesting the timing and tags for information dissemination based on analysis results" refers to a function that indicates the optimal time and associated identifiers for disseminating information based on the analysis results.

[0404] "Means of notification" refers to communication functions for informing users of generated information and suggestions.

[0405] "Means for collecting responses to newly disseminated information and updating the analysis model" refers to a function that collects and analyzes the responses of recipients to disseminated information and improves the analysis system based on the results.

[0406] "Means for recognizing a user's emotional state and personalizing information content according to that emotional state" refers to a function that detects a user's emotions and generates unique information based on that information.

[0407] "Means for selecting or generating visual data" refers to functions for selecting or creating images or videos that match the user's emotional state.

[0408] The server operates in a cloud environment to analyze historical information and emotional data collected from the user's smart device. At startup, the user imports their information into the system via their smart device. This includes biometric information to identify past information history and current emotional state. The emotion engine uses, for example, OpenAI's GPT model or Microsoft Azure's emotion recognition API. This allows for the analysis of emotions from the user's voice tone and facial expressions.

[0409] The device analyzes the emotional state in real time and uses the results to create prompts for the generative AI model. An example of a prompt might be, "If the user is feeling calm and peaceful, suggest the most appropriate effects and text from past calm posts." The generative AI model generates the most appropriate information and tags in response to this prompt and utilizes image processing software (e.g., Adobe Photoshop API) for visual data selection. This automatically selects or generates visual data that matches the emotion.

[0410] Users review the suggestions notified from their devices and share them as information on social media. Response data from recipients of the shared information is fed back to the server and used to update the analysis model. This feedback loop allows the system to self-improve so that future information dissemination is even more effective.

[0411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0412] Step 1:

[0413] Users provide information to the system using their smart devices. This input includes past information history and current biometric data (facial expressions and voice tone). The device collects this data and sends it to a server for processing. As output of this data, a basic information profile of the user is formed.

[0414] Step 2:

[0415] The server uses the received biometric data to perform analysis with its emotion engine. Here, it uses Microsoft Azure's emotion recognition API to identify the user's current emotional state. The input data is biometric information, and the output is a label for the identified emotional state. Based on the analysis, specific actions are taken, such as determining that the user's emotional state is "calm."

[0416] Step 3:

[0417] The server generates a prompt for the AI ​​model. This prompt asks for the most appropriate suggestion based on past information history. The input is the identified emotional state and past data profile, and the output is the generated prompt. Specifically, the server generates a sentence such as, "If the user is feeling calm and peaceful, suggest the most appropriate effect and text based on past calm posting data."

[0418] Step 4:

[0419] The generative AI model generates information content and tags based on prompt text. The input data is the prompt text, and the output is the generated post content and optimal tag suggestions. Specific operations include text analysis and generating positive messages that match the sentiment.

[0420] Step 5:

[0421] The server selects or generates visual data based on the generated information content. The input is the generated information content and emotional state, and the output is the corresponding visual data. This includes specific actions such as applying appropriate filters to images using the Adobe Photoshop API.

[0422] Step 6:

[0423] The terminal notifies the user of the generated information and visual data. The input is generated data from the server, and the output is notification information that the user can confirm. This also includes specific actions such as user confirmation of the notification.

[0424] Step 7:

[0425] The user checks the notified post content and shares the information on social media. After sharing, the device collects reaction data and sends it to the server. The input is the user's sharing action, and the output is the reaction data. This specifically illustrates how the information receives reactions such as "likes" and comments.

[0426] Step 8:

[0427] The server updates the analysis model based on the collected reaction data. The input is reaction data from social media, and the output is the updated analysis model. Specific actions such as retraining the model are then performed to improve the accuracy of the next information generation algorithm.

[0428] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0429] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0430] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0431] [Third Embodiment]

[0432] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0433] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0434] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0435] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0436] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0437] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0438] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0439] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0440] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0441] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0442] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0443] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0444] This invention is a system for optimizing and increasing the influence of user posts on social networking services (SNS). This system analyzes users' past posting data and trend data, and generates and suggests effective posting content, timing, and hashtags, thereby improving the efficiency of SNS marketing.

[0445] First, users link their social media accounts to the system and grant permission for analysis. This allows the system to collect the user's past posting data. The server then applies machine learning algorithms to analyze the collected data. Through this analysis, effective elements derived from past successes are identified, and posting strategies are formulated.

[0446] Furthermore, the server considers the activity times of the user's followers and trends on social media to determine the optimal posting timing. Based on this, the time of day when the user is most likely to gain engagement is suggested. Subsequently, in selecting hashtags, popular tags and tags related to the user's posting area are suggested.

[0447] For example, if a user tries to post cat-related content, the server will suggest highly relevant hashtags such as "cat" and "cat lover." Regarding posting timing, it will suggest nighttime hours to target the peak activity period of followers.

[0448] Next, the server uses AI to generate posts and related images that are likely to go viral based on this information. For example, it might generate posts that emphasize the cute movements of cats, or images that have trending filters applied.

[0449] The generated content and suggestions are notified to the user's device for review. The user then uses these suggestions to create a post and actually posts it on social media. After posting, the server collects the reactions again and uses this data to update the analysis model. This further improves the accuracy and effectiveness of future suggestions.

[0450] This system reduces the stress and trial-and-error involved in posting, allowing users to effectively increase their presence on social media.

[0451] The following describes the processing flow.

[0452] Step 1:

[0453] Users link their social media accounts to the system and grant the necessary permissions for analysis. This linkage allows the server to automatically collect past social media posting data.

[0454] Step 2:

[0455] The server stores the posted data collected via the API into a database, and also retrieves the latest social media trend data and follower activity information. This data is used for subsequent analysis.

[0456] Step 3:

[0457] The server performs data cleansing, removing noise and unnecessary data to prepare it for analysis. This cleansing process ensures that only essential data is fed into the model.

[0458] Step 4:

[0459] The server feeds the cleansed data into a machine learning algorithm to learn the characteristics of successful posts. Natural language processing and clustering techniques are commonly used here.

[0460] Step 5:

[0461] Based on the analysis results, the server generates post content, optimal posting timing, and recommended hashtags suitable for the user. At this time, historical data and trend data are integrated to create a summary of suggestions.

[0462] Step 6:

[0463] The server uses AI technology to automatically generate or select images that match the suggested post. The generated post text is also adjusted to align with the user's theme.

[0464] Step 7:

[0465] The server notifies the user's device of the generated post content and suggestions. The notified information is in a format that the user can easily review. The user then prepares their post based on this information.

[0466] Step 8:

[0467] Users review the proposal, make any necessary modifications or edits, and then post it on the social media platform.

[0468] Step 9:

[0469] The server automatically collects engagement data (such as the number of likes and comments) obtained after a post is made and stores it in a database. This data will be used for future analysis.

[0470] Step 10:

[0471] The server retrains the analysis model using newly collected engagement data, improving the accuracy of subsequent suggestions. This iterative process allows for continuous improvement of the system's effectiveness.

[0472] (Example 1)

[0473] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0474] On social networking services, there is a need to effectively create posts that enhance user influence and engagement. However, it is cumbersome and unpredictable for users to analyze their past posts and determine the optimal content, timing, and hashtags. Therefore, there is a need for a method that automatically generates effective posts and makes that success sustainable.

[0475] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0476] In this invention, the server includes means for acquiring the user's past information, means for analyzing the information to create effective posting content, and means for suggesting posting times and labels based on the analysis results. This enables users to make posts that enhance their presence on social media efficiently and effectively.

[0477] A "user" refers to an individual or group that uses a social networking service.

[0478] "Information" refers to past posts made by users on social networking services, follower activity data, engagement data, and so on.

[0479] "Analysis" refers to the process of deriving effective post content and suggestions based on collected information, and includes the use of machine learning algorithms.

[0480] "Posted content" refers to text, images, videos, and other related data that users upload to social networking services.

[0481] "Creation" refers to the process of generating new post content based on the analyzed data.

[0482] "Suggestions" refer to providing users with recommended posting times and labels (hashtags).

[0483] "Time" refers to time information that has been determined to be effective when posting during a specific time period.

[0484] "Labels" refer to tags and hashtags used to improve the discoverability of posts on social networking services.

[0485] "Notification" refers to the act of informing users of analysis results and generated suggestions.

[0486] "Improvement" refers to updating the analysis model based on newly acquired data to enhance the accuracy and effectiveness of subsequent proposals.

[0487] This invention is a system for effectively optimizing user posts on social networking services and increasing their influence on SNS. This system acquires and analyzes a user's past posting information to suggest posting content, timing, and hashtags. Furthermore, it utilizes a generative AI model to automatically generate creative posts and images. Specific embodiments are described below.

[0488] First, users link their social media accounts to the system and grant permission for data analysis. This allows the system to retrieve the user's past posting information and store it in a database. The server then performs analysis based on this information. The analysis includes data preprocessing using the Python Pandas library and model building using machine learning algorithms with Scikit-learn. This identifies elements of effective posting content and the optimal posting timing.

[0489] Next, the server uses SNS APIs to retrieve follower activity times and trend information. Based on this data, it suggests appropriate posting timings and relevant labels to the user. In this process, a generative AI model is used to automatically generate post text and related images. The generative model used is a general-purpose AI for natural language processing and image generation, specifically OpenAI's GPT and image generation algorithms.

[0490] The generated content and suggestions are notified to the user via their device. The user can review them, edit them as needed, and post them to social media. After posting, the server collects reaction data in real time and updates the analysis model to further improve the accuracy of future suggestions.

[0491] For example, if a user tries to post content with a "cat" theme, the server suggests popular labels such as "cat" and "cat lover," and recommends that the user post during times when their followers are most active. Furthermore, a generative AI model can be used to generate creative captions that highlight the cuteness of cats, as well as images filtered with trending topics.

[0492] A concrete example of a prompt to the generating AI model would be, "Please suggest popular hashtags and viral post phrases for cat-related social media posts." In this way, the present invention helps users optimize their social media activities to a high degree, enabling them to exert greater influence.

[0493] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0494] Step 1:

[0495] Users link their social media accounts to the system and grant permission to retrieve data. Based on this input, the system collects the user's past posting information via an API. This information includes text, media, and engagement counts. As output, this information is stored in a database. Specifically, the user clicks the link button on the system interface and grants the necessary permissions.

[0496] Step 2:

[0497] The server receives the collected posting information and performs analysis. The input is the user's past posting data. The analysis includes data preprocessing (cleaning, normalization) and the application of a machine learning model. This model extracts the factors that contribute to a successful post. As output, the elements of an effective post are identified. Specifically, the server preprocesses the data using Python's Pandas library and performs analysis using Scikit-learn.

[0498] Step 3:

[0499] The server uses social media APIs to collect trend information and follower activity data. Inputs include real-time trend information obtained from social media and access times from follower logs. This allows the server to calculate the optimal posting timing and associated labels. The output generates recommended time slots and tags. The server periodically retrieves data via social media APIs and feeds this information into the algorithm.

[0500] Step 4:

[0501] The server automatically generates posts and images using a generative AI model. Inputs include user posting themes and insights from past data. The output is creative text and images. Specifically, the server prompts the generative AI, which then generates content using GPT and image generation algorithms.

[0502] Step 5:

[0503] The device notifies the user of the generated post content and suggestions. The input is the generated content and suggestion information transferred from the server. As output, the user who receives the notification can review the content and edit the post. Specifically, the device conveys the information to the user via push notification or email.

[0504] Step 6:

[0505] Users use the suggestions as a reference and post to social media. The input is generated content that the user can edit or use as is. The output is the real-time post on social media, and engagement data is obtained. The server then collects this reaction data and uses it to update the model. Specifically, the server continuously tracks post engagement through the social media API.

[0506] (Application Example 1)

[0507] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0508] To effectively deliver advertisements and content on online social platforms, there is a need for a system that can generate and suggest appropriate content in real time based on users' past data and visual environment. However, conventional systems struggle to quickly and accurately reflect users' interests and visual environment in their posts. In particular, there are challenges in optimizing advertisements, such as timing and generating highly relevant visual data to maximize their effectiveness.

[0509] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0510] In this invention, the server includes a device for acquiring the user's past data, a device for analyzing the data to generate effective content, and a device for generating relevant advertising materials in real time based on the environment the user sees through their visual device. This enables the generation of optimal posts based on the user's visual environment and past activities, and the suggestion of advertising materials in real time.

[0511] A "user" is an individual or legal entity that uses the system to post content or optimize advertisements on online social platforms.

[0512] "Past data" refers to information that includes posts, reactions, and associated metadata previously created and published by users.

[0513] "Device" refers to a combination of hardware and software that enables the acquisition, analysis, generation, proposal, and distribution of digital data.

[0514] An "analytical model" is an algorithm based on mathematical or AI technology used to extract regularities or patterns from collected data.

[0515] "Identifier" is a term that refers to tags or keywords used to identify topics or categories within social media.

[0516] "Visual devices" refer to electronic devices that allow users to obtain information about their surroundings by wearing or using them, and which include elements of augmented reality.

[0517] "Advertising materials" are visual or text content generated for promotional purposes that are customized in real time based on user interests and behavior.

[0518] "Real-time" refers to a state with virtually no delay, where information processing is performed immediately and results are provided on the spot.

[0519] This invention provides a system that allows users to maximize the effectiveness of their posts and advertisements on social media. The system mainly consists of a server and user terminals, and it proposes appropriate content and timing to users through data collection, analysis, and generation.

[0520] The server first retrieves the user's past posting data from their social media account. This data includes metadata such as the content of the post, the time of posting, and related reactions. Next, the server applies machine learning algorithms to analyze this data and build an analytical model to identify the success factors of the user's posts.

[0521] Subsequently, the server suggests appropriate posting timings and identifiers, taking into account the activity times and trend data of the user's social media followers. Furthermore, if the user is using a visual aid, it generates advertising material in real time based on that visual information. In this process, image data captured by the visual aid is analyzed, and relevant advertisements and identifiers are shown to the user.

[0522] The generated content and suggestions are notified to the user's device (such as a smartphone or smart glasses). The user then posts content to social media, taking these suggestions into consideration. After posting, the server collects the responses again and updates the analysis model to improve the accuracy of future suggestions.

[0523] As a concrete example, a user wearing smart glasses in a cafe could have advertisements related to the cafe's topics and products automatically generated and posted to social media. An example of a prompt would be, "Please explain the process for generating social media posts related to the object the user is currently viewing."

[0524] This invention enables optimal social media activities based on users' real-time situations and past behavior, thereby efficiently improving marketing effectiveness.

[0525] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0526] Step 1:

[0527] The server connects with the user's social media account and collects past posting data. Specifically, it obtains the user's post content, posting time, and reaction data via an API. This input data is used to build a dataset. The output is a structured dataset for future analysis.

[0528] Step 2:

[0529] The server applies machine learning algorithms to analyze the collected data. Specifically, it inputs the dataset into a classification algorithm to extract features that generate high engagement. This analysis generates a model that shows the trends of effective posts. The output is this model along with a list of success factors.

[0530] Step 3:

[0531] The server collects trend data and follower activity times, analyzes this data, and proposes optimal posting timings and associated identifiers. Specifically, it uses an analytical model to identify peak activity times and associated topics, taking real-time trend API and user behavior data as input. The output is a list of proposed posting times and identifiers.

[0532] Step 4:

[0533] If a user is using a visual aid, the device captures their visual data and sends it to the server. The server analyzes this data and generates advertising material relevant to the user's visual environment. Specifically, it uses an image recognition algorithm to analyze the visual information and generate relevant advertisements or identifiers. The output is advertising material tailored to the user's visual environment.

[0534] Step 5:

[0535] The server notifies the user's terminal of the generated content and suggestions. The terminal presents the user with optimized content suggestions and encourages the user to review and submit the content. The output is a notification message for the user to review.

[0536] Step 6:

[0537] When a user posts a suggested content to social media, the server collects reaction data for that post again. Specifically, it retrieves engagement data via an API and updates the previously built analysis model. This feedback loop improves the accuracy of future suggestions. The output is the updated analysis model.

[0538] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0539] This invention is a system for optimizing and increasing the influence of user posts on social networking services (SNS), incorporating an emotion engine that recognizes user emotions. This makes it possible not only to advise on the optimal posting timing and hashtags, but also to suggest personalized post content that corresponds to the user's emotional state.

[0540] First, the user links their social media account to the system. At this time, the user authorizes the emotion engine to run and begins collecting emotional data. The device uses the emotion engine to analyze the user's facial expressions, voice tone, etc., to determine the user's current emotional state.

[0541] Next, the server generates optimal post content based on the user's past posting data and collected sentiment data. Here, posts are created that are tailored to the user's emotions; for example, posts with a positive tone are suggested if the user is happy, and posts containing encouraging messages are suggested if the user is feeling down.

[0542] Furthermore, the server utilizes information from the emotion engine to select or generate images that match the user's emotions. This image selection process might involve techniques such as selecting images with calm tones when the user is in a calm mood, or generating bright and lively images when the user is excited.

[0543] The generated post content and images are notified to the user's device for review. Based on the system's suggestions, the user posts on social media. The server then analyzes the engagement results of the post and updates the database to use the findings for future suggestions.

[0544] For example, if the emotion engine detects a user's emotions while watching a match, the server generates a post expressing the excitement related to the match and suggests an image that represents the atmosphere of the stadium. In this way, it is possible to support information dissemination in a manner that best suits the user's emotions and improve their engagement on social media.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] Users link their social media accounts to the system and authorize the collection of emotional data. In doing so, users consent to the system using an emotion recognition engine, enabling the system to analyze their emotions.

[0548] Step 2:

[0549] The device captures the user's facial expressions and voice through its camera and microphone, and inputs them into an emotion engine. This allows the engine to analyze and identify the user's real-time emotional state. For example, if the user is smiling, it recognizes "joy," and if they have a dejected expression, it recognizes "sadness."

[0550] Step 3:

[0551] In addition to sentiment data, the server collects the user's past posting data and follower reaction data. This data is stored in a database and serves as the basis for analysis.

[0552] Step 4:

[0553] The server uses machine learning algorithms to analyze collected data and generate posts optimized for the user's emotions. This results in posts with a tone and theme that matches the user's current feelings.

[0554] Step 5:

[0555] The server selects or generates relevant images based on the emotions determined by the emotion engine. Specifically, it provides bright and colorful images to users who are feeling happy, ensuring consistency with their emotions.

[0556] Step 6:

[0557] The server sends the generated post content and images to the user's device as suggestions based on their emotions. This process aims to present information in a format that is easily understandable to the user.

[0558] Step 7:

[0559] Users review the suggestions they receive on their devices and edit or modify them as needed. Once finished, they post the final content to social media.

[0560] Step 8:

[0561] The server automatically collects engagement data (e.g., number of likes, number of comments) obtained after a post is made and updates the database for analysis in conjunction with sentiment data.

[0562] Step 9:

[0563] The server uses the collected feedback data to retrain the sentiment engine and machine learning models, improving the accuracy and relevance of future suggestions. This feedback loop allows the system to continuously improve.

[0564] (Example 2)

[0565] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0566] Traditional social networking service posting systems could only suggest fixed timings and content without considering the user's emotional state. Therefore, they were unable to select the most appropriate content and images based on the user's current emotions, posing a challenge to maximizing engagement.

[0567] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0568] In this invention, the server includes means for acquiring past information of the user, means for analyzing the information and generating optimal post content based on the user's emotional state, and means for selecting or generating and suggesting posting timing, hashtags, and images appropriate to the emotion based on the analysis results. This makes it possible to generate optimal post content and images according to the user's emotional state.

[0569] "Users" refer to individuals or groups who use the system, and are primarily those who engage in posting activities on social networking services.

[0570] "Information" refers to all data that shows a user's past behavior and current emotional state, and this includes text, images, audio, etc.

[0571] "Analysis" refers to the process of analyzing acquired information to determine the user's emotional state and the most suitable content for posting.

[0572] An "emotion engine" refers to a technology that uses facial recognition and voice analysis to identify a user's emotional state in real time.

[0573] "Posted content" refers to messages and images that users send to other users on social networking services.

[0574] "Engagement" refers to the level of reaction and involvement from other users to a post, and includes likes, comments, shares, and so on.

[0575] "Image generation AI" refers to technology that automatically generates new images based on the user's emotional state and the content of their posts.

[0576] "Suggestions" refer to specific advice aimed at optimizing users' social networking activities, such as posting timing and hashtags.

[0577] One embodiment of this invention is a system for optimizing user posts on social networking services. This system utilizes an emotion engine that recognizes the user's emotions.

[0578] First, users link their social networking service accounts to the system. This grants permission for the emotion engine to operate, and the collection of emotion data begins. The device uses a camera and microphone to capture the user's face and voice, and the emotion engine analyzes this data. Facial recognition and voice analysis technologies are used to identify the user's emotional state.

[0579] Next, the server generates appropriate content based on the user's past posts and real-time sentiment data. A generative AI model is used to generate messages and hashtags optimized for the user's current emotions. For example, if the user is happy, a positive message will be suggested.

[0580] Furthermore, the server selects or generates images that correspond to the emotion. For this purpose, it's possible to use image generation AI to create new images. Specifically, images with calm color tones are selected for calm emotions.

[0581] The generated post content and images are sent to the user's device, making them available for review. The user then actually posts the content on social media based on the suggestions.

[0582] Once a post is submitted, the server analyzes the engagement with that post. This analysis is recorded in a database to improve the accuracy of future suggestions.

[0583] As a concrete example, consider a situation where a user is excited during an event. When the emotion engine detects this emotion, the server suggests a fun message that reflects the excitement, along with an image that represents the atmosphere of the event. In this way, users can communicate information in a manner that best suits their emotions.

[0584] An example of a prompt message would be: "The user is excited about the sporting event they are watching. Generate social media posts and images that match this emotion."

[0585] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0586] Step 1:

[0587] Users link their social networking service accounts to the system. This linkage allows the system to input the user's profile information and past posting data. Based on this information, the system extracts posting trends and past engagement data.

[0588] Step 2:

[0589] The device captures the user's facial expressions and voice using its camera and microphone. This information is used as input for the emotion engine. The emotion engine identifies the user's emotional state by analyzing facial expressions using image processing technology and voice tone using voice analysis technology. As output, specific data is obtained indicating the user's current emotional state.

[0590] Step 3:

[0591] The server uses the past posting data collected in Step 1 and the sentiment data obtained in Step 2 as input. The generative AI model analyzes this data and generates posting content and recommended hashtags optimized for the user's sentiment. As output, customized text corresponding to the user's sentiment is obtained.

[0592] Step 4:

[0593] The server selects or generates images appropriate to the sentiment based on the post content provided by the generative AI model. Considering the output data from the sentiment engine, it uses an image generation AI to generate appropriate visual materials. The output of this step is visual data to be attached to the post.

[0594] Step 5:

[0595] The generated post content and images are notified to the user's device for review. The user reviews the suggested content on their device and edits it as needed. In this step, the final post content is determined once the user's consent is obtained.

[0596] Step 6:

[0597] The user posts the confirmed content to the social networking service. The server collects engagement data (likes, comments, shares, etc.) for that post. This data is recorded in a database to help with future analysis and suggestions. As an output of the step, the engagement results are stored in data storage.

[0598] (Application Example 2)

[0599] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0600] In today's information dissemination platforms, it is not easy for users to disseminate emotionally relevant and influential information, and achieving effective engagement is a challenge. Furthermore, the lack of personalized information delivery that responds to the emotional state of individual users often diminishes the quality of information and its impact on recipients.

[0601] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0602] In this invention, the server includes means for recognizing the user's emotional state and personalizing the information content, means for selecting or generating visual data that matches the emotional state, and means for collecting responses to newly transmitted information and updating the analysis model. This enables personalized information transmission according to the user's emotional state, thereby improving the quality and impact of the information.

[0603] "User's past information" refers to information and related data that a user has previously shared.

[0604] "Means of acquisition" refers to functions for collecting information via databases or networks.

[0605] "Means for analyzing and generating optimal information content" refers to a function that analyzes collected information and creates information that is beneficial and influential to the user.

[0606] "A means of suggesting the timing and tags for information dissemination based on analysis results" refers to a function that indicates the optimal time and associated identifiers for disseminating information based on the analysis results.

[0607] "Means of notification" refers to communication functions for informing users of generated information and suggestions.

[0608] "Means for collecting responses to newly disseminated information and updating the analysis model" refers to a function that collects and analyzes the responses of recipients to disseminated information and improves the analysis system based on the results.

[0609] "Means for recognizing a user's emotional state and personalizing information content according to that emotional state" refers to a function that detects a user's emotions and generates unique information based on that information.

[0610] "Means for selecting or generating visual data" refers to functions for selecting or creating images or videos that match the user's emotional state.

[0611] The server operates in a cloud environment to analyze historical information and emotional data collected from the user's smart device. At startup, the user imports their information into the system via their smart device. This includes biometric information to identify past information history and current emotional state. The emotion engine uses, for example, OpenAI's GPT model or Microsoft Azure's emotion recognition API. This allows for the analysis of emotions from the user's voice tone and facial expressions.

[0612] The device analyzes the emotional state in real time and uses the results to create prompts for the generative AI model. An example of a prompt might be, "If the user is feeling calm and peaceful, suggest the most appropriate effects and text from past calm posts." The generative AI model generates the most appropriate information and tags in response to this prompt and utilizes image processing software (e.g., Adobe Photoshop API) for visual data selection. This automatically selects or generates visual data that matches the emotion.

[0613] Users review the suggestions notified from their devices and share them as information on social media. Response data from recipients of the shared information is fed back to the server and used to update the analysis model. This feedback loop allows the system to self-improve so that future information dissemination is even more effective.

[0614] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0615] Step 1:

[0616] Users provide information to the system using their smart devices. This input includes past information history and current biometric data (facial expressions and voice tone). The device collects this data and sends it to a server for processing. As output of this data, a basic information profile of the user is formed.

[0617] Step 2:

[0618] The server uses the received biometric data to perform analysis with its emotion engine. Here, it uses Microsoft Azure's emotion recognition API to identify the user's current emotional state. The input data is biometric information, and the output is a label for the identified emotional state. Based on the analysis, specific actions are taken, such as determining that the user's emotional state is "calm."

[0619] Step 3:

[0620] The server generates a prompt for the AI ​​model. This prompt asks for the most appropriate suggestion based on past information history. The input is the identified emotional state and past data profile, and the output is the generated prompt. Specifically, the server generates a sentence such as, "If the user is feeling calm and peaceful, suggest the most appropriate effect and text based on past calm posting data."

[0621] Step 4:

[0622] The generative AI model generates information content and tags based on prompt text. The input data is the prompt text, and the output is the generated post content and optimal tag suggestions. Specific operations include text analysis and generating positive messages that match the sentiment.

[0623] Step 5:

[0624] The server selects or generates visual data based on the generated information content. The input is the generated information content and emotional state, and the output is the corresponding visual data. This includes specific actions such as applying appropriate filters to images using the Adobe Photoshop API.

[0625] Step 6:

[0626] The terminal notifies the user of the generated information and visual data. The input is generated data from the server, and the output is notification information that the user can confirm. This also includes specific actions such as user confirmation of the notification.

[0627] Step 7:

[0628] The user checks the notified post content and shares the information on social media. After sharing, the device collects reaction data and sends it to the server. The input is the user's sharing action, and the output is the reaction data. This specifically illustrates how the information receives reactions such as "likes" and comments.

[0629] Step 8:

[0630] The server updates the analysis model based on the collected reaction data. The input is reaction data from social media, and the output is the updated analysis model. Specific actions such as retraining the model are then performed to improve the accuracy of the next information generation algorithm.

[0631] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0632] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0633] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0634] [Fourth Embodiment]

[0635] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0636] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0637] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0638] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0639] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0640] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0641] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0642] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0643] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0644] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0645] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0646] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0647] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0648] This invention is a system for optimizing and increasing the influence of user posts on social networking services (SNS). This system analyzes users' past posting data and trend data, and generates and suggests effective posting content, timing, and hashtags, thereby improving the efficiency of SNS marketing.

[0649] First, users link their social media accounts to the system and grant permission for analysis. This allows the system to collect the user's past posting data. The server then applies machine learning algorithms to analyze the collected data. Through this analysis, effective elements derived from past successes are identified, and posting strategies are formulated.

[0650] Furthermore, the server considers the activity times of the user's followers and trends on social media to determine the optimal posting timing. Based on this, the time of day when the user is most likely to gain engagement is suggested. Subsequently, in selecting hashtags, popular tags and tags related to the user's posting area are suggested.

[0651] For example, if a user tries to post cat-related content, the server will suggest highly relevant hashtags such as "cat" and "cat lover." Regarding posting timing, it will suggest nighttime hours to target the peak activity period of followers.

[0652] Next, the server uses AI to generate posts and related images that are likely to go viral based on this information. For example, it might generate posts that emphasize the cute movements of cats, or images that have trending filters applied.

[0653] The generated content and suggestions are notified to the user's device for review. The user then uses these suggestions to create a post and actually posts it on social media. After posting, the server collects the reactions again and uses this data to update the analysis model. This further improves the accuracy and effectiveness of future suggestions.

[0654] This system reduces the stress and trial-and-error involved in posting, allowing users to effectively increase their presence on social media.

[0655] The following describes the processing flow.

[0656] Step 1:

[0657] Users link their social media accounts to the system and grant the necessary permissions for analysis. This linkage allows the server to automatically collect past social media posting data.

[0658] Step 2:

[0659] The server stores the posted data collected via the API into a database, and also retrieves the latest social media trend data and follower activity information. This data is used for subsequent analysis.

[0660] Step 3:

[0661] The server performs data cleansing, removing noise and unnecessary data to prepare it for analysis. This cleansing process ensures that only essential data is fed into the model.

[0662] Step 4:

[0663] The server feeds the cleansed data into a machine learning algorithm to learn the characteristics of successful posts. Natural language processing and clustering techniques are commonly used here.

[0664] Step 5:

[0665] Based on the analysis results, the server generates post content, optimal posting timing, and recommended hashtags suitable for the user. At this time, historical data and trend data are integrated to create a summary of suggestions.

[0666] Step 6:

[0667] The server uses AI technology to automatically generate or select images that match the suggested post. The generated post text is also adjusted to align with the user's theme.

[0668] Step 7:

[0669] The server notifies the user's device of the generated post content and suggestions. The notified information is in a format that the user can easily review. The user then prepares their post based on this information.

[0670] Step 8:

[0671] Users review the proposal, make any necessary modifications or edits, and then post it on the social media platform.

[0672] Step 9:

[0673] The server automatically collects engagement data (such as the number of likes and comments) obtained after a post is made and stores it in a database. This data will be used for future analysis.

[0674] Step 10:

[0675] The server retrains the analysis model using newly collected engagement data, improving the accuracy of subsequent suggestions. This iterative process allows for continuous improvement of the system's effectiveness.

[0676] (Example 1)

[0677] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0678] On social networking services, there is a need to effectively create posts that enhance user influence and engagement. However, it is cumbersome and unpredictable for users to analyze their past posts and determine the optimal content, timing, and hashtags. Therefore, there is a need for a method that automatically generates effective posts and makes that success sustainable.

[0679] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0680] In this invention, the server includes means for acquiring the user's past information, means for analyzing the information to create effective posting content, and means for suggesting posting times and labels based on the analysis results. This enables users to make posts that enhance their presence on social media efficiently and effectively.

[0681] A "user" refers to an individual or group that uses a social networking service.

[0682] "Information" refers to past posts made by users on social networking services, follower activity data, engagement data, and so on.

[0683] "Analysis" refers to the process of deriving effective post content and suggestions based on collected information, and includes the use of machine learning algorithms.

[0684] "Posted content" refers to text, images, videos, and other related data that users upload to social networking services.

[0685] "Creation" refers to the process of generating new post content based on the analyzed data.

[0686] "Suggestions" refer to providing users with recommended posting times and labels (hashtags).

[0687] "Time" refers to time information that has been determined to be effective when posting during a specific time period.

[0688] "Labels" refer to tags and hashtags used to improve the discoverability of posts on social networking services.

[0689] "Notification" refers to the act of informing users of analysis results and generated suggestions.

[0690] "Improvement" refers to updating the analysis model based on newly acquired data to enhance the accuracy and effectiveness of subsequent proposals.

[0691] This invention is a system for effectively optimizing user posts on social networking services and increasing their influence on SNS. This system acquires and analyzes a user's past posting information to suggest posting content, timing, and hashtags. Furthermore, it utilizes a generative AI model to automatically generate creative posts and images. Specific embodiments are described below.

[0692] First, users link their social media accounts to the system and grant permission for data analysis. This allows the system to retrieve the user's past posting information and store it in a database. The server then performs analysis based on this information. The analysis includes data preprocessing using the Python Pandas library and model building using machine learning algorithms with Scikit-learn. This identifies elements of effective posting content and the optimal posting timing.

[0693] Next, the server uses SNS APIs to retrieve follower activity times and trend information. Based on this data, it suggests appropriate posting timings and relevant labels to the user. In this process, a generative AI model is used to automatically generate post text and related images. The generative model used is a general-purpose AI for natural language processing and image generation, specifically OpenAI's GPT and image generation algorithms.

[0694] The generated content and suggestions are notified to the user via their device. The user can review them, edit them as needed, and post them to social media. After posting, the server collects reaction data in real time and updates the analysis model to further improve the accuracy of future suggestions.

[0695] For example, if a user tries to post content with a "cat" theme, the server suggests popular labels such as "cat" and "cat lover," and recommends that the user post during times when their followers are most active. Furthermore, a generative AI model can be used to generate creative captions that highlight the cuteness of cats, as well as images filtered with trending topics.

[0696] A concrete example of a prompt to the generating AI model would be, "Please suggest popular hashtags and viral post phrases for cat-related social media posts." In this way, the present invention helps users optimize their social media activities to a high degree, enabling them to exert greater influence.

[0697] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0698] Step 1:

[0699] Users link their social media accounts to the system and grant permission to retrieve data. Based on this input, the system collects the user's past posting information via an API. This information includes text, media, and engagement counts. As output, this information is stored in a database. Specifically, the user clicks the link button on the system interface and grants the necessary permissions.

[0700] Step 2:

[0701] The server receives the collected posting information and performs analysis. The input is the user's past posting data. The analysis includes data preprocessing (cleaning, normalization) and the application of a machine learning model. This model extracts the factors that contribute to a successful post. As output, the elements of an effective post are identified. Specifically, the server preprocesses the data using Python's Pandas library and performs analysis using Scikit-learn.

[0702] Step 3:

[0703] The server uses social media APIs to collect trend information and follower activity data. Inputs include real-time trend information obtained from social media and access times from follower logs. This allows the server to calculate the optimal posting timing and associated labels. The output generates recommended time slots and tags. The server periodically retrieves data via social media APIs and feeds this information into the algorithm.

[0704] Step 4:

[0705] The server automatically generates posts and images using a generative AI model. Inputs include user posting themes and insights from past data. The output is creative text and images. Specifically, the server prompts the generative AI, which then generates content using GPT and image generation algorithms.

[0706] Step 5:

[0707] The device notifies the user of the generated post content and suggestions. The input is the generated content and suggestion information transferred from the server. As output, the user who receives the notification can review the content and edit the post. Specifically, the device conveys the information to the user via push notification or email.

[0708] Step 6:

[0709] Users use the suggestions as a reference and post to social media. The input is generated content that the user can edit or use as is. The output is the real-time post on social media, and engagement data is obtained. The server then collects this reaction data and uses it to update the model. Specifically, the server continuously tracks post engagement through the social media API.

[0710] (Application Example 1)

[0711] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0712] To effectively deliver advertisements and content on online social platforms, there is a need for a system that can generate and suggest appropriate content in real time based on users' past data and visual environment. However, conventional systems struggle to quickly and accurately reflect users' interests and visual environment in their posts. In particular, there are challenges in optimizing advertisements, such as timing and generating highly relevant visual data to maximize their effectiveness.

[0713] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0714] In this invention, the server includes a device for acquiring the user's past data, a device for analyzing the data to generate effective content, and a device for generating relevant advertising materials in real time based on the environment the user sees through their visual device. This enables the generation of optimal posts based on the user's visual environment and past activities, and the suggestion of advertising materials in real time.

[0715] A "user" is an individual or legal entity that uses the system to post content or optimize advertisements on online social platforms.

[0716] "Past data" refers to information that includes posts, reactions, and associated metadata previously created and published by users.

[0717] "Device" refers to a combination of hardware and software that enables the acquisition, analysis, generation, proposal, and distribution of digital data.

[0718] An "analytical model" is an algorithm based on mathematical or AI technology used to extract regularities or patterns from collected data.

[0719] "Identifier" is a term that refers to tags or keywords used to identify topics or categories within social media.

[0720] "Visual devices" refer to electronic devices that allow users to obtain information about their surroundings by wearing or using them, and which include elements of augmented reality.

[0721] "Advertising materials" are visual or text content generated for promotional purposes that are customized in real time based on user interests and behavior.

[0722] "Real-time" refers to a state with virtually no delay, where information processing is performed immediately and results are provided on the spot.

[0723] This invention provides a system that allows users to maximize the effectiveness of their posts and advertisements on social media. The system mainly consists of a server and user terminals, and it proposes appropriate content and timing to users through data collection, analysis, and generation.

[0724] The server first retrieves the user's past posting data from their social media account. This data includes metadata such as the content of the post, the time of posting, and related reactions. Next, the server applies machine learning algorithms to analyze this data and build an analytical model to identify the success factors of the user's posts.

[0725] Subsequently, the server suggests appropriate posting timings and identifiers, taking into account the activity times and trend data of the user's social media followers. Furthermore, if the user is using a visual aid, it generates advertising material in real time based on that visual information. In this process, image data captured by the visual aid is analyzed, and relevant advertisements and identifiers are shown to the user.

[0726] The generated content and suggestions are notified to the user's device (such as a smartphone or smart glasses). The user then posts content to social media, taking these suggestions into consideration. After posting, the server collects the responses again and updates the analysis model to improve the accuracy of future suggestions.

[0727] As a concrete example, a user wearing smart glasses in a cafe could have advertisements related to the cafe's topics and products automatically generated and posted to social media. An example of a prompt would be, "Please explain the process for generating social media posts related to the object the user is currently viewing."

[0728] This invention enables optimal social media activities based on users' real-time situations and past behavior, thereby efficiently improving marketing effectiveness.

[0729] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0730] Step 1:

[0731] The server connects with the user's social media account and collects past posting data. Specifically, it obtains the user's post content, posting time, and reaction data via an API. This input data is used to build a dataset. The output is a structured dataset for future analysis.

[0732] Step 2:

[0733] The server applies machine learning algorithms to analyze the collected data. Specifically, it inputs the dataset into a classification algorithm to extract features that generate high engagement. This analysis generates a model that shows the trends of effective posts. The output is this model along with a list of success factors.

[0734] Step 3:

[0735] The server collects trend data and follower activity times, analyzes this data, and proposes optimal posting timings and associated identifiers. Specifically, it uses an analytical model to identify peak activity times and associated topics, taking real-time trend API and user behavior data as input. The output is a list of proposed posting times and identifiers.

[0736] Step 4:

[0737] If a user is using a visual aid, the device captures their visual data and sends it to the server. The server analyzes this data and generates advertising material relevant to the user's visual environment. Specifically, it uses an image recognition algorithm to analyze the visual information and generate relevant advertisements or identifiers. The output is advertising material tailored to the user's visual environment.

[0738] Step 5:

[0739] The server notifies the user's terminal of the generated content and suggestions. The terminal presents the user with optimized content suggestions and encourages the user to review and submit the content. The output is a notification message for the user to review.

[0740] Step 6:

[0741] When a user posts a suggested content to social media, the server collects reaction data for that post again. Specifically, it retrieves engagement data via an API and updates the previously built analysis model. This feedback loop improves the accuracy of future suggestions. The output is the updated analysis model.

[0742] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0743] This invention is a system for optimizing and increasing the influence of user posts on social networking services (SNS), incorporating an emotion engine that recognizes user emotions. This makes it possible not only to advise on the optimal posting timing and hashtags, but also to suggest personalized post content that corresponds to the user's emotional state.

[0744] First, the user links their social media account to the system. At this time, the user authorizes the emotion engine to run and begins collecting emotional data. The device uses the emotion engine to analyze the user's facial expressions, voice tone, etc., to determine the user's current emotional state.

[0745] Next, the server generates optimal post content based on the user's past posting data and collected sentiment data. Here, posts are created that are tailored to the user's emotions; for example, posts with a positive tone are suggested if the user is happy, and posts containing encouraging messages are suggested if the user is feeling down.

[0746] Furthermore, the server utilizes information from the emotion engine to select or generate images that match the user's emotions. This image selection process might involve techniques such as selecting images with calm tones when the user is in a calm mood, or generating bright and lively images when the user is excited.

[0747] The generated post content and images are notified to the user's device for review. Based on the system's suggestions, the user posts on social media. The server then analyzes the engagement results of the post and updates the database to use the findings for future suggestions.

[0748] For example, if the emotion engine detects a user's emotions while watching a match, the server generates a post expressing the excitement related to the match and suggests an image that represents the atmosphere of the stadium. In this way, it is possible to support information dissemination in a manner that best suits the user's emotions and improve their engagement on social media.

[0749] The following describes the processing flow.

[0750] Step 1:

[0751] Users link their social media accounts to the system and authorize the collection of emotional data. In doing so, users consent to the system using an emotion recognition engine, enabling the system to analyze their emotions.

[0752] Step 2:

[0753] The device captures the user's facial expressions and voice through its camera and microphone, and inputs them into an emotion engine. This allows the engine to analyze and identify the user's real-time emotional state. For example, if the user is smiling, it recognizes "joy," and if they have a dejected expression, it recognizes "sadness."

[0754] Step 3:

[0755] In addition to sentiment data, the server collects the user's past posting data and follower reaction data. This data is stored in a database and serves as the basis for analysis.

[0756] Step 4:

[0757] The server uses machine learning algorithms to analyze collected data and generate posts optimized for the user's emotions. This results in posts with a tone and theme that matches the user's current feelings.

[0758] Step 5:

[0759] The server selects or generates relevant images based on the emotions determined by the emotion engine. Specifically, it provides bright and colorful images to users who are feeling happy, ensuring consistency with their emotions.

[0760] Step 6:

[0761] The server sends the generated post content and images to the user's device as suggestions based on their emotions. This process aims to present information in a format that is easily understandable to the user.

[0762] Step 7:

[0763] Users review the suggestions they receive on their devices and edit or modify them as needed. Once finished, they post the final content to social media.

[0764] Step 8:

[0765] The server automatically collects engagement data (e.g., number of likes, number of comments) obtained after a post is made and updates the database for analysis in conjunction with sentiment data.

[0766] Step 9:

[0767] The server uses the collected feedback data to retrain the sentiment engine and machine learning models, improving the accuracy and relevance of future suggestions. This feedback loop allows the system to continuously improve.

[0768] (Example 2)

[0769] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0770] Traditional social networking service posting systems could only suggest fixed timings and content without considering the user's emotional state. Therefore, they were unable to select the most appropriate content and images based on the user's current emotions, posing a challenge to maximizing engagement.

[0771] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0772] In this invention, the server includes means for acquiring past information of the user, means for analyzing the information and generating optimal post content based on the user's emotional state, and means for selecting or generating and suggesting posting timing, hashtags, and images appropriate to the emotion based on the analysis results. This makes it possible to generate optimal post content and images according to the user's emotional state.

[0773] "Users" refer to individuals or groups who use the system, and are primarily those who engage in posting activities on social networking services.

[0774] "Information" refers to all data that shows a user's past behavior and current emotional state, and this includes text, images, audio, etc.

[0775] "Analysis" refers to the process of analyzing acquired information to determine the user's emotional state and the most suitable content for posting.

[0776] An "emotion engine" refers to a technology that uses facial recognition and voice analysis to identify a user's emotional state in real time.

[0777] "Posted content" refers to messages and images that users send to other users on social networking services.

[0778] "Engagement" refers to the level of reaction and involvement from other users to a post, and includes likes, comments, shares, and so on.

[0779] "Image generation AI" refers to technology that automatically generates new images based on the user's emotional state and the content of their posts.

[0780] "Suggestions" refer to specific advice aimed at optimizing users' social networking activities, such as posting timing and hashtags.

[0781] One embodiment of this invention is a system for optimizing user posts on social networking services. This system utilizes an emotion engine that recognizes the user's emotions.

[0782] First, users link their social networking service accounts to the system. This grants permission for the emotion engine to operate, and the collection of emotion data begins. The device uses a camera and microphone to capture the user's face and voice, and the emotion engine analyzes this data. Facial recognition and voice analysis technologies are used to identify the user's emotional state.

[0783] Next, the server generates appropriate content based on the user's past posts and real-time sentiment data. A generative AI model is used to generate messages and hashtags optimized for the user's current emotions. For example, if the user is happy, a positive message will be suggested.

[0784] Furthermore, the server selects or generates images that correspond to the emotion. For this purpose, it's possible to use image generation AI to create new images. Specifically, images with calm color tones are selected for calm emotions.

[0785] The generated post content and images are sent to the user's device, making them available for review. The user then actually posts the content on social media based on the suggestions.

[0786] Once a post is submitted, the server analyzes the engagement with that post. This analysis is recorded in a database to improve the accuracy of future suggestions.

[0787] As a concrete example, consider a situation where a user is excited during an event. When the emotion engine detects this emotion, the server suggests a fun message that reflects the excitement, along with an image that represents the atmosphere of the event. In this way, users can communicate information in a manner that best suits their emotions.

[0788] An example of a prompt message would be: "The user is excited about the sporting event they are watching. Generate social media posts and images that match this emotion."

[0789] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0790] Step 1:

[0791] Users link their social networking service accounts to the system. This linkage allows the system to input the user's profile information and past posting data. Based on this information, the system extracts posting trends and past engagement data.

[0792] Step 2:

[0793] The device captures the user's facial expressions and voice using its camera and microphone. This information is used as input for the emotion engine. The emotion engine identifies the user's emotional state by analyzing facial expressions using image processing technology and voice tone using voice analysis technology. As output, specific data is obtained indicating the user's current emotional state.

[0794] Step 3:

[0795] The server uses the past posting data collected in Step 1 and the sentiment data obtained in Step 2 as input. The generative AI model analyzes this data and generates posting content and recommended hashtags optimized for the user's sentiment. As output, customized text corresponding to the user's sentiment is obtained.

[0796] Step 4:

[0797] The server selects or generates images appropriate to the sentiment based on the post content provided by the generative AI model. Considering the output data from the sentiment engine, it uses an image generation AI to generate appropriate visual materials. The output of this step is visual data to be attached to the post.

[0798] Step 5:

[0799] The generated post content and images are notified to the user's device for review. The user reviews the suggested content on their device and edits it as needed. In this step, the final post content is determined once the user's consent is obtained.

[0800] Step 6:

[0801] The user posts the confirmed content to the social networking service. The server collects engagement data (likes, comments, shares, etc.) for that post. This data is recorded in a database to help with future analysis and suggestions. As an output of the step, the engagement results are stored in data storage.

[0802] (Application Example 2)

[0803] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0804] In today's information dissemination platforms, it is not easy for users to disseminate emotionally relevant and influential information, and achieving effective engagement is a challenge. Furthermore, the lack of personalized information delivery that responds to the emotional state of individual users often diminishes the quality of information and its impact on recipients.

[0805] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0806] In this invention, the server includes means for recognizing the user's emotional state and personalizing the information content, means for selecting or generating visual data that matches the emotional state, and means for collecting responses to newly transmitted information and updating the analysis model. This enables personalized information transmission according to the user's emotional state, thereby improving the quality and impact of the information.

[0807] "User's past information" refers to information and related data that a user has previously shared.

[0808] "Means of acquisition" refers to functions for collecting information via databases or networks.

[0809] "Means for analyzing and generating optimal information content" refers to a function that analyzes collected information and creates information that is beneficial and influential to the user.

[0810] "A means of suggesting the timing and tags for information dissemination based on analysis results" refers to a function that indicates the optimal time and associated identifiers for disseminating information based on the analysis results.

[0811] "Means of notification" refers to communication functions for informing users of generated information and suggestions.

[0812] "Means for collecting responses to newly disseminated information and updating the analysis model" refers to a function that collects and analyzes the responses of recipients to disseminated information and improves the analysis system based on the results.

[0813] "Means for recognizing a user's emotional state and personalizing information content according to that emotional state" refers to a function that detects a user's emotions and generates unique information based on that information.

[0814] "Means for selecting or generating visual data" refers to functions for selecting or creating images or videos that match the user's emotional state.

[0815] The server operates in a cloud environment to analyze historical information and emotional data collected from the user's smart device. At startup, the user imports their information into the system via their smart device. This includes biometric information to identify past information history and current emotional state. The emotion engine uses, for example, OpenAI's GPT model or Microsoft Azure's emotion recognition API. This allows for the analysis of emotions from the user's voice tone and facial expressions.

[0816] The device analyzes the emotional state in real time and uses the results to create prompts for the generative AI model. An example of a prompt might be, "If the user is feeling calm and peaceful, suggest the most appropriate effects and text from past calm posts." The generative AI model generates the most appropriate information and tags in response to this prompt and utilizes image processing software (e.g., Adobe Photoshop API) for visual data selection. This automatically selects or generates visual data that matches the emotion.

[0817] Users review the suggestions notified from their devices and share them as information on social media. Response data from recipients of the shared information is fed back to the server and used to update the analysis model. This feedback loop allows the system to self-improve so that future information dissemination is even more effective.

[0818] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0819] Step 1:

[0820] Users provide information to the system using their smart devices. This input includes past information history and current biometric data (facial expressions and voice tone). The device collects this data and sends it to a server for processing. As output of this data, a basic information profile of the user is formed.

[0821] Step 2:

[0822] The server uses the received biometric data to perform analysis with its emotion engine. Here, it uses Microsoft Azure's emotion recognition API to identify the user's current emotional state. The input data is biometric information, and the output is a label for the identified emotional state. Based on the analysis, specific actions are taken, such as determining that the user's emotional state is "calm."

[0823] Step 3:

[0824] The server generates a prompt for the AI ​​model. This prompt asks for the most appropriate suggestion based on past information history. The input is the identified emotional state and past data profile, and the output is the generated prompt. Specifically, the server generates a sentence such as, "If the user is feeling calm and peaceful, suggest the most appropriate effect and text based on past calm posting data."

[0825] Step 4:

[0826] The generative AI model generates information content and tags based on prompt text. The input data is the prompt text, and the output is the generated post content and optimal tag suggestions. Specific operations include text analysis and generating positive messages that match the sentiment.

[0827] Step 5:

[0828] The server selects or generates visual data based on the generated information content. The input is the generated information content and emotional state, and the output is the corresponding visual data. This includes specific actions such as applying appropriate filters to images using the Adobe Photoshop API.

[0829] Step 6:

[0830] The terminal notifies the user of the generated information and visual data. The input is generated data from the server, and the output is notification information that the user can confirm. This also includes specific actions such as user confirmation of the notification.

[0831] Step 7:

[0832] The user checks the notified post content and shares the information on social media. After sharing, the device collects reaction data and sends it to the server. The input is the user's sharing action, and the output is the reaction data. This specifically illustrates how the information receives reactions such as "likes" and comments.

[0833] Step 8:

[0834] The server updates the analysis model based on the collected reaction data. The input is reaction data from social media, and the output is the updated analysis model. Specific actions such as retraining the model are then performed to improve the accuracy of the next information generation algorithm.

[0835] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0836] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0837] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0838] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0839] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0840] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0841] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0842] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0843] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0844] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0845] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0846] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0847] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0848] 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.

[0849] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0850] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0851] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0852] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0853] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0854] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0855] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0856] The following is further disclosed regarding the embodiments described above.

[0857] (Claim 1)

[0858] Means for obtaining the user's past data,

[0859] A means for analyzing the data to generate effective posting content,

[0860] A means of suggesting posting timing and hashtags based on analysis results,

[0861] A means of notifying users of the generated post content and suggestions,

[0862] A means of collecting reactions to newly posted content and updating the analysis model,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, which generates personalized suggestions based on the user's past posting style.

[0866] (Claim 3)

[0867] The system according to claim 1, which automatically generates images relevant to the content of a post.

[0868] "Example 1"

[0869] (Claim 1)

[0870] Means for obtaining the user's past information,

[0871] A means of analyzing the information to create effective posting content,

[0872] A means of proposing the posting time and label based on the analysis results,

[0873] A means of informing users of the generated post content and suggestions,

[0874] A method for collecting responses to newly posted content and improving the analysis model,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, which generates personalized suggestions based on patterns in the user's past posts.

[0878] (Claim 3)

[0879] The system according to claim 1, which automatically generates visual information related to the content of a post.

[0880] "Application Example 1"

[0881] (Claim 1)

[0882] A device for acquiring the user's past data,

[0883] A device that analyzes the data and generates effective content,

[0884] A device that proposes posting time and identifier based on analysis results,

[0885] A device that informs the user of the generated content and suggestions,

[0886] A device that collects responses to newly posted information and updates the analysis model,

[0887] A device that generates relevant advertising materials in real time based on the environment viewed by the user through a visual device,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, which generates personalized suggestions based on the user's past expression style.

[0891] (Claim 3)

[0892] The system according to claim 1, which automatically generates visual data relevant to the content.

[0893] "Example 2 of combining an emotion engine"

[0894] (Claim 1)

[0895] Means for obtaining past information about users,

[0896] A means for analyzing the information and generating optimal post content based on the user's emotional state,

[0897] A means for selecting or generating and suggesting images that are appropriate for the posting timing, hashtags, and sentiment based on the analysis results,

[0898] A means of notifying users of the generated post content and suggestions and allowing them to confirm them,

[0899] A means of collecting reactions to newly posted content and updating the analysis model,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, which uses an emotion engine to identify the emotional state of a user using facial recognition and voice analysis.

[0903] (Claim 3)

[0904] The system according to claim 1, which automatically selects or generates images relevant to the content of a post based on the emotional state.

[0905] "Application example 2 when combining with an emotional engine"

[0906] (Claim 1)

[0907] Means for obtaining the user's past information,

[0908] A means for analyzing the information and generating optimal information content,

[0909] A means of proposing the timing and tags for information dissemination based on the analysis results,

[0910] A means of notifying the user of the generated information content and suggestions,

[0911] A means of collecting responses to newly disseminated information and updating the analysis model,

[0912] A means for recognizing the user's emotional state and personalizing the information content according to that emotional state,

[0913] A means for selecting or generating visual data that matches an emotional state,

[0914] A system that includes this.

[0915] (Claim 2)

[0916] The system according to claim 1, which generates personalized suggestions based on the user's past information sharing style.

[0917] (Claim 3)

[0918] The system according to claim 1, which automatically generates visual data relevant to the information content. [Explanation of Symbols]

[0919] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for obtaining the user's past data, A means for analyzing the data to generate effective posting content, A means of suggesting posting timing and hashtags based on analysis results, A means of notifying users of the generated post content and suggestions, A means of collecting reactions to newly posted content and updating the analysis model, A system that includes this.

2. The system according to claim 1, which generates personalized suggestions based on the user's past posting style.

3. The system according to claim 1, which automatically generates images relevant to the content of a post.

Images