system

Abstract

We provide the system. [Solution] Means for collecting user-generated data, A means for performing sentiment analysis based on the user-generated data and detecting negative emotions, Based on the results of sentiment analysis, a means of sending alerts to users, A method for predicting the optimal posting time based on past performance data, A means of automatically generating content, The means for providing the automatically generated content to the user, 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 steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern digital society, it is extremely important for companies and individuals to effectively utilize social media. However, tasks such as content generation, optimization, and customer support require a great deal of time and effort and are often inconsistent. Also, it is difficult to grasp negative user reactions in real time, and appropriate responses may be delayed. Furthermore, optimizing visual content and predicting the optimal timing of posting are also complex tasks. For these problems, means to efficiently and integrally address them are required.

Means for Solving the Problems

[0005] To address this challenge, we provide a system equipped with the following features. This system first collects user-generated data and performs sentiment analysis based on it to instantly detect negative emotions. Based on the detection results, it enables a rapid response by issuing alerts to users. It also provides a function to predict the optimal posting time by analyzing past performance data using machine learning algorithms. Furthermore, an automatic content generation function enables the generation and provision of consistent, high-quality posts to users. In addition, by incorporating a function to recognize and optimize visual data and an interactive response function via a chatbot, it can effectively address a wide range of social media management needs.

[0006] "User-generated data" refers to text, images, videos, and associated metadata posted by users on social media platforms.

[0007] "Sentiment analysis" is the process of analyzing the content of user-generated data and determining whether the emotions contained within it are positive, negative, or neutral.

[0008] An "alert" refers to a warning message that notifies a user when certain conditions are met.

[0009] "Performance data" refers to data that records engagement rates, reactions, and follower growth / decrease related to past social media posts.

[0010] "Automated content generation" refers to the process of automatically creating content such as text and images using software.

[0011] "Visual data" refers to visual content such as images and videos, and by analyzing this data, visual information can be extracted and optimized.

[0012] A "chatbot" refers to a program that uses artificial intelligence to interact with users in natural language, and can automate common inquiries and support tasks. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a labeled 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 a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] [[ID=·23]] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] The system of this invention streamlines the operation of social media through the cooperation of servers, terminals, and users.

[0035] Server operation

[0036] The server collects user-generated data in real time from social media platform APIs. This includes metadata such as comments, shares, and likes on a brand's posts. The collected data is stored in a database and passed to a sentiment analysis module. The server uses natural language processing algorithms to analyze the data and determine negative, positive, and neutral sentiments. Based on this analysis, if there are many negative reactions, an alert is immediately generated and the user is notified.

[0037] Furthermore, the server aggregates past posting data and uses machine learning algorithms to predict the optimal posting time. This maximizes engagement with posted content. With the automated content generation feature, the server automatically creates posts and captions in a tone based on brand guidelines. This process enables consistent information dissemination while minimizing intervention from content managers.

[0038] Furthermore, it recognizes and optimizes visual data such as images and videos. This process ensures that visual content is delivered in a more engaging format.

[0039] Terminal operation

[0040] The device provides an interface for the user, displaying real-time analysis results and content suggestions. Users can preview recommended posting times and generated content, and edit them as needed. Alerts from the server are notified to the user through the device, enabling quick responses.

[0041] User actions

[0042] Users can develop effective social media strategies based on the information provided on their devices. For example, when planning a new product campaign, users can use the optimal posting time and generated content suggested by the server to prepare posts according to the schedule. Additionally, a chatbot function provides 24 / 7 customer support and can automatically handle common inquiries.

[0043] This type of system allows users to manage social media platforms in a timely and effective manner and monitor their brand's reputation.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server collects user-generated data through social media platform APIs. This includes information such as posts, comments, and reactions. The collected data is stored in a database.

[0047] Step 2:

[0048] The server uses natural language processing to perform sentiment analysis based on the collected data. This allows for an understanding of the sentiment of posts and comments, classifying them as positive, negative, or neutral. If a large number of negative sentiments are detected, the server immediately generates an alert and notifies the administrator.

[0049] Step 3:

[0050] The server analyzes past posting data to identify the best times for engagement. Using machine learning algorithms, it learns successful posting patterns from the past and predicts the optimal posting times for the future.

[0051] Step 4:

[0052] The server uses an automated content generation module to generate posts and captions that comply with brand guidelines. The generated content is optimized based on past engagement data.

[0053] Step 5:

[0054] The device presents users with recommended posting times from the server, generated content, and alerts through an intuitive dashboard. Based on this information, users can review and edit their posts and schedules.

[0055] Step 6:

[0056] Users upload images and videos through their devices. The devices send these to a server, which analyzes the visual data and generates optimization suggestions. The devices then present these suggestions to the user, who can make adjustments as needed.

[0057] Step 7:

[0058] The server provides a 24 / 7 chatbot function, automatically responding to general inquiries. In special cases or when escalation is necessary, it notifies the appropriate person to take action.

[0059] Step 8:

[0060] Users leverage information and features provided by the server to implement effective social media strategies. This allows users to improve their brand reputation and build deeper engagement with their target audience.

[0061] (Example 1)

[0062] 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."

[0063] With the rapid increase in user-generated information on information exchange platforms, it is becoming difficult for information providers to quickly obtain useful insights. Furthermore, if negative reactions are not detected early and appropriate responses cannot be taken, the reputation of the information provider or their brand may be damaged. In addition, manually selecting the optimal information distribution time and automatically generating effective content is difficult, and the development of efficient strategies is required.

[0064] 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.

[0065] In this invention, the server includes means for collecting information from an information exchange infrastructure, means for performing text analysis based on the information and detecting negative emotions, and means for sending a warning to the information provider based on the results of the text analysis. This enables the information provider to obtain emotional insights in real time, allowing for a rapid response and efficient information management.

[0066] An "information exchange platform" is a platform that serves as the foundation for exchanging information over a digital network.

[0067] "Information" refers to content and data that users generate or share on social media and online platforms.

[0068] "Text analysis" is the process of analyzing emotions and intentions from text data using natural language processing technology.

[0069] "Negative emotions" are negative reactions from users that indicate dissatisfaction or criticism, as detected through sentiment analysis.

[0070] A "warning" is a notification issued by the system based on the results of sentiment analysis to prompt the information provider to take immediate action.

[0071] An "information provider" is an entity that generates, manages, or disseminates content on an online platform.

[0072] An embodiment of this invention is a system for information providers to streamline the operation of a social media platform, in which the server, terminal, and user work in high-level coordination.

[0073] Server operation

[0074] The server collects user-generated information from the information exchange platform using APIs. In this process, the server uses programming languages ​​such as Python and database software for information management (e.g., MySQL®). The collected information is stored in the database and processed as a preliminary step for analysis using natural language processing techniques.

[0075] The server uses natural language processing libraries (e.g., NLTK, TextBlob) to determine the sentiment of the information. If negative sentiment is detected, the server immediately sends a warning to the information provider. This process allows the information provider to quickly understand the situation and take appropriate action.

[0076] Furthermore, the server collects past posting data and uses machine learning algorithms (e.g., Scikit-learn) to predict the optimal delivery time. In addition, it provides a function to automatically generate content that matches the tone and style by utilizing generative AI models (e.g., GPT-3®).

[0077] Regarding visual information, the server can use image processing frameworks (e.g., OpenCV, TENSORFLOW®) to analyze and optimize collected images and videos. This makes the delivery of visual content more effective.

[0078] Terminal operation

[0079] The terminal provides users with an intuitive interface, displaying real-time analysis results, predictive information, and automatically generated content from the server. Through this interface, users can preview the generated content, edit it as needed, and respond quickly to warnings from the server.

[0080] User actions

[0081] Users can build strategies based on the information provided on their devices. For example, when planning a campaign for a new product, users can efficiently disseminate information by utilizing the optimal distribution time and automatically generated content. Furthermore, customer support can be strengthened by using an automated dialogue system that provides interactive responses to handle general inquiries.

[0082] Specific example

[0083] For example, suppose a user from a food company is promoting a new snack product. The server provides information such as, "According to market research, Friday at 6 PM is the best time to post," and also uses a generative AI model to automatically generate catchphrases like, "Check out this week's new snack!" Based on this information, the user can deliver content according to the set schedule and achieve effective engagement.

[0084] Example of a prompt

[0085] "Please create a positive introductory statement for the new product. Please follow the brand guidelines."

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The server collects data from the information exchange platform's API. As input, it sends user-generated information (e.g., number of comments, shares, likes) that meets specific criteria as API requests. As output, it retrieves this data in JSON format and saves it to the database. Specifically, the server is configured to periodically execute a Python script to retrieve the latest data from the API.

[0089] Step 2:

[0090] The server preprocesses the collected information through a text cleaning process. It receives raw information stored in a database as input. Unnecessary symbols and HTML tags are removed from this information, converting the text data into a clean format. The output is text data in a format suitable for analysis. Specifically, string manipulation using regular expressions is performed.

[0091] Step 3:

[0092] The server performs sentiment analysis on clean text data using natural language processing algorithms. It uses the text data obtained in the previous step as input. As output, it generates a sentiment score for each text and stores it in a database. Specifically, it performs sentiment scoring using the NLTK library, and if a text is judged to be negative, it proceeds with further analysis.

[0093] Step 4:

[0094] The server analyzes past posting data using a machine learning algorithm to predict the optimal posting time. It takes past posting history and engagement data as input. As output, it generates a predicted optimal posting time. Specifically, it trains the Scikit-learn random forest algorithm and provides the prediction results.

[0095] Step 5:

[0096] The server automatically generates content using a generative AI model. It takes a prompt (e.g., "Create a positive description of the new product") as input. The generated content is retrieved as output in text format. Specifically, this involves sending a prompt to the generative AI model via a machine learning API and retrieving the returned generated text.

[0097] Step 6:

[0098] The server analyzes visual information to perform image recognition and optimization. It receives image and video data obtained from social media as input. It generates optimized visual information as output. Specifically, it uses TensorFlow and OpenCV to perform image compression and file extension conversion.

[0099] Step 7:

[0100] The terminal notifies the user of analysis results, generated content, and warnings sent from the server. It receives various data from the server via communication protocols as input. It displays information on the user interface as output. Specifically, it provides a real-time updated dashboard and includes notification functionality.

[0101] Step 8:

[0102] Users develop strategies based on information provided through the device interface. Inputs include optimization time, generated content, and warning messages. Outputs include planning product campaigns and creating posting schedules. Specifically, users evaluate received suggestions and edit content and prepare posts as needed.

[0103] (Application Example 1)

[0104] 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."

[0105] In today's social media environment, companies need to communicate with consumers efficiently and conduct effective advertising. However, it is not easy to grasp consumer sentiment and market trends in real time and respond quickly based on that information. Furthermore, while timely content posting and optimization of visual data are also required, there is a lack of systems to efficiently manage these aspects. In particular, there are challenges in optimizing advertising campaigns that cannot be adequately addressed with traditional methods.

[0106] 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.

[0107] In this invention, the server includes means for collecting user-generated data, means for performing sentiment analysis and detecting negative emotions, means for predicting the optimal posting time, and means for optimizing promotional activities. This enables companies to grasp market trends in real time and deploy strategic advertising based on consumer emotions.

[0108] "User-generated data" refers to information such as posts, comments, and ratings created by users, which are stored and shared on the platform.

[0109] "Sentiment analysis" is a process that uses natural language processing technology to determine a user's emotional state (negative, positive, neutral, etc.) from text data.

[0110] A "warning" is a notification or message intended to inform a user of the possibility of unexpected problems or negative consequences.

[0111] "Performance data" refers to information that shows the history of reactions and engagement to past posts and information content, and is used to optimize the system.

[0112] "Posting time" refers to the optimal time to publish user-generated data and content on the platform, and is important for gaining a lot of engagement.

[0113] "Information content" refers to all content provided to users, including media such as text, images, and videos.

[0114] "Market trends" are indicators that show changes in consumer preferences and behavioral patterns, as well as trends, in a particular market, and they influence decision-making in economic activities.

[0115] "Promotional activities" refer to public relations and marketing activities aimed at increasing consumer awareness and stimulating demand for products and services.

[0116] The system for implementing this invention primarily involves the cooperation of a server, a terminal, and a user. The server first collects user-generated data in real time using the API of a social media platform. This data includes user posts, comments, ratings, etc. The collected data is stored in a database, and sentiment analysis is performed using natural language processing algorithms. In this process, the server classifies whether the user's sentiment is negative, positive, or neutral, and issues warnings as necessary.

[0117] The server further uses machine learning algorithms based on collected historical performance data to predict the optimal posting time. This prediction makes it possible to maximize engagement with the information content. It also has a function to analyze market trends in real time to optimize promotional activities.

[0118] The terminal provides a user interface, displaying analysis results sent from the server, recommended posting times, and generated information. Through this terminal, users can make strategic decisions based on the presented information. For example, when promoting a new product, it's possible to run a campaign at the optimal time predicted by the server.

[0119] As a concrete example, a food brand is planning a campaign for a new drink. Using this application, the brand manager can determine the right timing and directly reach consumers with the most suitable content.

[0120] When using a generative AI model, the following prompt statements are possible:

[0121] "For a new drink campaign from a certain food brand, please suggest the optimal timing for posting information on social media. Please provide predictions based on past engagement data."

[0122] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0123] Step 1:

[0124] The server uses social media platform APIs to collect user-generated data. This data includes posts, comments, ratings, etc. The collected data is stored in a database and used for subsequent processing. The input is raw data obtained through the API, and the output is data stored in a formatted manner in the database.

[0125] Step 2:

[0126] The server applies natural language processing to stored user-generated data to perform sentiment analysis. This process analyzes the text of the data to classify whether it carries positive, negative, or neutral sentiment. The input is text data from the database, and the output is the sentiment classification result for each text. Specifically, it uses a text analysis library to perform tokenization and grammatical analysis.

[0127] Step 3:

[0128] Based on the sentiment analysis results, the server sends a warning to the device if there is a high concentration of negative emotions. This warning allows the user to take immediate action. The input is the sentiment analysis classification result, and the output is the warning message. The user can view this message on their device. Specifically, a push notification is sent using the notification function.

[0129] Step 4:

[0130] The server collects historical performance data and uses a machine learning algorithm to predict the optimal posting time. This prediction is used to maximize engagement for future posts. The input is historical engagement data, and the output is the predicted optimal posting time. Specifically, it performs machine learning model training and prediction processing.

[0131] Step 5:

[0132] The terminal displays analysis results sent from the server, recommended posting times, and generated information content in a user interface. This allows users to make timely strategic decisions. The input is analysis results and predicted data from the server, and the output is the information displayed on the terminal. Specifically, it performs graphical data display using a UI framework.

[0133] Step 6:

[0134] Users utilize the information provided on their devices to implement campaign and posting plans. Through the application, users can select and execute specific, data-driven actions. Input is the displayed information, and output is the actual actions performed by the user. Specifically, users configure settings using buttons and forms provided within the application.

[0135] 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.

[0136] The system of this invention streamlines social media operations through the coordination of servers, terminals, and users, and enables advanced interaction using an emotion engine.

[0137] Server operation

[0138] The server collects user-generated data from social media platforms. Examples include user posts, comments, and metadata. This data is stored in a database and passed to a sentiment analysis module. The server uses a sentiment engine to perform more detailed sentiment analysis, recognizing user emotions in real time. This information is used to determine whether posts and comments are positive, negative, or neutral. If a large number of negative emotions are detected, an alert is immediately generated to notify the user.

[0139] Furthermore, the server analyzes past performance data based on sentiment data obtained from the sentiment engine to predict the optimal posting time. It also utilizes this sentiment data to automatically generate more personalized content. For example, if it detects a pattern indicating user satisfaction, it generates content with a tone that matches that emotion.

[0140] Terminal operation

[0141] The device intuitively displays sentiment analysis results from the server, recommended posting times, and generated content to the user. Through this interface, the user can receive alerts and preview and edit the provided content. Visual data uploads and optimization results are also viewed on this device.

[0142] User actions

[0143] Users can build effective social media strategies based on information provided from their devices. For example, if the sentiment engine detects trends within the user's target audience, it can determine content and posting times accordingly. Furthermore, users can utilize chatbot functionality to provide personalized responses to their target audience, thereby improving their reputation.

[0144] Based on this model, systems incorporating an emotion engine support more effective social media management that takes user emotions into account, thereby strengthening engagement with target audiences.

[0145] The following describes the processing flow.

[0146] Step 1:

[0147] The server collects user-generated data through social media platform APIs. This includes data on posts, comments, and related reactions. This data is stored in a database to prepare it for subsequent processing.

[0148] Step 2:

[0149] The server uses the collected data to run an emotion engine. This engine utilizes natural language processing technology to classify emotions such as positive, negative, and neutral from the data. It also recognizes the emotions of individual users in real time and understands their trends.

[0150] Step 3:

[0151] The server activates an alert system based on emotional data. When a certain level of negative emotion is detected, it immediately generates an alert and notifies the user.

[0152] Step 4:

[0153] The server analyzes past performance data and combines it with sentiment information from the sentiment engine to predict the optimal posting time. This prediction indicates the time of day when user engagement is maximized.

[0154] Step 5:

[0155] The server automatically generates content that reflects emotional data. For example, if a lot of joy is detected, it will generate content with a bright and positive tone that is appropriate for this. This content is optimized in accordance with brand guidelines.

[0156] Step 6:

[0157] The device provides users with an interface that displays generated content, optimal posting times, and alerts. Users can view this information and adjust their posting content and strategy.

[0158] Step 7:

[0159] Users develop effective social media strategies based on analysis results from the emotion engine. For example, if a target audience shows a positive response to a particular campaign, additional content tailored to that response will be provided.

[0160] Step 8:

[0161] Users can leverage chatbot functionality to receive personalized, real-time responses that resonate with their emotions. This feature allows users to deepen their relationships with their target audience and increase engagement.

[0162] (Example 2)

[0163] 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".

[0164] Effective social media management presents challenges in processing large volumes of user-generated data and analyzing the resulting sentiments in real time. Furthermore, manually posting at the appropriate time and creating personalized content is time-consuming and labor-intensive, and responding quickly to negative sentiments is difficult. A system is needed to address these issues.

[0165] 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.

[0166] In this invention, the server includes means for acquiring user-generated data, means for performing sentiment analysis based on the user-generated data and identifying negative emotions, and means for acquiring sentiment labels for text data using a natural language processing model. This enables automated sentiment analysis and real-time detection of negative emotions.

[0167] "User-generated data" refers to information such as comments, images, and videos posted by users on social media platforms.

[0168] "Sentiment analysis" refers to the process of classifying emotions in text using natural language processing techniques and assigning emotion labels such as positive, negative, and neutral.

[0169] "Negative emotions" refers to information indicating negative feelings contained in user-generated data.

[0170] A "natural language processing model" refers to a program that uses machine learning algorithms to analyze, classify, and generate natural language text.

[0171] "Sentimental labels for text data" refer to tags that indicate emotions such as positive, negative, and neutral, which are assigned to text through sentiment analysis.

[0172] A "time series analysis algorithm" refers to a computational method used to model changes in data over time and predict future data.

[0173] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to automatically generate new text and content.

[0174] One embodiment of this invention is one that enables effective social media operation by coordinating a server, a terminal, and a user.

[0175] The server is the main component that manages the overall processing. The server retrieves data in real time from social media platforms using APIs. The collected data is organized and stored in a database. Based on the obtained user-generated data, sentiment analysis is performed using the natural language processing library NLTK and the deep learning model BERT. This analysis identifies whether the sentiment of each post is positive, negative, or neutral, and if negative sentiment is detected, an alert is immediately generated.

[0176] Furthermore, the server uses time-series analysis algorithms based on historical data to predict the optimal posting time. In addition, it leverages generative AI models to automatically generate content tailored to the user's target audience. For example, it can generate posts with a similar tone based on elements that have previously pleased users. In this way, the server consistently delivers optimized content.

[0177] The device intuitively displays analysis results and content suggestions sent from the server to the user. Based on the results and suggestions, the user can quickly adjust their posts. The device also allows for the uploading of visual data and confirmation of optimization results.

[0178] Users can build more effective social media strategies based on the information their devices provide. For example, they could launch new campaigns based on target audience trends revealed by sentiment analysis. Furthermore, they can improve engagement by fine-tuning generated content and posting it at the most opportune times.

[0179] An example of a prompt might be, "Generate text for the following post that will evoke positive emotions in the target audience." This allows the generation AI model to efficiently generate the specific content the user is looking for.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The server retrieves user-generated data using the APIs of social media platforms. This data includes posts, comments, and meta information. It accepts specific hashtags and account information as input and stores the retrieved data in a database as output. This stored data is then used for subsequent processing.

[0183] Step 2:

[0184] The server sends the stored user-generated data to the sentiment analysis module. It receives each text data item retrieved from the database as input, performs data calculations using a natural language processing library (e.g., NLTK or BERT), and labels the sentiment of each post. The output of this process is a sentiment label categorized as positive, negative, or neutral.

[0185] Step 3:

[0186] The server detects negative emotions based on the results of sentiment analysis. It receives emotion labels as input and generates an alert if negative emotions are predominant. The generated alert is immediately notified to the user, allowing them to recognize and address the problem early.

[0187] Step 4:

[0188] The server analyzes historical performance data to predict the optimal posting time. It receives historical interaction data and posting time history as input, and uses a time-series analysis algorithm to calculate the next recommended posting time as output. This information is used to optimize user operations.

[0189] Step 5:

[0190] The server generates content using an AI model based on sentiment analysis results. It receives user target audience profile information and sentiment trends as input, and uses prompts to instruct the AI ​​to generate content. The output is text and images optimized for the target audience, in a format usable by the user.

[0191] Step 6:

[0192] The terminal presents the user with analysis results and generated content sent from the server. It receives data from the server as input, visually organizes the information, and displays it as output. Based on this information, the user can adjust their posting content.

[0193] Step 7:

[0194] Users utilize data provided by their devices to develop effective posting strategies for their next posts. They receive device analytics results and recommendations as input, use them to plan their posts, and post content during the times when they are expected to perform best. This is expected to maximize user engagement on social media.

[0195] (Application Example 2)

[0196] 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 device 14 will be referred to as the "terminal."

[0197] When running advertising campaigns, it is difficult to respond immediately to the diverse emotions of users and maximize effectiveness in real time. Current methods are inefficient or sometimes delayed in quickly analyzing user feedback and optimizing ad content. This results in the challenge of not maximizing the effectiveness of advertising.

[0198] 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.

[0199] In this invention, the server includes a device for storing biometric information, a device for performing emotional evaluation based on the biometric information and detecting negative emotions, and a device for notifying the user based on the results of the emotional evaluation. This enables real-time evaluation of users' emotions in advertising campaigns, immediate detection of negative emotions, and rapid optimization of advertising content.

[0200] "Biometric information" refers to data that shows the emotional state and physiological responses of individual users.

[0201] "Emotional assessment" is a process that analyzes a user's emotions based on collected biometric information and determines whether they tend to be positive or negative.

[0202] "Negative emotions" refer to emotional states such as sadness and anger that lead to discomfort for the user.

[0203] "Notification" refers to the act of communicating specific information or warnings to a user, or the means of doing so.

[0204] "Performance data" refers to recorded information about past actions and performance, which is useful for developing efficient strategies.

[0205] "Communication time" refers to the time period during which specific information is most effectively transmitted.

[0206] "Information" refers to digital content generated based on the user's emotional state and behavior.

[0207] An "advertising campaign" refers to a series of activities carried out to increase awareness of a particular product or service and to stimulate demand.

[0208] "Measuring effectiveness" is the process of using quantitative and qualitative metrics to evaluate the success of an advertising campaign.

[0209] "Emotional data" refers to a dataset containing comprehensive information about users' emotional states.

[0210] For this invention to be implemented, coordination between the server, terminal, and user is crucial. The server first collects biometric information and performs an emotional assessment based on this information. Specifically, it stores the collected biometric information in a database and analyzes the user's emotions through an emotion analysis module. This emotion analysis uses an emotion engine to recognize in real time whether the user's emotions are positive or negative. If negative emotions are detected, a notification is immediately generated and transmitted to the user.

[0211] Furthermore, the server measures the effectiveness of advertising campaigns and automatically optimizes ad content using emotional data. This includes a process of calculating appropriate communication time based on past performance data and generating information tailored to the user's emotional state.

[0212] The device can intuitively display sentiment evaluation results and optimized advertising information provided by the server to the user. Through this interface, the user can receive notifications, review the provided advertisements, and send feedback as needed. This feedback is then sent back to the server for further analysis by the sentiment engine.

[0213] For example, when an advertiser conducts an advertising campaign using smartphones, they can analyze users' real-time emotional responses and quickly adjust the ad content. This process makes it possible to maximize the effectiveness of the advertising campaign and improve user engagement.

[0214] An example of a prompt would be, "How can we understand audience emotional responses to our advertising campaign in real time and make immediate adjustments?" By leveraging generative AI models, advertisers can use these emotional data-driven prompts to optimize their strategies.

[0215] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0216] Step 1:

[0217] The server acquires biometric information, including data collection from the user's smartphone or wearable device. Input data includes heart rate and facial expression data, which are temporarily stored on the server. This data is then passed to an emotion analysis module as output. The data collection and transfer are performed securely using a cloud storage service.

[0218] Step 2:

[0219] The server uses an emotion analysis module to analyze acquired biometric information. The input is the user's biometric information, and the output is an evaluation of their emotions. Specifically, the system performs pattern recognition and emotion classification using a generative AI model. This data processing allows the user's emotional state to be determined in real time as positive, negative, etc.

[0220] Step 3:

[0221] The server analyzes the sentiment evaluation results and immediately generates a notification if negative emotions are detected. This notification generation involves specific actions, such as taking the sentiment evaluation results as input and outputting a warning message to the user. The notification format is implemented as a text message or push notification.

[0222] Step 4:

[0223] The server analyzes advertising campaign performance data and calculates the appropriate communication time. The input is historical performance data, and the output is the optimal posting timing. This involves statistical methods using data analysis algorithms.

[0224] Step 5:

[0225] The server automatically generates advertising information using a generative AI model. The input consists of emotional data and calculated communication time, while the output is the generated advertising content. This process automatically constructs personalized advertising content.

[0226] Step 6:

[0227] The terminal displays sentiment ratings and advertising information sent from the server to the user. Input information is notification data from the server, and output is a display on the user interface. Specifically, it conveys information intuitively through a GUI (Graphical User Interface).

[0228] Step 7:

[0229] Users review the information provided via their devices and send feedback as needed. The input is the advertising information displayed on the device, and the output is feedback data sent to the server. This process allows the server to receive new data, enabling further optimization of the sentiment engine.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] [Second Embodiment]

[0234] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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".

[0246] The system of this invention streamlines the operation of social media through the cooperation of servers, terminals, and users.

[0247] Server operation

[0248] The server collects user-generated data in real time from social media platform APIs. This includes metadata such as comments, shares, and likes on a brand's posts. The collected data is stored in a database and passed to a sentiment analysis module. The server uses natural language processing algorithms to analyze the data and determine negative, positive, and neutral sentiments. Based on this analysis, if there are many negative reactions, an alert is immediately generated and the user is notified.

[0249] Furthermore, the server aggregates past posting data and uses machine learning algorithms to predict the optimal posting time. This maximizes engagement with posted content. With the automated content generation feature, the server automatically creates posts and captions in a tone based on brand guidelines. This process enables consistent information dissemination while minimizing intervention from content managers.

[0250] Furthermore, it recognizes and optimizes visual data such as images and videos. This process ensures that visual content is delivered in a more engaging format.

[0251] Terminal operation

[0252] The device provides an interface for the user, displaying real-time analysis results and content suggestions. Users can preview recommended posting times and generated content, and edit them as needed. Alerts from the server are notified to the user through the device, enabling quick responses.

[0253] User actions

[0254] Users can develop effective social media strategies based on the information provided on their devices. For example, when planning a new product campaign, users can use the optimal posting time and generated content suggested by the server to prepare posts according to the schedule. Additionally, a chatbot function provides 24 / 7 customer support and can automatically handle common inquiries.

[0255] This type of system allows users to manage social media platforms in a timely and effective manner and monitor their brand's reputation.

[0256] The following describes the processing flow.

[0257] Step 1:

[0258] The server collects user-generated data through social media platform APIs. This includes information such as posts, comments, and reactions. The collected data is stored in a database.

[0259] Step 2:

[0260] The server uses natural language processing to perform sentiment analysis based on the collected data. This allows for an understanding of the sentiment of posts and comments, classifying them as positive, negative, or neutral. If a large number of negative sentiments are detected, the server immediately generates an alert and notifies the administrator.

[0261] Step 3:

[0262] The server analyzes past posting data to identify the best times for engagement. Using machine learning algorithms, it learns successful posting patterns from the past and predicts the optimal posting times for the future.

[0263] Step 4:

[0264] The server uses an automated content generation module to generate posts and captions that comply with brand guidelines. The generated content is optimized based on past engagement data.

[0265] Step 5:

[0266] The device presents users with recommended posting times from the server, generated content, and alerts through an intuitive dashboard. Based on this information, users can review and edit their posts and schedules.

[0267] Step 6:

[0268] Users upload images and videos through their devices. The devices send these to a server, which analyzes the visual data and generates optimization suggestions. The devices then present these suggestions to the user, who can make adjustments as needed.

[0269] Step 7:

[0270] The server provides a 24 / 7 chatbot function, automatically responding to general inquiries. In special cases or when escalation is necessary, it notifies the appropriate person to take action.

[0271] Step 8:

[0272] Users leverage information and features provided by the server to implement effective social media strategies. This allows users to improve their brand reputation and build deeper engagement with their target audience.

[0273] (Example 1)

[0274] 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."

[0275] With the rapid increase in user-generated information on information exchange platforms, it is becoming difficult for information providers to quickly obtain useful insights. Furthermore, if negative reactions are not detected early and appropriate responses cannot be taken, the reputation of the information provider or their brand may be damaged. In addition, manually selecting the optimal information distribution time and automatically generating effective content is difficult, and the development of efficient strategies is required.

[0276] 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.

[0277] In this invention, the server includes means for collecting information from an information exchange infrastructure, means for performing text analysis based on the information and detecting negative emotions, and means for sending a warning to the information provider based on the results of the text analysis. This enables the information provider to obtain emotional insights in real time, allowing for a rapid response and efficient information management.

[0278] An "information exchange platform" is a platform that serves as the foundation for exchanging information over a digital network.

[0279] "Information" refers to content and data that users generate or share on social media and online platforms.

[0280] "Text analysis" is the process of analyzing emotions and intentions from text data using natural language processing technology.

[0281] "Negative emotions" are negative reactions from users that indicate dissatisfaction or criticism, as detected through sentiment analysis.

[0282] A "warning" is a notification issued by the system based on the results of sentiment analysis to prompt the information provider to take immediate action.

[0283] An "information provider" is a subject that generates, manages, or distributes content on an online platform.

[0284] An embodiment of this invention is a system for an information provider to improve the operation efficiency of a social media platform, in which a server, a terminal, and a user operate in highly coordinated manner.

[0285] Server Operations

[0286] The server collects user-generated information from an information exchange infrastructure using an API. At this time, the server uses a programming language such as Python and database software for information management (e.g., MySQL). The collected information is stored in a database and processed as a pre-stage for analysis using natural language processing technology.

[0287] The server uses a natural language processing library (e.g., NLTK, TextBlob) to determine the sentiment of the information. If a negative sentiment is detected, the server immediately sends a warning to the information provider. Through this process, the information provider can quickly understand the situation and respond.

[0288] In addition, the server accumulates past posting data and uses a machine learning algorithm (e.g., Scikit-learn) to predict the optimal delivery time. Furthermore, it provides a function to automatically generate content that matches the tone and style by leveraging a generative AI model (e.g., GPT-3).

[0289] Regarding visual information, the server can analyze and optimize the collected images and videos using an image processing framework (e.g., OpenCV, TensorFlow). This makes the delivery of visual content more effective.

[0290] Terminal Operations

[0291] The terminal provides users with an intuitive interface, displaying real-time analysis results, predictive information, and automatically generated content from the server. Through this interface, users can preview the generated content, edit it as needed, and respond quickly to warnings from the server.

[0292] User actions

[0293] Users can build strategies based on the information provided on their devices. For example, when planning a campaign for a new product, users can efficiently disseminate information by utilizing the optimal distribution time and automatically generated content. Furthermore, customer support can be strengthened by using an automated dialogue system that provides interactive responses to handle general inquiries.

[0294] Specific example

[0295] For example, suppose a user from a food company is promoting a new snack product. The server provides information such as, "According to market research, Friday at 6 PM is the best time to post," and also uses a generative AI model to automatically generate catchphrases like, "Check out this week's new snack!" Based on this information, the user can deliver content according to the set schedule and achieve effective engagement.

[0296] Example of a prompt

[0297] "Please create a positive introductory statement for the new product. Please follow the brand guidelines."

[0298] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0299] Step 1:

[0300] The server collects data from the API of the information exchange infrastructure. As input, it sends user-generated information (e.g., number of comments, shares, likes) that meets specific conditions as an API request. As output, it obtains these data in JSON format and saves it in the database. Specifically, the server is set to periodically execute a Python script to obtain the latest data from the API.

[0301] Step 2:

[0302] The server preprocesses the collected information through a text cleaning process. As input, it receives the raw information stored in the database. It removes unnecessary symbols and HTML tags from this information and converts the text data into a clean format. As output, it obtains text data in a format suitable for analysis. Specifically, it performs string operations using regular expressions.

[0303] Step 3:

[0304] The server performs sentiment analysis on the clean text data using natural language processing algorithms. As input, it uses the text data obtained in the previous step. As output, it generates a sentiment score for each text and stores it in the database. Specifically, it performs sentiment scoring using the NLTK library and, if it is determined to be negative, further analysis is carried out.

[0305] Step 4:

[0306] The server analyzes past post data using machine learning algorithms to predict the optimal posting time. As input, it incorporates past posting history and engagement data. As output, it generates a predicted value for the optimal posting time. Specifically, it trains the random forest algorithm of Scikit-learn and provides the prediction result.

[0307] Step 5:

[0308] The server automatically generates content using a generative AI model. It takes a prompt (e.g., "Create a positive description of the new product") as input. The generated content is retrieved as output in text format. Specifically, this involves sending a prompt to the generative AI model via a machine learning API and retrieving the returned generated text.

[0309] Step 6:

[0310] The server analyzes visual information to perform image recognition and optimization. It receives image and video data obtained from social media as input. It generates optimized visual information as output. Specifically, it uses TensorFlow and OpenCV to perform image compression and file extension conversion.

[0311] Step 7:

[0312] The terminal notifies the user of analysis results, generated content, and warnings sent from the server. It receives various data from the server via communication protocols as input. It displays information on the user interface as output. Specifically, it provides a real-time updated dashboard and includes notification functionality.

[0313] Step 8:

[0314] Users develop strategies based on information provided through the device interface. Inputs include optimization time, generated content, and warning messages. Outputs include planning product campaigns and creating posting schedules. Specifically, users evaluate received suggestions and edit content and prepare posts as needed.

[0315] (Application Example 1)

[0316] 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 glasses 214 will be referred to as the "terminal."

[0317] In today's social media environment, companies need to communicate with consumers efficiently and conduct effective advertising. However, it is not easy to grasp consumer sentiment and market trends in real time and respond quickly based on that information. Furthermore, while timely content posting and optimization of visual data are also required, there is a lack of systems to efficiently manage these aspects. In particular, there are challenges in optimizing advertising campaigns that cannot be adequately addressed with traditional methods.

[0318] 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.

[0319] In this invention, the server includes means for collecting user-generated data, means for performing sentiment analysis and detecting negative emotions, means for predicting the optimal posting time, and means for optimizing promotional activities. This enables companies to grasp market trends in real time and deploy strategic advertising based on consumer emotions.

[0320] "User-generated data" refers to information such as posts, comments, and ratings created by users, which are stored and shared on the platform.

[0321] "Sentiment analysis" is a process that uses natural language processing technology to determine a user's emotional state (negative, positive, neutral, etc.) from text data.

[0322] A "warning" is a notification or message intended to inform a user of the possibility of unexpected problems or negative consequences.

[0323] "Performance data" refers to information that shows the history of reactions and engagement to past posts and information content, and is used to optimize the system.

[0324] "Posting time" refers to the optimal time to publish user-generated data and content on the platform, and is important for gaining a lot of engagement.

[0325] "Information content" refers to all content provided to users, including media such as text, images, and videos.

[0326] "Market trends" are indicators that show changes in consumer preferences and behavioral patterns, as well as trends, in a particular market, and they influence decision-making in economic activities.

[0327] "Promotional activities" refer to public relations and marketing activities aimed at increasing consumer awareness and stimulating demand for products and services.

[0328] The system for implementing this invention primarily involves the cooperation of a server, a terminal, and a user. The server first collects user-generated data in real time using the API of a social media platform. This data includes user posts, comments, ratings, etc. The collected data is stored in a database, and sentiment analysis is performed using natural language processing algorithms. In this process, the server classifies whether the user's sentiment is negative, positive, or neutral, and issues warnings as necessary.

[0329] The server further uses machine learning algorithms based on collected historical performance data to predict the optimal posting time. This prediction makes it possible to maximize engagement with the information content. It also has a function to analyze market trends in real time to optimize promotional activities.

[0330] The terminal provides a user interface, displaying analysis results sent from the server, recommended posting times, and generated information. Through this terminal, users can make strategic decisions based on the presented information. For example, when promoting a new product, it's possible to run a campaign at the optimal time predicted by the server.

[0331] As a concrete example, a food brand is planning a campaign for a new drink. Using this application, the brand manager can determine the right timing and directly reach consumers with the most suitable content.

[0332] When using a generative AI model, the following prompt statements are possible:

[0333] "For a new drink campaign from a certain food brand, please suggest the optimal timing for posting information on social media. Please provide predictions based on past engagement data."

[0334] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0335] Step 1:

[0336] The server uses social media platform APIs to collect user-generated data. This data includes posts, comments, ratings, etc. The collected data is stored in a database and used for subsequent processing. The input is raw data obtained through the API, and the output is data stored in a formatted manner in the database.

[0337] Step 2:

[0338] The server applies natural language processing to stored user-generated data to perform sentiment analysis. This process analyzes the text of the data to classify whether it carries positive, negative, or neutral sentiment. The input is text data from the database, and the output is the sentiment classification result for each text. Specifically, it uses a text analysis library to perform tokenization and grammatical analysis.

[0339] Step 3:

[0340] Based on the sentiment analysis results, the server sends a warning to the device if there is a high concentration of negative emotions. This warning allows the user to take immediate action. The input is the sentiment analysis classification result, and the output is the warning message. The user can view this message on their device. Specifically, a push notification is sent using the notification function.

[0341] Step 4:

[0342] The server collects historical performance data and uses a machine learning algorithm to predict the optimal posting time. This prediction is used to maximize engagement for future posts. The input is historical engagement data, and the output is the predicted optimal posting time. Specifically, it performs machine learning model training and prediction processing.

[0343] Step 5:

[0344] The terminal displays analysis results sent from the server, recommended posting times, and generated information content in a user interface. This allows users to make timely strategic decisions. The input is analysis results and predicted data from the server, and the output is the information displayed on the terminal. Specifically, it performs graphical data display using a UI framework.

[0345] Step 6:

[0346] Users utilize the information provided on their devices to implement campaign and posting plans. Through the application, users can select and execute specific, data-driven actions. Input is the displayed information, and output is the actual actions performed by the user. Specifically, users configure settings using buttons and forms provided within the application.

[0347] 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.

[0348] The system of this invention streamlines social media operations through the coordination of servers, terminals, and users, and enables advanced interaction using an emotion engine.

[0349] Server operation

[0350] The server collects user-generated data from social media platforms. Examples include user posts, comments, and metadata. This data is stored in a database and passed to a sentiment analysis module. The server uses a sentiment engine to perform more detailed sentiment analysis, recognizing user emotions in real time. This information is used to determine whether posts and comments are positive, negative, or neutral. If a large number of negative emotions are detected, an alert is immediately generated to notify the user.

[0351] Furthermore, the server analyzes past performance data based on sentiment data obtained from the sentiment engine to predict the optimal posting time. It also utilizes this sentiment data to automatically generate more personalized content. For example, if it detects a pattern indicating user satisfaction, it generates content with a tone that matches that emotion.

[0352] Terminal operation

[0353] The device intuitively displays sentiment analysis results from the server, recommended posting times, and generated content to the user. Through this interface, the user can receive alerts and preview and edit the provided content. Visual data uploads and optimization results are also viewed on this device.

[0354] User actions

[0355] Users can build effective social media strategies based on information provided from their devices. For example, if the sentiment engine detects trends within the user's target audience, it can determine content and posting times accordingly. Furthermore, users can utilize chatbot functionality to provide personalized responses to their target audience, thereby improving their reputation.

[0356] Based on this model, systems incorporating an emotion engine support more effective social media management that takes user emotions into account, thereby strengthening engagement with target audiences.

[0357] The following describes the processing flow.

[0358] Step 1:

[0359] The server collects user-generated data through social media platform APIs. This includes data on posts, comments, and related reactions. This data is stored in a database to prepare it for subsequent processing.

[0360] Step 2:

[0361] The server uses the collected data to run an emotion engine. This engine utilizes natural language processing technology to classify emotions such as positive, negative, and neutral from the data. It also recognizes the emotions of individual users in real time and understands their trends.

[0362] Step 3:

[0363] The server activates an alert system based on emotional data. When a certain level of negative emotion is detected, it immediately generates an alert and notifies the user.

[0364] Step 4:

[0365] The server analyzes past performance data and combines it with sentiment information from the sentiment engine to predict the optimal posting time. This prediction indicates the time of day when user engagement is maximized.

[0366] Step 5:

[0367] The server automatically generates content that reflects emotional data. For example, if a lot of joy is detected, it will generate content with a bright and positive tone that is appropriate for this. This content is optimized in accordance with brand guidelines.

[0368] Step 6:

[0369] The device provides users with an interface that displays generated content, optimal posting times, and alerts. Users can view this information and adjust their posting content and strategy.

[0370] Step 7:

[0371] Users develop effective social media strategies based on analysis results from the emotion engine. For example, if a target audience shows a positive response to a particular campaign, additional content tailored to that response will be provided.

[0372] Step 8:

[0373] Users can leverage chatbot functionality to receive personalized, real-time responses that resonate with their emotions. This feature allows users to deepen their relationships with their target audience and increase engagement.

[0374] (Example 2)

[0375] 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".

[0376] Effective social media management presents challenges in processing large volumes of user-generated data and analyzing the resulting sentiments in real time. Furthermore, manually posting at the appropriate time and creating personalized content is time-consuming and labor-intensive, and responding quickly to negative sentiments is difficult. A system is needed to address these issues.

[0377] 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.

[0378] In this invention, the server includes means for acquiring user-generated data, means for performing sentiment analysis based on the user-generated data and identifying negative emotions, and means for acquiring sentiment labels for text data using a natural language processing model. This enables automated sentiment analysis and real-time detection of negative emotions.

[0379] "User-generated data" refers to information such as comments, images, and videos posted by users on social media platforms.

[0380] "Sentiment analysis" refers to the process of classifying emotions in text using natural language processing techniques and assigning emotion labels such as positive, negative, and neutral.

[0381] "Negative emotions" refers to information indicating negative feelings contained in user-generated data.

[0382] A "natural language processing model" refers to a program that uses machine learning algorithms to analyze, classify, and generate natural language text.

[0383] "Sentimental labels for text data" refer to tags that indicate emotions such as positive, negative, and neutral, which are assigned to text through sentiment analysis.

[0384] A "time series analysis algorithm" refers to a computational method used to model changes in data over time and predict future data.

[0385] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to automatically generate new text and content.

[0386] One embodiment of this invention is one that enables effective social media operation by coordinating a server, a terminal, and a user.

[0387] The server is the main component that manages the overall processing. The server retrieves data in real time from social media platforms using APIs. The collected data is organized and stored in a database. Based on the obtained user-generated data, sentiment analysis is performed using the natural language processing library NLTK and the deep learning model BERT. This analysis identifies whether the sentiment of each post is positive, negative, or neutral, and if negative sentiment is detected, an alert is immediately generated.

[0388] Furthermore, the server uses time-series analysis algorithms based on historical data to predict the optimal posting time. In addition, it leverages generative AI models to automatically generate content tailored to the user's target audience. For example, it can generate posts with a similar tone based on elements that have previously pleased users. In this way, the server consistently delivers optimized content.

[0389] The device intuitively displays analysis results and content suggestions sent from the server to the user. Based on the results and suggestions, the user can quickly adjust their posts. The device also allows for the uploading of visual data and confirmation of optimization results.

[0390] Users can build more effective social media strategies based on the information their devices provide. For example, they could launch new campaigns based on target audience trends revealed by sentiment analysis. Furthermore, they can improve engagement by fine-tuning generated content and posting it at the most opportune times.

[0391] An example of a prompt might be, "Generate text for the following post that will evoke positive emotions in the target audience." This allows the generation AI model to efficiently generate the specific content the user is looking for.

[0392] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0393] Step 1:

[0394] The server retrieves user-generated data using the APIs of social media platforms. This data includes posts, comments, and meta information. It accepts specific hashtags and account information as input and stores the retrieved data in a database as output. This stored data is then used for subsequent processing.

[0395] Step 2:

[0396] The server sends the stored user-generated data to the sentiment analysis module. It receives each text data item retrieved from the database as input, performs data calculations using a natural language processing library (e.g., NLTK or BERT), and labels the sentiment of each post. The output of this process is a sentiment label categorized as positive, negative, or neutral.

[0397] Step 3:

[0398] The server detects negative emotions based on the results of sentiment analysis. It receives emotion labels as input and generates an alert if negative emotions are predominant. The generated alert is immediately notified to the user, allowing them to recognize and address the problem early.

[0399] Step 4:

[0400] The server analyzes historical performance data to predict the optimal posting time. It receives historical interaction data and posting time history as input, and uses a time-series analysis algorithm to calculate the next recommended posting time as output. This information is used to optimize user operations.

[0401] Step 5:

[0402] The server generates content using an AI model based on sentiment analysis results. It receives user target audience profile information and sentiment trends as input, and uses prompts to instruct the AI ​​to generate content. The output is text and images optimized for the target audience, in a format usable by the user.

[0403] Step 6:

[0404] The terminal presents the user with analysis results and generated content sent from the server. It receives data from the server as input, visually organizes the information, and displays it as output. Based on this information, the user can adjust their posting content.

[0405] Step 7:

[0406] Users utilize data provided by their devices to develop effective posting strategies for their next posts. They receive device analytics results and recommendations as input, use them to plan their posts, and post content during the times when they are expected to perform best. This is expected to maximize user engagement on social media.

[0407] (Application Example 2)

[0408] 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 as the "terminal".

[0409] When running advertising campaigns, it is difficult to respond immediately to the diverse emotions of users and maximize effectiveness in real time. Current methods are inefficient or sometimes delayed in quickly analyzing user feedback and optimizing ad content. This results in the challenge of not maximizing the effectiveness of advertising.

[0410] 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.

[0411] In this invention, the server includes a device for storing biometric information, a device for performing emotional evaluation based on the biometric information and detecting negative emotions, and a device for notifying the user based on the results of the emotional evaluation. This enables real-time evaluation of users' emotions in advertising campaigns, immediate detection of negative emotions, and rapid optimization of advertising content.

[0412] "Biometric information" refers to data that shows the emotional state and physiological responses of individual users.

[0413] "Emotional assessment" is a process that analyzes a user's emotions based on collected biometric information and determines whether they tend to be positive or negative.

[0414] "Negative emotions" refer to emotional states such as sadness and anger that lead to discomfort for the user.

[0415] "Notification" refers to the act of communicating specific information or warnings to a user, or the means of doing so.

[0416] "Performance data" refers to recorded information about past actions and performance, which is useful for developing efficient strategies.

[0417] "Communication time" refers to the time period during which specific information is most effectively transmitted.

[0418] "Information" refers to digital content generated based on the user's emotional state and behavior.

[0419] An "advertising campaign" refers to a series of activities carried out to increase awareness of a particular product or service and to stimulate demand.

[0420] "Measuring effectiveness" is the process of using quantitative and qualitative metrics to evaluate the success of an advertising campaign.

[0421] "Emotional data" refers to a dataset containing comprehensive information about users' emotional states.

[0422] For this invention to be implemented, coordination between the server, terminal, and user is crucial. The server first collects biometric information and performs an emotional assessment based on this information. Specifically, it stores the collected biometric information in a database and analyzes the user's emotions through an emotion analysis module. This emotion analysis uses an emotion engine to recognize in real time whether the user's emotions are positive or negative. If negative emotions are detected, a notification is immediately generated and transmitted to the user.

[0423] Furthermore, the server measures the effectiveness of advertising campaigns and automatically optimizes ad content using emotional data. This includes a process of calculating appropriate communication time based on past performance data and generating information tailored to the user's emotional state.

[0424] The device can intuitively display sentiment evaluation results and optimized advertising information provided by the server to the user. Through this interface, the user can receive notifications, review the provided advertisements, and send feedback as needed. This feedback is then sent back to the server for further analysis by the sentiment engine.

[0425] For example, when an advertiser conducts an advertising campaign using smartphones, they can analyze users' real-time emotional responses and quickly adjust the ad content. This process makes it possible to maximize the effectiveness of the advertising campaign and improve user engagement.

[0426] An example of a prompt would be, "How can we understand audience emotional responses to our advertising campaign in real time and make immediate adjustments?" By leveraging generative AI models, advertisers can use these emotional data-driven prompts to optimize their strategies.

[0427] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0428] Step 1:

[0429] The server acquires biometric information, including data collection from the user's smartphone or wearable device. Input data includes heart rate and facial expression data, which are temporarily stored on the server. This data is then passed to an emotion analysis module as output. The data collection and transfer are performed securely using a cloud storage service.

[0430] Step 2:

[0431] The server uses an emotion analysis module to analyze acquired biometric information. The input is the user's biometric information, and the output is an evaluation of their emotions. Specifically, the system performs pattern recognition and emotion classification using a generative AI model. This data processing allows the user's emotional state to be determined in real time as positive, negative, etc.

[0432] Step 3:

[0433] The server analyzes the sentiment evaluation results and immediately generates a notification if negative emotions are detected. This notification generation involves specific actions, such as taking the sentiment evaluation results as input and outputting a warning message to the user. The notification format is implemented as a text message or push notification.

[0434] Step 4:

[0435] The server analyzes advertising campaign performance data and calculates the appropriate communication time. The input is historical performance data, and the output is the optimal posting timing. This involves statistical methods using data analysis algorithms.

[0436] Step 5:

[0437] The server automatically generates advertising information using a generative AI model. The input consists of emotional data and calculated communication time, while the output is the generated advertising content. This process automatically constructs personalized advertising content.

[0438] Step 6:

[0439] The terminal displays sentiment ratings and advertising information sent from the server to the user. Input information is notification data from the server, and output is a display on the user interface. Specifically, it conveys information intuitively through a GUI (Graphical User Interface).

[0440] Step 7:

[0441] Users review the information provided via their devices and send feedback as needed. The input is the advertising information displayed on the device, and the output is feedback data sent to the server. This process allows the server to receive new data, enabling further optimization of the sentiment engine.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] [Third Embodiment]

[0446] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0447] 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.

[0448] 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).

[0449] 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.

[0450] 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.

[0451] 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).

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] 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".

[0458] The system of this invention streamlines the operation of social media through the cooperation of servers, terminals, and users.

[0459] Server operation

[0460] The server collects user-generated data in real time from social media platform APIs. This includes metadata such as comments, shares, and likes on a brand's posts. The collected data is stored in a database and passed to a sentiment analysis module. The server uses natural language processing algorithms to analyze the data and determine negative, positive, and neutral sentiments. Based on this analysis, if there are many negative reactions, an alert is immediately generated and the user is notified.

[0461] Furthermore, the server aggregates past posting data and uses machine learning algorithms to predict the optimal posting time. This maximizes engagement with posted content. With the automated content generation feature, the server automatically creates posts and captions in a tone based on brand guidelines. This process enables consistent information dissemination while minimizing intervention from content managers.

[0462] Furthermore, it recognizes and optimizes visual data such as images and videos. This process ensures that visual content is delivered in a more engaging format.

[0463] Terminal operation

[0464] The device provides an interface for the user, displaying real-time analysis results and content suggestions. Users can preview recommended posting times and generated content, and edit them as needed. Alerts from the server are notified to the user through the device, enabling quick responses.

[0465] User actions

[0466] Users can develop effective social media strategies based on the information provided on their devices. For example, when planning a new product campaign, users can use the optimal posting time and generated content suggested by the server to prepare posts according to the schedule. Additionally, a chatbot function provides 24 / 7 customer support and can automatically handle common inquiries.

[0467] This type of system allows users to manage social media platforms in a timely and effective manner and monitor their brand's reputation.

[0468] The following describes the processing flow.

[0469] Step 1:

[0470] The server collects user-generated data through social media platform APIs. This includes information such as posts, comments, and reactions. The collected data is stored in a database.

[0471] Step 2:

[0472] The server uses natural language processing to perform sentiment analysis based on the collected data. This allows for an understanding of the sentiment of posts and comments, classifying them as positive, negative, or neutral. If a large number of negative sentiments are detected, the server immediately generates an alert and notifies the administrator.

[0473] Step 3:

[0474] The server analyzes past posting data to identify the best times for engagement. Using machine learning algorithms, it learns successful posting patterns from the past and predicts the optimal posting times for the future.

[0475] Step 4:

[0476] The server uses an automated content generation module to generate posts and captions that comply with brand guidelines. The generated content is optimized based on past engagement data.

[0477] Step 5:

[0478] The device presents users with recommended posting times from the server, generated content, and alerts through an intuitive dashboard. Based on this information, users can review and edit their posts and schedules.

[0479] Step 6:

[0480] Users upload images and videos through their devices. The devices send these to a server, which analyzes the visual data and generates optimization suggestions. The devices then present these suggestions to the user, who can make adjustments as needed.

[0481] Step 7:

[0482] The server provides a 24 / 7 chatbot function, automatically responding to general inquiries. In special cases or when escalation is necessary, it notifies the appropriate person to take action.

[0483] Step 8:

[0484] Users leverage information and features provided by the server to implement effective social media strategies. This allows users to improve their brand reputation and build deeper engagement with their target audience.

[0485] (Example 1)

[0486] 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."

[0487] With the rapid increase in user-generated information on information exchange platforms, it is becoming difficult for information providers to quickly obtain useful insights. Furthermore, if negative reactions are not detected early and appropriate responses cannot be taken, the reputation of the information provider or their brand may be damaged. In addition, manually selecting the optimal information distribution time and automatically generating effective content is difficult, and the development of efficient strategies is required.

[0488] 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.

[0489] In this invention, the server includes means for collecting information from an information exchange infrastructure, means for performing text analysis based on the information and detecting negative emotions, and means for sending a warning to the information provider based on the results of the text analysis. This enables the information provider to obtain emotional insights in real time, allowing for a rapid response and efficient information management.

[0490] An "information exchange platform" is a platform that serves as the foundation for exchanging information over a digital network.

[0491] "Information" refers to content and data that users generate or share on social media and online platforms.

[0492] "Text analysis" is the process of analyzing emotions and intentions from text data using natural language processing technology.

[0493] "Negative emotions" are negative reactions from users that indicate dissatisfaction or criticism, as detected through sentiment analysis.

[0494] A "warning" is a notification issued by the system based on the results of sentiment analysis to prompt the information provider to take immediate action.

[0495] An "information provider" is an entity that generates, manages, or disseminates content on an online platform.

[0496] An embodiment of this invention is a system for information providers to streamline the operation of a social media platform, in which the server, terminal, and user work in high-level coordination.

[0497] Server operation

[0498] The server collects user-generated information from the information exchange platform using APIs. In this process, the server uses programming languages ​​such as Python and database software (e.g., MySQL) for information management. The collected information is stored in the database and processed as a preliminary step for analysis using natural language processing techniques.

[0499] The server uses natural language processing libraries (e.g., NLTK, TextBlob) to determine the sentiment of the information. If negative sentiment is detected, the server immediately sends a warning to the information provider. This process allows the information provider to quickly understand the situation and take appropriate action.

[0500] Furthermore, the server collects past posting data and uses machine learning algorithms (e.g., Scikit-learn) to predict the optimal delivery time. In addition, it utilizes generative AI models (e.g., GPT-3) to provide a function that automatically generates content that matches the tone and style.

[0501] Regarding visual information, the server can use image processing frameworks (e.g., OpenCV, TensorFlow) to analyze and optimize collected images and videos. This makes the delivery of visual content more effective.

[0502] Terminal operation

[0503] The terminal provides users with an intuitive interface, displaying real-time analysis results, predictive information, and automatically generated content from the server. Through this interface, users can preview the generated content, edit it as needed, and respond quickly to warnings from the server.

[0504] User actions

[0505] Users can build strategies based on the information provided on their devices. For example, when planning a campaign for a new product, users can efficiently disseminate information by utilizing the optimal distribution time and automatically generated content. Furthermore, customer support can be strengthened by using an automated dialogue system that provides interactive responses to handle general inquiries.

[0506] Specific example

[0507] For example, suppose a user from a food company is promoting a new snack product. The server provides information such as, "According to market research, Friday at 6 PM is the best time to post," and also uses a generative AI model to automatically generate catchphrases like, "Check out this week's new snack!" Based on this information, the user can deliver content according to the set schedule and achieve effective engagement.

[0508] Example of a prompt

[0509] "Please create a positive introductory statement for the new product. Please follow the brand guidelines."

[0510] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0511] Step 1:

[0512] The server collects data from the information exchange platform's API. As input, it sends user-generated information (e.g., number of comments, shares, likes) that meets specific criteria as API requests. As output, it retrieves this data in JSON format and saves it to the database. Specifically, the server is configured to periodically execute a Python script to retrieve the latest data from the API.

[0513] Step 2:

[0514] The server preprocesses the collected information through a text cleaning process. It receives raw information stored in a database as input. Unnecessary symbols and HTML tags are removed from this information, converting the text data into a clean format. The output is text data in a format suitable for analysis. Specifically, string manipulation using regular expressions is performed.

[0515] Step 3:

[0516] The server performs sentiment analysis on clean text data using natural language processing algorithms. It uses the text data obtained in the previous step as input. As output, it generates a sentiment score for each text and stores it in a database. Specifically, it performs sentiment scoring using the NLTK library, and if a text is judged to be negative, it proceeds with further analysis.

[0517] Step 4:

[0518] The server analyzes past posting data using a machine learning algorithm to predict the optimal posting time. It takes past posting history and engagement data as input. As output, it generates a predicted optimal posting time. Specifically, it trains the Scikit-learn random forest algorithm and provides the prediction results.

[0519] Step 5:

[0520] The server automatically generates content using a generative AI model. It takes a prompt (e.g., "Create a positive description of the new product") as input. The generated content is retrieved as output in text format. Specifically, this involves sending a prompt to the generative AI model via a machine learning API and retrieving the returned generated text.

[0521] Step 6:

[0522] The server analyzes visual information to perform image recognition and optimization. It receives image and video data obtained from social media as input. It generates optimized visual information as output. Specifically, it uses TensorFlow and OpenCV to perform image compression and file extension conversion.

[0523] Step 7:

[0524] The terminal notifies the user of analysis results, generated content, and warnings sent from the server. It receives various data from the server via communication protocols as input. It displays information on the user interface as output. Specifically, it provides a real-time updated dashboard and includes notification functionality.

[0525] Step 8:

[0526] Users develop strategies based on information provided through the device interface. Inputs include optimization time, generated content, and warning messages. Outputs include planning product campaigns and creating posting schedules. Specifically, users evaluate received suggestions and edit content and prepare posts as needed.

[0527] (Application Example 1)

[0528] 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."

[0529] In today's social media environment, companies need to communicate with consumers efficiently and conduct effective advertising. However, it is not easy to grasp consumer sentiment and market trends in real time and respond quickly based on that information. Furthermore, while timely content posting and optimization of visual data are also required, there is a lack of systems to efficiently manage these aspects. In particular, there are challenges in optimizing advertising campaigns that cannot be adequately addressed with traditional methods.

[0530] 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.

[0531] In this invention, the server includes means for collecting user-generated data, means for performing sentiment analysis and detecting negative emotions, means for predicting the optimal posting time, and means for optimizing promotional activities. This enables companies to grasp market trends in real time and deploy strategic advertising based on consumer emotions.

[0532] "User-generated data" refers to information such as posts, comments, and ratings created by users, which are stored and shared on the platform.

[0533] "Sentiment analysis" is a process that uses natural language processing technology to determine a user's emotional state (negative, positive, neutral, etc.) from text data.

[0534] A "warning" is a notification or message intended to inform a user of the possibility of unexpected problems or negative consequences.

[0535] "Performance data" refers to information that shows the history of reactions and engagement to past posts and information content, and is used to optimize the system.

[0536] "Posting time" refers to the optimal time to publish user-generated data and content on the platform, and is important for gaining a lot of engagement.

[0537] "Information content" refers to all content provided to users, including media such as text, images, and videos.

[0538] "Market trends" are indicators that show changes in consumer preferences and behavioral patterns, as well as trends, in a particular market, and they influence decision-making in economic activities.

[0539] "Promotional activities" refer to public relations and marketing activities aimed at increasing consumer awareness and stimulating demand for products and services.

[0540] The system for implementing this invention primarily involves the cooperation of a server, a terminal, and a user. The server first collects user-generated data in real time using the API of a social media platform. This data includes user posts, comments, ratings, etc. The collected data is stored in a database, and sentiment analysis is performed using natural language processing algorithms. In this process, the server classifies whether the user's sentiment is negative, positive, or neutral, and issues warnings as necessary.

[0541] The server further uses machine learning algorithms based on collected historical performance data to predict the optimal posting time. This prediction makes it possible to maximize engagement with the information content. It also has a function to analyze market trends in real time to optimize promotional activities.

[0542] The terminal provides a user interface, displaying analysis results sent from the server, recommended posting times, and generated information. Through this terminal, users can make strategic decisions based on the presented information. For example, when promoting a new product, it's possible to run a campaign at the optimal time predicted by the server.

[0543] As a concrete example, a food brand is planning a campaign for a new drink. Using this application, the brand manager can determine the right timing and directly reach consumers with the most suitable content.

[0544] When using a generative AI model, the following prompt statements are possible:

[0545] "For a new drink campaign from a certain food brand, please suggest the optimal timing for posting information on social media. Please provide predictions based on past engagement data."

[0546] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0547] Step 1:

[0548] The server uses social media platform APIs to collect user-generated data. This data includes posts, comments, ratings, etc. The collected data is stored in a database and used for subsequent processing. The input is raw data obtained through the API, and the output is data stored in a formatted manner in the database.

[0549] Step 2:

[0550] The server applies natural language processing to stored user-generated data to perform sentiment analysis. This process analyzes the text of the data to classify whether it carries positive, negative, or neutral sentiment. The input is text data from the database, and the output is the sentiment classification result for each text. Specifically, it uses a text analysis library to perform tokenization and grammatical analysis.

[0551] Step 3:

[0552] Based on the sentiment analysis results, the server sends a warning to the device if there is a high concentration of negative emotions. This warning allows the user to take immediate action. The input is the sentiment analysis classification result, and the output is the warning message. The user can view this message on their device. Specifically, a push notification is sent using the notification function.

[0553] Step 4:

[0554] The server collects historical performance data and uses a machine learning algorithm to predict the optimal posting time. This prediction is used to maximize engagement for future posts. The input is historical engagement data, and the output is the predicted optimal posting time. Specifically, it performs machine learning model training and prediction processing.

[0555] Step 5:

[0556] The terminal displays analysis results sent from the server, recommended posting times, and generated information content in a user interface. This allows users to make timely strategic decisions. The input is analysis results and predicted data from the server, and the output is the information displayed on the terminal. Specifically, it performs graphical data display using a UI framework.

[0557] Step 6:

[0558] Users utilize the information provided on their devices to implement campaign and posting plans. Through the application, users can select and execute specific, data-driven actions. Input is the displayed information, and output is the actual actions performed by the user. Specifically, users configure settings using buttons and forms provided within the application.

[0559] 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.

[0560] The system of this invention streamlines social media operations through the coordination of servers, terminals, and users, and enables advanced interaction using an emotion engine.

[0561] Server operation

[0562] The server collects user-generated data from social media platforms. Examples include user posts, comments, and metadata. This data is stored in a database and passed to a sentiment analysis module. The server uses a sentiment engine to perform more detailed sentiment analysis, recognizing user emotions in real time. This information is used to determine whether posts and comments are positive, negative, or neutral. If a large number of negative emotions are detected, an alert is immediately generated to notify the user.

[0563] Furthermore, the server analyzes past performance data based on sentiment data obtained from the sentiment engine to predict the optimal posting time. It also utilizes this sentiment data to automatically generate more personalized content. For example, if it detects a pattern indicating user satisfaction, it generates content with a tone that matches that emotion.

[0564] Terminal operation

[0565] The device intuitively displays sentiment analysis results from the server, recommended posting times, and generated content to the user. Through this interface, the user can receive alerts and preview and edit the provided content. Visual data uploads and optimization results are also viewed on this device.

[0566] User actions

[0567] Users can build effective social media strategies based on information provided from their devices. For example, if the sentiment engine detects trends within the user's target audience, it can determine content and posting times accordingly. Furthermore, users can utilize chatbot functionality to provide personalized responses to their target audience, thereby improving their reputation.

[0568] Based on this model, systems incorporating an emotion engine support more effective social media management that takes user emotions into account, thereby strengthening engagement with target audiences.

[0569] The following describes the processing flow.

[0570] Step 1:

[0571] The server collects user-generated data through social media platform APIs. This includes data on posts, comments, and related reactions. This data is stored in a database to prepare it for subsequent processing.

[0572] Step 2:

[0573] The server uses the collected data to run an emotion engine. This engine utilizes natural language processing technology to classify emotions such as positive, negative, and neutral from the data. It also recognizes the emotions of individual users in real time and understands their trends.

[0574] Step 3:

[0575] The server activates an alert system based on emotional data. When a certain level of negative emotion is detected, it immediately generates an alert and notifies the user.

[0576] Step 4:

[0577] The server analyzes past performance data and combines it with sentiment information from the sentiment engine to predict the optimal posting time. This prediction indicates the time of day when user engagement is maximized.

[0578] Step 5:

[0579] The server automatically generates content that reflects emotional data. For example, if a lot of joy is detected, it will generate content with a bright and positive tone that is appropriate for this. This content is optimized in accordance with brand guidelines.

[0580] Step 6:

[0581] The device provides users with an interface that displays generated content, optimal posting times, and alerts. Users can view this information and adjust their posting content and strategy.

[0582] Step 7:

[0583] Users develop effective social media strategies based on analysis results from the emotion engine. For example, if a target audience shows a positive response to a particular campaign, additional content tailored to that response will be provided.

[0584] Step 8:

[0585] Users can leverage chatbot functionality to receive personalized, real-time responses that resonate with their emotions. This feature allows users to deepen their relationships with their target audience and increase engagement.

[0586] (Example 2)

[0587] 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."

[0588] Effective social media management presents challenges in processing large volumes of user-generated data and analyzing the resulting sentiments in real time. Furthermore, manually posting at the appropriate time and creating personalized content is time-consuming and labor-intensive, and responding quickly to negative sentiments is difficult. A system is needed to address these issues.

[0589] 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.

[0590] In this invention, the server includes means for acquiring user-generated data, means for performing sentiment analysis based on the user-generated data and identifying negative emotions, and means for acquiring sentiment labels for text data using a natural language processing model. This enables automated sentiment analysis and real-time detection of negative emotions.

[0591] "User-generated data" refers to information such as comments, images, and videos posted by users on social media platforms.

[0592] "Sentiment analysis" refers to the process of classifying emotions in text using natural language processing techniques and assigning emotion labels such as positive, negative, and neutral.

[0593] "Negative emotions" refers to information indicating negative feelings contained in user-generated data.

[0594] A "natural language processing model" refers to a program that uses machine learning algorithms to analyze, classify, and generate natural language text.

[0595] "Sentimental labels for text data" refer to tags that indicate emotions such as positive, negative, and neutral, which are assigned to text through sentiment analysis.

[0596] A "time series analysis algorithm" refers to a computational method used to model changes in data over time and predict future data.

[0597] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to automatically generate new text and content.

[0598] One embodiment of this invention is one that enables effective social media operation by coordinating a server, a terminal, and a user.

[0599] The server is the main component that manages the overall processing. The server retrieves data in real time from social media platforms using APIs. The collected data is organized and stored in a database. Based on the obtained user-generated data, sentiment analysis is performed using the natural language processing library NLTK and the deep learning model BERT. This analysis identifies whether the sentiment of each post is positive, negative, or neutral, and if negative sentiment is detected, an alert is immediately generated.

[0600] Furthermore, the server uses time-series analysis algorithms based on historical data to predict the optimal posting time. In addition, it leverages generative AI models to automatically generate content tailored to the user's target audience. For example, it can generate posts with a similar tone based on elements that have previously pleased users. In this way, the server consistently delivers optimized content.

[0601] The device intuitively displays analysis results and content suggestions sent from the server to the user. Based on the results and suggestions, the user can quickly adjust their posts. The device also allows for the uploading of visual data and confirmation of optimization results.

[0602] Users can build more effective social media strategies based on the information their devices provide. For example, they could launch new campaigns based on target audience trends revealed by sentiment analysis. Furthermore, they can improve engagement by fine-tuning generated content and posting it at the most opportune times.

[0603] An example of a prompt might be, "Generate text for the following post that will evoke positive emotions in the target audience." This allows the generation AI model to efficiently generate the specific content the user is looking for.

[0604] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0605] Step 1:

[0606] The server retrieves user-generated data using the APIs of social media platforms. This data includes posts, comments, and meta information. It accepts specific hashtags and account information as input and stores the retrieved data in a database as output. This stored data is then used for subsequent processing.

[0607] Step 2:

[0608] The server sends the stored user-generated data to the sentiment analysis module. It receives each text data item retrieved from the database as input, performs data calculations using a natural language processing library (e.g., NLTK or BERT), and labels the sentiment of each post. The output of this process is a sentiment label categorized as positive, negative, or neutral.

[0609] Step 3:

[0610] The server detects negative emotions based on the results of sentiment analysis. It receives emotion labels as input and generates an alert if negative emotions are predominant. The generated alert is immediately notified to the user, allowing them to recognize and address the problem early.

[0611] Step 4:

[0612] The server analyzes historical performance data to predict the optimal posting time. It receives historical interaction data and posting time history as input, and uses a time-series analysis algorithm to calculate the next recommended posting time as output. This information is used to optimize user operations.

[0613] Step 5:

[0614] The server generates content using an AI model based on sentiment analysis results. It receives user target audience profile information and sentiment trends as input, and uses prompts to instruct the AI ​​to generate content. The output is text and images optimized for the target audience, in a format usable by the user.

[0615] Step 6:

[0616] The terminal presents the user with analysis results and generated content sent from the server. It receives data from the server as input, visually organizes the information, and displays it as output. Based on this information, the user can adjust their posting content.

[0617] Step 7:

[0618] Users utilize data provided by their devices to develop effective posting strategies for their next posts. They receive device analytics results and recommendations as input, use them to plan their posts, and post content during the times when they are expected to perform best. This is expected to maximize user engagement on social media.

[0619] (Application Example 2)

[0620] 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."

[0621] When running advertising campaigns, it is difficult to respond immediately to the diverse emotions of users and maximize effectiveness in real time. Current methods are inefficient or sometimes delayed in quickly analyzing user feedback and optimizing ad content. This results in the challenge of not maximizing the effectiveness of advertising.

[0622] 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.

[0623] In this invention, the server includes a device for storing biometric information, a device for performing emotional evaluation based on the biometric information and detecting negative emotions, and a device for notifying the user based on the results of the emotional evaluation. This enables real-time evaluation of users' emotions in advertising campaigns, immediate detection of negative emotions, and rapid optimization of advertising content.

[0624] "Biometric information" refers to data that shows the emotional state and physiological responses of individual users.

[0625] "Emotional assessment" is a process that analyzes a user's emotions based on collected biometric information and determines whether they tend to be positive or negative.

[0626] "Negative emotions" refer to emotional states such as sadness and anger that lead to discomfort for the user.

[0627] "Notification" refers to the act of communicating specific information or warnings to a user, or the means of doing so.

[0628] "Performance data" refers to recorded information about past actions and performance, which is useful for developing efficient strategies.

[0629] "Communication time" refers to the time period during which specific information is most effectively transmitted.

[0630] "Information" refers to digital content generated based on the user's emotional state and behavior.

[0631] An "advertising campaign" refers to a series of activities carried out to increase awareness of a particular product or service and to stimulate demand.

[0632] "Measuring effectiveness" is the process of using quantitative and qualitative metrics to evaluate the success of an advertising campaign.

[0633] "Emotional data" refers to a dataset containing comprehensive information about users' emotional states.

[0634] For this invention to be implemented, coordination between the server, terminal, and user is crucial. The server first collects biometric information and performs an emotional assessment based on this information. Specifically, it stores the collected biometric information in a database and analyzes the user's emotions through an emotion analysis module. This emotion analysis uses an emotion engine to recognize in real time whether the user's emotions are positive or negative. If negative emotions are detected, a notification is immediately generated and transmitted to the user.

[0635] Furthermore, the server measures the effectiveness of advertising campaigns and automatically optimizes ad content using emotional data. This includes a process of calculating appropriate communication time based on past performance data and generating information tailored to the user's emotional state.

[0636] The device can intuitively display sentiment evaluation results and optimized advertising information provided by the server to the user. Through this interface, the user can receive notifications, review the provided advertisements, and send feedback as needed. This feedback is then sent back to the server for further analysis by the sentiment engine.

[0637] For example, when an advertiser conducts an advertising campaign using smartphones, they can analyze users' real-time emotional responses and quickly adjust the ad content. This process makes it possible to maximize the effectiveness of the advertising campaign and improve user engagement.

[0638] An example of a prompt would be, "How can we understand audience emotional responses to our advertising campaign in real time and make immediate adjustments?" By leveraging generative AI models, advertisers can use these emotional data-driven prompts to optimize their strategies.

[0639] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0640] Step 1:

[0641] The server acquires biometric information, including data collection from the user's smartphone or wearable device. Input data includes heart rate and facial expression data, which are temporarily stored on the server. This data is then passed to an emotion analysis module as output. The data collection and transfer are performed securely using a cloud storage service.

[0642] Step 2:

[0643] The server uses an emotion analysis module to analyze acquired biometric information. The input is the user's biometric information, and the output is an evaluation of their emotions. Specifically, the system performs pattern recognition and emotion classification using a generative AI model. This data processing allows the user's emotional state to be determined in real time as positive, negative, etc.

[0644] Step 3:

[0645] The server analyzes the sentiment evaluation results and immediately generates a notification if negative emotions are detected. This notification generation involves specific actions, such as taking the sentiment evaluation results as input and outputting a warning message to the user. The notification format is implemented as a text message or push notification.

[0646] Step 4:

[0647] The server analyzes advertising campaign performance data and calculates the appropriate communication time. The input is historical performance data, and the output is the optimal posting timing. This involves statistical methods using data analysis algorithms.

[0648] Step 5:

[0649] The server automatically generates advertising information using a generative AI model. The input consists of emotional data and calculated communication time, while the output is the generated advertising content. This process automatically constructs personalized advertising content.

[0650] Step 6:

[0651] The terminal displays sentiment ratings and advertising information sent from the server to the user. Input information is notification data from the server, and output is a display on the user interface. Specifically, it conveys information intuitively through a GUI (Graphical User Interface).

[0652] Step 7:

[0653] Users review the information provided via their devices and send feedback as needed. The input is the advertising information displayed on the device, and the output is feedback data sent to the server. This process allows the server to receive new data, enabling further optimization of the sentiment engine.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] [Fourth Embodiment]

[0658] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0659] 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.

[0660] 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).

[0661] 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.

[0662] 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.

[0663] 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).

[0664] 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.

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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.

[0669] 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.

[0670] 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".

[0671] The system of this invention streamlines the operation of social media through the cooperation of servers, terminals, and users.

[0672] Server operation

[0673] The server collects user-generated data in real time from social media platform APIs. This includes metadata such as comments, shares, and likes on a brand's posts. The collected data is stored in a database and passed to a sentiment analysis module. The server uses natural language processing algorithms to analyze the data and determine negative, positive, and neutral sentiments. Based on this analysis, if there are many negative reactions, an alert is immediately generated and the user is notified.

[0674] Furthermore, the server aggregates past posting data and uses machine learning algorithms to predict the optimal posting time. This maximizes engagement with posted content. With the automated content generation feature, the server automatically creates posts and captions in a tone based on brand guidelines. This process enables consistent information dissemination while minimizing intervention from content managers.

[0675] Furthermore, it recognizes and optimizes visual data such as images and videos. This process ensures that visual content is delivered in a more engaging format.

[0676] Terminal operation

[0677] The device provides an interface for the user, displaying real-time analysis results and content suggestions. Users can preview recommended posting times and generated content, and edit them as needed. Alerts from the server are notified to the user through the device, enabling quick responses.

[0678] User actions

[0679] Users can develop effective social media strategies based on the information provided on their devices. For example, when planning a new product campaign, users can use the optimal posting time and generated content suggested by the server to prepare posts according to the schedule. Additionally, a chatbot function provides 24 / 7 customer support and can automatically handle common inquiries.

[0680] This type of system allows users to manage social media platforms in a timely and effective manner and monitor their brand's reputation.

[0681] The following describes the processing flow.

[0682] Step 1:

[0683] The server collects user-generated data through social media platform APIs. This includes information such as posts, comments, and reactions. The collected data is stored in a database.

[0684] Step 2:

[0685] The server uses natural language processing to perform sentiment analysis based on the collected data. This allows for an understanding of the sentiment of posts and comments, classifying them as positive, negative, or neutral. If a large number of negative sentiments are detected, the server immediately generates an alert and notifies the administrator.

[0686] Step 3:

[0687] The server analyzes past posting data to identify the best times for engagement. Using machine learning algorithms, it learns successful posting patterns from the past and predicts the optimal posting times for the future.

[0688] Step 4:

[0689] The server uses an automated content generation module to generate posts and captions that comply with brand guidelines. The generated content is optimized based on past engagement data.

[0690] Step 5:

[0691] The device presents users with recommended posting times from the server, generated content, and alerts through an intuitive dashboard. Based on this information, users can review and edit their posts and schedules.

[0692] Step 6:

[0693] Users upload images and videos through their devices. The devices send these to a server, which analyzes the visual data and generates optimization suggestions. The devices then present these suggestions to the user, who can make adjustments as needed.

[0694] Step 7:

[0695] The server provides a 24 / 7 chatbot function, automatically responding to general inquiries. In special cases or when escalation is necessary, it notifies the appropriate person to take action.

[0696] Step 8:

[0697] Users leverage information and features provided by the server to implement effective social media strategies. This allows users to improve their brand reputation and build deeper engagement with their target audience.

[0698] (Example 1)

[0699] 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".

[0700] With the rapid increase in user-generated information on information exchange platforms, it is becoming difficult for information providers to quickly obtain useful insights. Furthermore, if negative reactions are not detected early and appropriate responses cannot be taken, the reputation of the information provider or their brand may be damaged. In addition, manually selecting the optimal information distribution time and automatically generating effective content is difficult, and the development of efficient strategies is required.

[0701] 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.

[0702] In this invention, the server includes means for collecting information from an information exchange infrastructure, means for performing text analysis based on the information and detecting negative emotions, and means for sending a warning to the information provider based on the results of the text analysis. This enables the information provider to obtain emotional insights in real time, allowing for a rapid response and efficient information management.

[0703] An "information exchange platform" is a platform that serves as the foundation for exchanging information over a digital network.

[0704] "Information" refers to content and data that users generate or share on social media and online platforms.

[0705] "Text analysis" is the process of analyzing emotions and intentions from text data using natural language processing technology.

[0706] "Negative emotions" are negative reactions from users that indicate dissatisfaction or criticism, as detected through sentiment analysis.

[0707] A "warning" is a notification issued by the system based on the results of sentiment analysis to prompt the information provider to take immediate action.

[0708] An "information provider" is an entity that generates, manages, or disseminates content on an online platform.

[0709] An embodiment of this invention is a system for information providers to streamline the operation of a social media platform, in which the server, terminal, and user work in high-level coordination.

[0710] Server operation

[0711] The server collects user-generated information from the information exchange platform using APIs. In this process, the server uses programming languages ​​such as Python and database software (e.g., MySQL) for information management. The collected information is stored in the database and processed as a preliminary step for analysis using natural language processing techniques.

[0712] The server uses natural language processing libraries (e.g., NLTK, TextBlob) to determine the sentiment of the information. If negative sentiment is detected, the server immediately sends a warning to the information provider. This process allows the information provider to quickly understand the situation and take appropriate action.

[0713] Furthermore, the server collects past posting data and uses machine learning algorithms (e.g., Scikit-learn) to predict the optimal delivery time. In addition, it utilizes generative AI models (e.g., GPT-3) to provide a function that automatically generates content that matches the tone and style.

[0714] Regarding visual information, the server can use image processing frameworks (e.g., OpenCV, TensorFlow) to analyze and optimize collected images and videos. This makes the delivery of visual content more effective.

[0715] Terminal operation

[0716] The terminal provides users with an intuitive interface, displaying real-time analysis results, predictive information, and automatically generated content from the server. Through this interface, users can preview the generated content, edit it as needed, and respond quickly to warnings from the server.

[0717] User actions

[0718] Users can build strategies based on the information provided on their devices. For example, when planning a campaign for a new product, users can efficiently disseminate information by utilizing the optimal distribution time and automatically generated content. Furthermore, customer support can be strengthened by using an automated dialogue system that provides interactive responses to handle general inquiries.

[0719] Specific example

[0720] For example, suppose a user from a food company is promoting a new snack product. The server provides information such as, "According to market research, Friday at 6 PM is the best time to post," and also uses a generative AI model to automatically generate catchphrases like, "Check out this week's new snack!" Based on this information, the user can deliver content according to the set schedule and achieve effective engagement.

[0721] Example of a prompt

[0722] "Please create a positive introductory statement for the new product. Please follow the brand guidelines."

[0723] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0724] Step 1:

[0725] The server collects data from the information exchange platform's API. As input, it sends user-generated information (e.g., number of comments, shares, likes) that meets specific criteria as API requests. As output, it retrieves this data in JSON format and saves it to the database. Specifically, the server is configured to periodically execute a Python script to retrieve the latest data from the API.

[0726] Step 2:

[0727] The server preprocesses the collected information through a text cleaning process. It receives raw information stored in a database as input. Unnecessary symbols and HTML tags are removed from this information, converting the text data into a clean format. The output is text data in a format suitable for analysis. Specifically, string manipulation using regular expressions is performed.

[0728] Step 3:

[0729] The server performs sentiment analysis on clean text data using natural language processing algorithms. It uses the text data obtained in the previous step as input. As output, it generates a sentiment score for each text and stores it in a database. Specifically, it performs sentiment scoring using the NLTK library, and if a text is judged to be negative, it proceeds with further analysis.

[0730] Step 4:

[0731] The server analyzes past posting data using a machine learning algorithm to predict the optimal posting time. It takes past posting history and engagement data as input. As output, it generates a predicted optimal posting time. Specifically, it trains the Scikit-learn random forest algorithm and provides the prediction results.

[0732] Step 5:

[0733] The server automatically generates content using a generative AI model. It takes a prompt (e.g., "Create a positive description of the new product") as input. The generated content is retrieved as output in text format. Specifically, this involves sending a prompt to the generative AI model via a machine learning API and retrieving the returned generated text.

[0734] Step 6:

[0735] The server analyzes visual information to perform image recognition and optimization. It receives image and video data obtained from social media as input. It generates optimized visual information as output. Specifically, it uses TensorFlow and OpenCV to perform image compression and file extension conversion.

[0736] Step 7:

[0737] The terminal notifies the user of analysis results, generated content, and warnings sent from the server. It receives various data from the server via communication protocols as input. It displays information on the user interface as output. Specifically, it provides a real-time updated dashboard and includes notification functionality.

[0738] Step 8:

[0739] Users develop strategies based on information provided through the device interface. Inputs include optimization time, generated content, and warning messages. Outputs include planning product campaigns and creating posting schedules. Specifically, users evaluate received suggestions and edit content and prepare posts as needed.

[0740] (Application Example 1)

[0741] 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".

[0742] In today's social media environment, companies need to communicate with consumers efficiently and conduct effective advertising. However, it is not easy to grasp consumer sentiment and market trends in real time and respond quickly based on that information. Furthermore, while timely content posting and optimization of visual data are also required, there is a lack of systems to efficiently manage these aspects. In particular, there are challenges in optimizing advertising campaigns that cannot be adequately addressed with traditional methods.

[0743] 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.

[0744] In this invention, the server includes means for collecting user-generated data, means for performing sentiment analysis and detecting negative emotions, means for predicting the optimal posting time, and means for optimizing promotional activities. This enables companies to grasp market trends in real time and deploy strategic advertising based on consumer emotions.

[0745] "User-generated data" refers to information such as posts, comments, and ratings created by users, which are stored and shared on the platform.

[0746] "Sentiment analysis" is a process that uses natural language processing technology to determine a user's emotional state (negative, positive, neutral, etc.) from text data.

[0747] A "warning" is a notification or message intended to inform a user of the possibility of unexpected problems or negative consequences.

[0748] "Performance data" refers to information that shows the history of reactions and engagement to past posts and information content, and is used to optimize the system.

[0749] "Posting time" refers to the optimal time to publish user-generated data and content on the platform, and is important for gaining a lot of engagement.

[0750] "Information content" refers to all content provided to users, including media such as text, images, and videos.

[0751] "Market trends" are indicators that show changes in consumer preferences and behavioral patterns, as well as trends, in a particular market, and they influence decision-making in economic activities.

[0752] "Promotional activities" refer to public relations and marketing activities aimed at increasing consumer awareness and stimulating demand for products and services.

[0753] The system for implementing this invention primarily involves the cooperation of a server, a terminal, and a user. The server first collects user-generated data in real time using the API of a social media platform. This data includes user posts, comments, ratings, etc. The collected data is stored in a database, and sentiment analysis is performed using natural language processing algorithms. In this process, the server classifies whether the user's sentiment is negative, positive, or neutral, and issues warnings as necessary.

[0754] The server further uses machine learning algorithms based on collected historical performance data to predict the optimal posting time. This prediction makes it possible to maximize engagement with the information content. It also has a function to analyze market trends in real time to optimize promotional activities.

[0755] The terminal provides a user interface, displaying analysis results sent from the server, recommended posting times, and generated information. Through this terminal, users can make strategic decisions based on the presented information. For example, when promoting a new product, it's possible to run a campaign at the optimal time predicted by the server.

[0756] As a concrete example, a food brand is planning a campaign for a new drink. Using this application, the brand manager can determine the right timing and directly reach consumers with the most suitable content.

[0757] When using a generative AI model, the following prompt statements are possible:

[0758] "For a new drink campaign from a certain food brand, please suggest the optimal timing for posting information on social media. Please provide predictions based on past engagement data."

[0759] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0760] Step 1:

[0761] The server uses social media platform APIs to collect user-generated data. This data includes posts, comments, ratings, etc. The collected data is stored in a database and used for subsequent processing. The input is raw data obtained through the API, and the output is data stored in a formatted manner in the database.

[0762] Step 2:

[0763] The server applies natural language processing to stored user-generated data to perform sentiment analysis. This process analyzes the text of the data to classify whether it carries positive, negative, or neutral sentiment. The input is text data from the database, and the output is the sentiment classification result for each text. Specifically, it uses a text analysis library to perform tokenization and grammatical analysis.

[0764] Step 3:

[0765] Based on the sentiment analysis results, the server sends a warning to the device if there is a high concentration of negative emotions. This warning allows the user to take immediate action. The input is the sentiment analysis classification result, and the output is the warning message. The user can view this message on their device. Specifically, a push notification is sent using the notification function.

[0766] Step 4:

[0767] The server collects historical performance data and uses a machine learning algorithm to predict the optimal posting time. This prediction is used to maximize engagement for future posts. The input is historical engagement data, and the output is the predicted optimal posting time. Specifically, it performs machine learning model training and prediction processing.

[0768] Step 5:

[0769] The terminal displays analysis results sent from the server, recommended posting times, and generated information content in a user interface. This allows users to make timely strategic decisions. The input is analysis results and predicted data from the server, and the output is the information displayed on the terminal. Specifically, it performs graphical data display using a UI framework.

[0770] Step 6:

[0771] Users utilize the information provided on their devices to implement campaign and posting plans. Through the application, users can select and execute specific, data-driven actions. Input is the displayed information, and output is the actual actions performed by the user. Specifically, users configure settings using buttons and forms provided within the application.

[0772] 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.

[0773] The system of this invention streamlines social media operations through the coordination of servers, terminals, and users, and enables advanced interaction using an emotion engine.

[0774] Server operation

[0775] The server collects user-generated data from social media platforms. Examples include user posts, comments, and metadata. This data is stored in a database and passed to a sentiment analysis module. The server uses a sentiment engine to perform more detailed sentiment analysis, recognizing user emotions in real time. This information is used to determine whether posts and comments are positive, negative, or neutral. If a large number of negative emotions are detected, an alert is immediately generated to notify the user.

[0776] Furthermore, the server analyzes past performance data based on sentiment data obtained from the sentiment engine to predict the optimal posting time. It also utilizes this sentiment data to automatically generate more personalized content. For example, if it detects a pattern indicating user satisfaction, it generates content with a tone that matches that emotion.

[0777] Terminal operation

[0778] The device intuitively displays sentiment analysis results from the server, recommended posting times, and generated content to the user. Through this interface, the user can receive alerts and preview and edit the provided content. Visual data uploads and optimization results are also viewed on this device.

[0779] User actions

[0780] Users can build effective social media strategies based on information provided from their devices. For example, if the sentiment engine detects trends within the user's target audience, it can determine content and posting times accordingly. Furthermore, users can utilize chatbot functionality to provide personalized responses to their target audience, thereby improving their reputation.

[0781] Based on this model, systems incorporating an emotion engine support more effective social media management that takes user emotions into account, thereby strengthening engagement with target audiences.

[0782] The following describes the processing flow.

[0783] Step 1:

[0784] The server collects user-generated data through social media platform APIs. This includes data on posts, comments, and related reactions. This data is stored in a database to prepare it for subsequent processing.

[0785] Step 2:

[0786] The server uses the collected data to run an emotion engine. This engine utilizes natural language processing technology to classify emotions such as positive, negative, and neutral from the data. It also recognizes the emotions of individual users in real time and understands their trends.

[0787] Step 3:

[0788] The server activates an alert system based on emotional data. When a certain level of negative emotion is detected, it immediately generates an alert and notifies the user.

[0789] Step 4:

[0790] The server analyzes past performance data and combines it with sentiment information from the sentiment engine to predict the optimal posting time. This prediction indicates the time of day when user engagement is maximized.

[0791] Step 5:

[0792] The server automatically generates content that reflects emotional data. For example, if a lot of joy is detected, it will generate content with a bright and positive tone that is appropriate for this. This content is optimized in accordance with brand guidelines.

[0793] Step 6:

[0794] The device provides users with an interface that displays generated content, optimal posting times, and alerts. Users can view this information and adjust their posting content and strategy.

[0795] Step 7:

[0796] Users develop effective social media strategies based on analysis results from the emotion engine. For example, if a target audience shows a positive response to a particular campaign, additional content tailored to that response will be provided.

[0797] Step 8:

[0798] Users can leverage chatbot functionality to receive personalized, real-time responses that resonate with their emotions. This feature allows users to deepen their relationships with their target audience and increase engagement.

[0799] (Example 2)

[0800] 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".

[0801] Effective social media management presents challenges in processing large volumes of user-generated data and analyzing the resulting sentiments in real time. Furthermore, manually posting at the appropriate time and creating personalized content is time-consuming and labor-intensive, and responding quickly to negative sentiments is difficult. A system is needed to address these issues.

[0802] 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.

[0803] In this invention, the server includes means for acquiring user-generated data, means for performing sentiment analysis based on the user-generated data and identifying negative emotions, and means for acquiring sentiment labels for text data using a natural language processing model. This enables automated sentiment analysis and real-time detection of negative emotions.

[0804] "User-generated data" refers to information such as comments, images, and videos posted by users on social media platforms.

[0805] "Sentiment analysis" refers to the process of classifying emotions in text using natural language processing techniques and assigning emotion labels such as positive, negative, and neutral.

[0806] "Negative emotions" refers to information indicating negative feelings contained in user-generated data.

[0807] A "natural language processing model" refers to a program that uses machine learning algorithms to analyze, classify, and generate natural language text.

[0808] "Sentimental labels for text data" refer to tags that indicate emotions such as positive, negative, and neutral, which are assigned to text through sentiment analysis.

[0809] A "time series analysis algorithm" refers to a computational method used to model changes in data over time and predict future data.

[0810] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to automatically generate new text and content.

[0811] One embodiment of this invention is one that enables effective social media operation by coordinating a server, a terminal, and a user.

[0812] The server is the main component that manages the overall processing. The server retrieves data in real time from social media platforms using APIs. The collected data is organized and stored in a database. Based on the obtained user-generated data, sentiment analysis is performed using the natural language processing library NLTK and the deep learning model BERT. This analysis identifies whether the sentiment of each post is positive, negative, or neutral, and if negative sentiment is detected, an alert is immediately generated.

[0813] Furthermore, the server uses time-series analysis algorithms based on historical data to predict the optimal posting time. In addition, it leverages generative AI models to automatically generate content tailored to the user's target audience. For example, it can generate posts with a similar tone based on elements that have previously pleased users. In this way, the server consistently delivers optimized content.

[0814] The device intuitively displays analysis results and content suggestions sent from the server to the user. Based on the results and suggestions, the user can quickly adjust their posts. The device also allows for the uploading of visual data and confirmation of optimization results.

[0815] Users can build more effective social media strategies based on the information their devices provide. For example, they could launch new campaigns based on target audience trends revealed by sentiment analysis. Furthermore, they can improve engagement by fine-tuning generated content and posting it at the most opportune times.

[0816] An example of a prompt might be, "Generate text for the following post that will evoke positive emotions in the target audience." This allows the generation AI model to efficiently generate the specific content the user is looking for.

[0817] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0818] Step 1:

[0819] The server retrieves user-generated data using the APIs of social media platforms. This data includes posts, comments, and meta information. It accepts specific hashtags and account information as input and stores the retrieved data in a database as output. This stored data is then used for subsequent processing.

[0820] Step 2:

[0821] The server sends the stored user-generated data to the sentiment analysis module. It receives each text data item retrieved from the database as input, performs data calculations using a natural language processing library (e.g., NLTK or BERT), and labels the sentiment of each post. The output of this process is a sentiment label categorized as positive, negative, or neutral.

[0822] Step 3:

[0823] The server detects negative emotions based on the results of sentiment analysis. It receives emotion labels as input and generates an alert if negative emotions are predominant. The generated alert is immediately notified to the user, allowing them to recognize and address the problem early.

[0824] Step 4:

[0825] The server analyzes historical performance data to predict the optimal posting time. It receives historical interaction data and posting time history as input, and uses a time-series analysis algorithm to calculate the next recommended posting time as output. This information is used to optimize user operations.

[0826] Step 5:

[0827] The server generates content using an AI model based on sentiment analysis results. It receives user target audience profile information and sentiment trends as input, and uses prompts to instruct the AI ​​to generate content. The output is text and images optimized for the target audience, in a format usable by the user.

[0828] Step 6:

[0829] The terminal presents the user with analysis results and generated content sent from the server. It receives data from the server as input, visually organizes the information, and displays it as output. Based on this information, the user can adjust their posting content.

[0830] Step 7:

[0831] Users utilize data provided by their devices to develop effective posting strategies for their next posts. They receive device analytics results and recommendations as input, use them to plan their posts, and post content during the times when they are expected to perform best. This is expected to maximize user engagement on social media.

[0832] (Application Example 2)

[0833] 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".

[0834] When running advertising campaigns, it is difficult to respond immediately to the diverse emotions of users and maximize effectiveness in real time. Current methods are inefficient or sometimes delayed in quickly analyzing user feedback and optimizing ad content. This results in the challenge of not maximizing the effectiveness of advertising.

[0835] 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.

[0836] In this invention, the server includes a device for storing biometric information, a device for performing emotional evaluation based on the biometric information and detecting negative emotions, and a device for notifying the user based on the results of the emotional evaluation. This enables real-time evaluation of users' emotions in advertising campaigns, immediate detection of negative emotions, and rapid optimization of advertising content.

[0837] "Biometric information" refers to data that shows the emotional state and physiological responses of individual users.

[0838] "Emotional assessment" is a process that analyzes a user's emotions based on collected biometric information and determines whether they tend to be positive or negative.

[0839] "Negative emotions" refer to emotional states such as sadness and anger that lead to discomfort for the user.

[0840] "Notification" refers to the act of communicating specific information or warnings to a user, or the means of doing so.

[0841] "Performance data" refers to recorded information about past actions and performance, which is useful for developing efficient strategies.

[0842] "Communication time" refers to the time period during which specific information is most effectively transmitted.

[0843] "Information" refers to digital content generated based on the user's emotional state and behavior.

[0844] An "advertising campaign" refers to a series of activities carried out to increase awareness of a particular product or service and to stimulate demand.

[0845] "Measuring effectiveness" is the process of using quantitative and qualitative metrics to evaluate the success of an advertising campaign.

[0846] "Emotional data" refers to a dataset containing comprehensive information about users' emotional states.

[0847] For this invention to be implemented, coordination between the server, terminal, and user is crucial. The server first collects biometric information and performs an emotional assessment based on this information. Specifically, it stores the collected biometric information in a database and analyzes the user's emotions through an emotion analysis module. This emotion analysis uses an emotion engine to recognize in real time whether the user's emotions are positive or negative. If negative emotions are detected, a notification is immediately generated and transmitted to the user.

[0848] Furthermore, the server measures the effectiveness of advertising campaigns and automatically optimizes ad content using emotional data. This includes a process of calculating appropriate communication time based on past performance data and generating information tailored to the user's emotional state.

[0849] The device can intuitively display sentiment evaluation results and optimized advertising information provided by the server to the user. Through this interface, the user can receive notifications, review the provided advertisements, and send feedback as needed. This feedback is then sent back to the server for further analysis by the sentiment engine.

[0850] For example, when an advertiser conducts an advertising campaign using smartphones, they can analyze users' real-time emotional responses and quickly adjust the ad content. This process makes it possible to maximize the effectiveness of the advertising campaign and improve user engagement.

[0851] An example of a prompt would be, "How can we understand audience emotional responses to our advertising campaign in real time and make immediate adjustments?" By leveraging generative AI models, advertisers can use these emotional data-driven prompts to optimize their strategies.

[0852] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0853] Step 1:

[0854] The server acquires biometric information, including data collection from the user's smartphone or wearable device. Input data includes heart rate and facial expression data, which are temporarily stored on the server. This data is then passed to an emotion analysis module as output. The data collection and transfer are performed securely using a cloud storage service.

[0855] Step 2:

[0856] The server uses an emotion analysis module to analyze acquired biometric information. The input is the user's biometric information, and the output is an evaluation of their emotions. Specifically, the system performs pattern recognition and emotion classification using a generative AI model. This data processing allows the user's emotional state to be determined in real time as positive, negative, etc.

[0857] Step 3:

[0858] The server analyzes the sentiment evaluation results and immediately generates a notification if negative emotions are detected. This notification generation involves specific actions, such as taking the sentiment evaluation results as input and outputting a warning message to the user. The notification format is implemented as a text message or push notification.

[0859] Step 4:

[0860] The server analyzes advertising campaign performance data and calculates the appropriate communication time. The input is historical performance data, and the output is the optimal posting timing. This involves statistical methods using data analysis algorithms.

[0861] Step 5:

[0862] The server automatically generates advertising information using a generative AI model. The input consists of emotional data and calculated communication time, while the output is the generated advertising content. This process automatically constructs personalized advertising content.

[0863] Step 6:

[0864] The terminal displays sentiment ratings and advertising information sent from the server to the user. Input information is notification data from the server, and output is a display on the user interface. Specifically, it conveys information intuitively through a GUI (Graphical User Interface).

[0865] Step 7:

[0866] Users review the information provided via their devices and send feedback as needed. The input is the advertising information displayed on the device, and the output is feedback data sent to the server. This process allows the server to receive new data, enabling further optimization of the sentiment engine.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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."

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] The following is further disclosed regarding the embodiments described above.

[0889] (Claim 1)

[0890] Means for collecting user-generated data,

[0891] A means for performing sentiment analysis based on the user-generated data and detecting negative emotions,

[0892] Based on the results of sentiment analysis, a means of sending alerts to users,

[0893] A method for predicting the optimal posting time based on past performance data,

[0894] A means of automatically generating content,

[0895] The means for providing the automatically generated content to the user,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, further comprising means for recognizing and optimizing visual data.

[0899] (Claim 3)

[0900] The system according to claim 1, further comprising means for providing interactive responses using a chatbot.

[0901] "Example 1"

[0902] (Claim 1)

[0903] Means of collecting information from an information exchange platform,

[0904] A means for performing text analysis based on the aforementioned information and detecting negative emotions,

[0905] A means of sending a warning to the information provider based on the results of text analysis,

[0906] A method for predicting the appropriate information delivery time based on past performance data,

[0907] A means of automatically generating content,

[0908] Means for providing the automatically generated content to the information provider,

[0909] A system that includes this.

[0910] (Claim 2)

[0911] The system according to claim 1, further comprising means for recognizing and optimizing visual information.

[0912] (Claim 3)

[0913] The system according to claim 1, further comprising an automated dialogue device for providing interactive responses.

[0914] "Application Example 1"

[0915] (Claim 1)

[0916] Means for collecting user-generated data,

[0917] A means for performing sentiment analysis based on the user-generated data and detecting negative emotions,

[0918] Based on the results of sentiment analysis, a means of issuing warnings to users,

[0919] A method for predicting the optimal posting time based on past performance data,

[0920] A means of automatically generating information content,

[0921] Means for providing the automatically generated information content to the user,

[0922] A means of analyzing market trends and consumer reactions in real time to optimize advertising activities,

[0923] A system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, further comprising means for recognizing and optimizing visual data.

[0926] (Claim 3)

[0927] The system according to claim 1, further comprising means for providing interactive responses using a chatbot.

[0928] "Example 2 of combining an emotion engine"

[0929] (Claim 1)

[0930] A means of obtaining user-generated data,

[0931] A means for performing emotion analysis based on the user-generated data and identifying negative emotions,

[0932] A means of sending a warning to the user based on the results of emotion analysis,

[0933] A method for estimating the optimal posting time based on past performance data,

[0934] A means of automatically generating content,

[0935] A means for presenting the automatically generated content to the user,

[0936] A method for obtaining sentiment labels from text data using a natural language processing model,

[0937] A method for calculating the optimal posting time using a time-series analysis algorithm,

[0938] A means of generating response content using an AI model,

[0939] A system that includes this.

[0940] (Claim 2)

[0941] The system according to claim 1, further comprising means for detecting and optimizing visual information.

[0942] (Claim 3)

[0943] The system according to claim 1, further comprising means for using a program for providing interactive responses.

[0944] "Application example 2 when combining with an emotional engine"

[0945] (Claim 1)

[0946] A device for accumulating biological information,

[0947] A device that performs emotional evaluation based on the aforementioned biological information and detects negative emotions,

[0948] A device that notifies the user based on the results of the emotional assessment,

[0949] A device that calculates the appropriate communication time based on past performance data,

[0950] A device that automatically generates information,

[0951] A device that provides the automatically generated information to the user,

[0952] A device that measures the effectiveness of advertising campaigns and optimizes advertising content using emotional data,

[0953] A system that includes this.

[0954] (Claim 2)

[0955] The system according to claim 1, further comprising a device for analyzing and optimizing visual information.

[0956] (Claim 3)

[0957] The system according to claim 1, further comprising a device that provides a response using a conversational agent. [Explanation of symbols]

[0958] 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 collecting user-generated data, A means for performing sentiment analysis based on the user-generated data and detecting negative emotions, Based on the results of sentiment analysis, a means of sending alerts to users, A method for predicting the optimal posting time based on past performance data, A means of automatically generating content, The means for providing the automatically generated content to the user, A system that includes this.

2. The system according to claim 1, further comprising means for recognizing and optimizing visual data.

3. The system according to claim 1, further comprising means for providing interactive responses using a chatbot.

Images