system

Abstract

Provide a system. 【Solution means】 Means for automatically generating advertising text from information input using natural language processing, Means for analyzing the behavior information of past users to identify the optimal delivery time, Means for analyzing posts on social media and classifying emotions, Means for individually optimizing information based on the past behavior history of users, Means for analyzing video and moving images to optimize visual elements, Information processing means for automatically responding to inquiries from users, Means for analyzing the effectiveness of the provided advertising campaigns and providing feedback for strategic improvement, A system including the above.

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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern digital society, in order for companies and individuals to effectively utilize social media, unified management across a variety of platforms and an appropriate approach to the target audience are required. However, these tasks require time and effort, and it is particularly difficult to respond in real time and optimize posts based on user behavior patterns. Therefore, there is an increasing need for an integrated system to improve efficiency and quality in social media strategies.

Means for Solving the Problems

[0005] This invention provides an AI social media manager equipped with means for automatically generating content using natural language processing, means for determining the optimal posting time based on user behavior data, means for classifying sentiment through sentiment analysis, means for optimizing content based on user behavior history, means for optimizing images and videos, and means for real-time automated responses. This system enables centralized management of multiple social media channels, maximizing engagement and achieving consistent branding.

[0006] "Natural language processing" is the technology that enables computers to understand, interpret, and generate human language.

[0007] "Automatic content generation" is a process in which an algorithm automatically creates appropriate text and captions based on the input data.

[0008] "User behavior data" refers to a collection of information about users' activities and interactions on social media.

[0009] "Optimal posting time" refers to the time of day when a post on social media is considered most effective in generating maximum engagement.

[0010] Sentiment analysis is a technique that classifies the emotions expressed in text data as positive, negative, or neutral.

[0011] "Content optimization" is the process of improving the quality and relevance of information provided by taking into account user preferences and behavioral history.

[0012] "Image and video optimization" is a technology that enhances the appearance and communication effectiveness of visual content by automatically adjusting its resolution, brightness, contrast, and other parameters.

[0013] "Automated response" refers to a system that quickly provides appropriate answers to user inquiries from a pre-configured database. [Brief explanation of the drawing]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered 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.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] The AI ​​social media manager system of the present invention consists of a server, a terminal, and a user. The server has the ability to automatically generate appropriate content from input data using a natural language processing algorithm and to create posts that conform to the brand strategy specified by the user. For example, based on information about a new product announcement, the server generates a caption that emphasizes the characteristics and benefits of the product.

[0036] By analyzing user behavior data, the server identifies the optimal posting time for the highest engagement and suggests a schedule to users. This allows companies to effectively reach their target audience.

[0037] Furthermore, the server analyzes brand-related posts on social media and categorizes sentiment. This process allows for the rapid detection of negative reactions, enabling users to take appropriate responses based on the situation.

[0038] Based on users' past behavior, the server recommends personalized content to support more effective marketing activities. In addition, image and video recognition algorithms automatically optimize visual content, enhancing the delivery of messages to target audiences.

[0039] The terminal receives user instructions and uses data from the server to provide real-time automated responses. For example, when a user inquires about a product, the terminal can search for the relevant information in the database and provide an answer immediately.

[0040] This system allows users to streamline the management of multiple social media platforms, enabling consistent branding and an optimal approach to their target audience.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user inputs brand information and target audience data. The server receives this data and begins automatically generating appropriate content using natural language processing.

[0044] Step 2:

[0045] The server analyzes the generated content and identifies the optimal posting time based on user behavior data. Based on this information, the server creates a posting schedule and proposes it to the user.

[0046] Step 3:

[0047] The server analyzes brand-related posting data collected from social media, performs sentiment analysis, and categorizes emotions. If negative reactions are detected, the server sends an alert to the user.

[0048] Step 4:

[0049] The server generates personalized content based on the user's past behavior history and provides the user with a list of recommended content.

[0050] Step 5:

[0051] When image and video data are uploaded, the server recognizes them and optimizes their visual attributes (brightness, contrast, etc.).

[0052] Step 6:

[0053] The terminal receives user inquiries in real time and searches for relevant information in the database provided by the server. The terminal then generates an automated response and sends the answer to the user.

[0054] (Example 1)

[0055] 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."

[0056] In today's information media environment, businesses and individuals are required to efficiently manage large-scale information activities. However, creating information, disseminating it at the optimal time, analyzing received information and its sentiment, and providing personalized information to each individual are all challenging tasks, necessitating an effective management system. Therefore, there is a need for technological means to simultaneously achieve automation and optimization of information operations.

[0057] 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.

[0058] In this invention, the server includes means for automatically generating information from input information using natural language processing, means for analyzing past operator behavior to identify the optimal activity time, and means for analyzing posts on information media and classifying emotions. This enables large-scale automation and individual optimization of information operations.

[0059] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0060] "Automatic information generation" is a process in which a machine automatically constructs new information based on the input information.

[0061] "User behavior" refers to the patterns and history of user actions when using a system, and is data that is useful for system improvement and individual optimization.

[0062] "Optimal activity time" refers to the time period selected based on analysis to maximize the effectiveness of information dissemination.

[0063] An "information medium" is any platform or channel used to transmit, share, or store information.

[0064] "Emotional classification" is the process of categorizing the emotions contained in information or text into positive, negative, neutral, and so on.

[0065] A "still image" refers to a visual representation or photograph that is not moving, and is a form of visual data.

[0066] A "video" is a form of media that expresses movement by having a series of still images play in sequence over time.

[0067] "Visual information optimization" is the process of using algorithms to modify and improve images and videos in order to enhance their appearance and effect.

[0068] "Automatic response to inquiries" refers to a function where a system mechanically provides answers to questions and requests from users based on pre-configured information.

[0069] This system is designed to allow operators to efficiently manage their activities on information media. The system primarily consists of a server, terminals, and operators. The server uses natural language processing algorithms to automatically generate new content based on information provided by the operators. For example, the server uses a generative AI model. Specifically, it leverages widely available generative AI technologies to generate text that highlights product characteristics.

[0070] In addition, the server analyzes past user behavior to identify the optimal posting time. Digital analytics tools and statistical software are used for data analysis. This allows users to post information during times of high engagement, increasing efficiency.

[0071] Furthermore, the server analyzes posts on the information platform and classifies the sentiment (emotions) expressed. This allows for the rapid detection of negative reactions, enabling operators to quickly respond to situations requiring immediate attention. Natural language processing technology is used to classify each post as positive, negative, or neutral.

[0072] In optimizing visual information, the server analyzes images and videos to make adjustments that maintain an optimal appearance. It uses common image processing libraries and visual algorithms to improve visual elements.

[0073] The terminal receives inquiries from the operator and automatically responds based on information provided by the server. For example, the terminal can instantly provide the best answer from a database of pre-configured questions about the product.

[0074] For example, if an operator wants to promote a new product, "EcoPhone," this system can be used to automatically generate posts that effectively highlight the product's features and benefits. Furthermore, if the operator enters a prompt such as, "EcoPhone is made with the latest technology and uses environmentally friendly materials. Please generate a social media post based on this," the AI ​​model will generate a creative message on their behalf.

[0075] This system enables operators to deliver consistent messaging and effectively reach their targets.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server receives brand strategy and product information provided by the operator and generates prompt messages based on this information. This input includes product characteristics, target audience information, and the purpose of the post. Specifically, the server retrieves product information from the database and creates prompt messages in a format that is easy for the generating AI model to understand.

[0079] Step 2:

[0080] The server inputs prompt text into a generative AI model, which automatically generates content in natural language. Based on the input prompt text, the generative AI model outputs post content that highlights the product's features. The AI ​​model is hosted on the server, and processing takes place on the internal network. Specifically, the generated text is saved as a temporary file and used in subsequent processes.

[0081] Step 3:

[0082] The server analyzes the user's past behavior history and engagement data to calculate the optimal posting time. The input for this step is access data related to past posts, and the output is a suggestion of the optimal time slot. The server uses analytical software to statistically analyze the differences in engagement based on posting timing and reports the derived data to the user.

[0083] Step 4:

[0084] The server analyzes sentiment from posts on information platforms and classifies the emotions they express. The input is recently posted comments and feedback, and the output is whether the content is positive, negative, or neutral. Here, the server uses natural language processing techniques to analyze keywords and context within the text and calculate a sentiment score.

[0085] Step 5:

[0086] The server is responsible for optimizing visual content, analyzing still images and videos to improve their quality. The input for this step is image and video data uploaded by the user, and the output is an improved version with automatically adjusted brightness and contrast. The server utilizes image processing libraries and applies histogram equalization and color correction algorithms.

[0087] Step 6:

[0088] The terminal receives inquiries from the operator in real time and provides automated responses. The input consists of the operator's questions and requests, and the output is a database-based answer. The terminal accesses the database on the server, searches for the most appropriate answer from a pre-configured set of questions and answers, and presents it.

[0089] (Application Example 1)

[0090] 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."

[0091] Modern advertising strategies require effectively reaching target audiences, optimizing visual elements, and maximizing ad effectiveness. Real-time user interaction and results analysis, along with incorporating feedback into future strategies, are also crucial. However, there is a lack of systems to efficiently manage these processes.

[0092] 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.

[0093] In this invention, the server includes means for automatically generating advertising text from input information using natural language processing, means for analyzing past user behavior information to identify the optimal delivery time, and means for analyzing the effectiveness of the delivered advertising campaign and providing feedback for strategic improvement. This enables the planning and execution of efficient and effective advertising strategies.

[0094] "Natural language processing" is a technology that uses computers to analyze and understand human language.

[0095] "Inputted information" refers to data and instructions received from the user.

[0096] "Advertising text" refers to text created for the purpose of promoting a product or service.

[0097] "User behavior information" refers to data about a user's past behavioral history and trends.

[0098] "Delivery time" refers to the optimal time to publish or send advertising content.

[0099] "Visual elements" are the elements contained in images and videos, and are components that appeal to people's vision.

[0100] "Information processing means" refers to mechanical or programmed methods for receiving data and processing it.

[0101] "The effectiveness of an advertising campaign" refers to the impact and results that promotional activities have on the audience.

[0102] "Feedback for strategic improvement" refers to the analysis of the results of an advertisement and the suggestions and advice provided to help improve future campaigns.

[0103] The system implementing this invention has a server-centric structure. The server first analyzes information input from the user using natural language processing algorithms. Specifically, the software uses TENSORFLOW® and PyTorch for natural language processing and leverages OpenAI®'s GPT model to automatically generate advertising text. The text generated based on user instructions and product information is used as part of an advertising campaign.

[0104] Next, the server analyzes the user's past behavior history. During this process, data mining techniques are used to understand user behavior and trends, and to identify the optimal service time. A machine learning library using Python is applied to this data analysis.

[0105] Furthermore, the terminal receives inquiries from users in real time and refers to a pre-configured database as a means of information processing. This allows for immediate responses to user questions. For example, if a user inquires about the details of an advertising campaign, the server quickly retrieves the relevant information from the database and provides an appropriate answer.

[0106] As a concrete example, consider a marketing campaign for a new sneaker. In this case, the server generates an advertising tagline based on information such as "We want to promote sneakers featuring the latest design and performance." It uses a prompt message such as, "Suggest an effective ad copy and posting time based on the new product launch information." This supports campaign deployment at appropriate times for the target audience of young people.

[0107] This configuration allows advertising strategies to be implemented efficiently and effectively while maintaining consistency.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The server receives advertising campaign information entered by users. This input includes information about product features and target audience. The server analyzes this data using natural language processing algorithms to extract features necessary for generating advertising text. In this process, TensorFlow and GPT models are used to process the text data.

[0111] Step 2:

[0112] The server analyzes collected data by referencing past user behavior history. Input data includes records of past advertising campaigns and user responses. Using a machine learning library based on Python, the server predicts the optimal delivery time based on past trends and generates this as output. This result is used to optimize campaign schedules.

[0113] Step 3:

[0114] The terminal receives user inquiries in real time. Users input questions about specific advertising campaigns into the terminal. The terminal uses a pre-configured database for information processing, instantly retrieving the appropriate answer. This process is performed using a database management system and output as a response to the user.

[0115] Step 4:

[0116] The server integrates generated ad text and delivery time information to optimize ad campaign planning. Input includes past campaign results and newly generated ad content. The server then re-evaluates the overall ad strategy and outputs feedback for the next campaign. Based on this feedback, users can refine their next ad strategy.

[0117] Step 5:

[0118] Users review the feedback and new advertising strategies provided by the server and then execute new campaigns based on that. The input is the feedback information from the server, and the output is the actual advertising execution in the market. Through this process, the effectiveness of the advertising is evaluated by the user and reflected in the strategy.

[0119] 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.

[0120] This invention is a social media management system utilizing AI technology, providing advanced marketing support by combining natural language processing, user behavior analysis, and an emotion engine. The core of the system includes an analysis and generation engine installed on the server, which enables content generation, user emotion recognition, and the provision of optimal posting timing.

[0121] The server first receives brand information and message themes entered by the user and generates basic content using natural language processing. During this process, an emotion engine is also used to analyze the user's emotional state. The emotion engine analyzes text and audio data to identify the user's emotions. Based on this, it automatically adjusts the tone and style of the generated content to provide a message that best matches the user's intent.

[0122] Furthermore, the server analyzes past user behavior data to calculate the optimal posting time and presents users with a posting schedule designed to maximize engagement. The server also utilizes feedback from the sentiment engine in this process to achieve a more personalized strategy.

[0123] Regarding image and video analysis, the server identifies objects in visual content and automatically adjusts brightness and contrast to enhance visual appeal. This feature is particularly effective in advertising campaigns and branding.

[0124] The terminal quickly receives user inquiries, generates appropriate answers from the server's database, and provides them to the user in real time. This process allows companies to improve the efficiency of their customer service.

[0125] As a concrete example, when a company conducts marketing activities for a new product, the server instantly generates ad copy based on the characteristics of the product offered and the target market. The emotion engine selects a positive tone according to the campaign's objectives and delivers a message that takes into account the emotional response of the recipient. Once the user approves this content, it is posted at the optimal time. This allows companies to efficiently communicate their brand value and reach the right customer segments.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The user inputs data about brand information, target audience, and message tone into the system. The server receives this input data and activates a natural language processing algorithm.

[0129] Step 2:

[0130] The server uses natural language processing to generate basic content based on the input data. It then automatically verifies whether the generated text aligns with the company's messaging strategy.

[0131] Step 3:

[0132] The server activates an emotion engine, analyzing data provided by the user and past interactions to identify the user's emotional state. Based on this analysis, it optimizes the tone and style of the content it generates.

[0133] Step 4:

[0134] The server analyzes past user behavior data to calculate the optimal posting time that maximizes engagement. Based on this information, it presents a recommended posting schedule to the user.

[0135] Step 5:

[0136] The server analyzes image and video data and identifies objects within it. It also automatically adjusts image brightness and contrast to improve the quality of the visual content.

[0137] Step 6:

[0138] The terminal immediately receives user inquiries and transmits them to the server in real time. The server retrieves the appropriate information from the database and quickly provides the user with an answer through the terminal.

[0139] Step 7:

[0140] After all processing is complete, the user reviews and modifies the plan and content provided by the server and posts to social media at what they deem the optimal time.

[0141] (Example 2)

[0142] 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".

[0143] In today's social media landscape, it's crucial to effectively create personalized marketing content based on user-provided information and deliver it at the right time. However, traditional systems struggle to adequately reflect users' emotional states and behavioral data, making it difficult to optimize content generation and delivery schedules, which hinders engagement.

[0144] 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.

[0145] In this invention, the server includes means for automatically generating content using natural language processing with a generation AI model based on information input from the user, means for analyzing the emotional state of the input data using an emotion engine and adjusting the tone of the content, and means for analyzing past user behavior data to identify the optimal posting timing and present a schedule. This enables the creation of content customized to the user's needs and delivery at the appropriate time.

[0146] A "generative AI model" refers to an algorithm that automatically generates text and other content based on information provided by the user.

[0147] "Natural language processing" refers to the process of analyzing input text and generating appropriate output using technologies that enable computers to understand, generate, and manipulate human language.

[0148] An "emotion engine" refers to a technology that analyzes the user's emotional state and emotional nuances from input data, and adjusts the tone and style of content based on that analysis.

[0149] "User behavior data" refers to data such as users' past activities and engagement patterns on social media, and this data is used to analyze and determine the optimal timing for posting.

[0150] "Visual elements" refer to the constituent elements included in visual content such as images and videos, and optimizing these elements improves the appeal of the information.

[0151] A "response database" refers to a dataset containing a pre-prepared list of answers used to generate appropriate responses to user inquiries.

[0152] This invention provides a method for supporting marketing by combining natural language processing, user behavior analysis, and an emotion engine through a social media management system that utilizes AI technology.

[0153] The server first receives brand information and message themes entered by the user, and then uses a generative AI model to generate content using natural language processing technology. This generative AI model uses text generation algorithms such as GPT.

[0154] Next, the server uses an emotion engine to analyze the emotional state of the input data and adjust the tone of the generated content. The emotion engine identifies emotional nuances from text and audio data and optimizes the content accordingly.

[0155] The server further analyzes past user behavior data to calculate the optimal posting timing to maximize engagement. This data analysis uses machine learning algorithms and takes into account the user's social media activity patterns.

[0156] In addition, the server analyzes image and video content, identifying the visual elements it contains. By automatically adjusting brightness and contrast to enhance visual appeal, it improves the effectiveness of advertisements and branding.

[0157] The terminal plays the role of immediately receiving user inquiries. It can automatically generate appropriate responses from information stored in the server's database and provide them to the user in real time. This allows users to receive efficient support from the company.

[0158] As a concrete example, when a company launches a marketing campaign for a new product, the user inputs information about the product's characteristics and target market as prompts. If the prompt is something like, "Create advertising copy for a new eco-friendly product. The target audience is people in their 20s and 30s who are interested in environmental issues. Use the emotion engine to adjust the message to a positive tone and calculate the optimal posting time," the server will immediately generate marketing copy based on this information and deliver it on an optimized schedule.

[0159] This system enables users to effectively communicate their brand and product information and maximize their reach to their target audience.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The user inputs a prompt message into the server, which includes brand information and a message theme. This prompt message serves as the basis for content generation using a generative AI model. Based on the input information, the server uses natural language processing techniques to generate text. The generated content forms the basis of the message.

[0163] Step 2:

[0164] The server passes the generated content to the emotion engine, which performs sentiment analysis based on the user's intent. The input is the previously generated content, and the output is content optimized for emotional tone and style. Text and audio data are analyzed, and the tone of the message is adjusted based on the desired emotion.

[0165] Step 3:

[0166] The server receives historical user behavior data as input and uses statistical analysis and machine learning algorithms to calculate the optimal posting timing. In this process, it considers the user's activity patterns and engagement data on social media and outputs the optimal posting schedule. As a result, a timeframe for achieving maximum engagement is provided.

[0167] Step 4:

[0168] The server receives image and video data provided by the user as input and performs automatic analysis of its visual elements. This includes adjusting brightness and contrast, resulting in optimized visual content as output. Improvements through visual analysis maximize the visual appeal of the content.

[0169] Step 5:

[0170] The user reviews the generated final content and proposed schedule, makes any necessary revisions, and approves the content. This allows the server to automatically post the content according to the specified schedule. The system is then adjusted to ensure the content is delivered at the optimal time.

[0171] Step 6:

[0172] The terminal receives inquiries from users in real time, and the server generates and outputs appropriate responses from a pre-configured response database. By providing these responses to the user, the terminal enables rapid communication. This allows users to receive feedback and information immediately.

[0173] (Application Example 2)

[0174] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0175] In social media marketing, there is a need to create content that attracts user interest, deliver messages that resonate with user emotions, and optimize posting timing to effectively promote engagement. However, traditional methods only consider these elements individually, making it difficult to achieve a comprehensive and efficient marketing strategy.

[0176] 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.

[0177] In this invention, the server includes means for automatically generating content from input data using natural language processing, means for identifying the optimal posting time by analyzing past user behavior data, and means for analyzing posts on social media and classifying sentiment. This enables the execution of an effective marketing strategy.

[0178] "Natural language processing" is a technology that uses computers to understand human language and automatically generate or analyze it.

[0179] "Automatic content generation" refers to a process where a program automatically creates text and media based on input data.

[0180] "User behavior data" refers to the history of actions and choices taken by users when using a service.

[0181] "Posting time optimization" is a technique that calculates and identifies the optimal time to post information in order to maximize user engagement.

[0182] "Sentiment analysis" is the process of identifying and classifying a user's emotions from text or audio.

[0183] "Tone adjustment" is the process of modifying the style and expression of a message or content to make it more appropriate for its purpose.

[0184] "Machine learning" is a technology that uses algorithms to allow computers to analyze data and learn patterns on their own.

[0185] "Image processing" is a technique that uses computers to analyze images and modify or improve their characteristics as needed.

[0186] "Engagement" is a term that describes the degree of user engagement with posts on social media.

[0187] To implement this invention, the server is equipped with a program that uses natural language processing technology to convert input data into content. This program automatically generates advertising copy and other content using a generative AI model based on brand information and messages entered by the user. The server uses spaCy, a Python natural language processing library, to perform text analysis and generation.

[0188] Furthermore, the device collects user behavior data and provides a function to estimate the optimal posting time based on that history. This utilizes the machine learning library scikit-learn to analyze past posting data and engagement data to calculate the appropriate timing.

[0189] The sentiment engine is also implemented on the server side, using the TextBlob library to perform sentiment analysis on text and identify the user's emotional state. This allows the server to adjust the tone of the content to suit the user's intent and situation.

[0190] For image and video analysis, the server uses OpenCV to optimize visual content. This enhances the visual appeal of advertisements and other content by automatically adjusting the brightness and contrast of images.

[0191] As a concrete example, when a coffee shop advertises a new seasonal beverage, the system can generate advertising copy promoting "a new drink that lets you enjoy the scents and flavors of autumn" using CAMP. The system automatically adjusts the autumn foliage scene as visual content, providing an advertisement with visual appeal. For example, by inputting instructions such as "Generate an advertisement promoting a new autumn-only product" into the server's AI model, it is possible to generate appropriate content.

[0192] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0193] Step 1:

[0194] The server receives brand information and message content provided by the user. Using this input data, it performs basic text analysis using a natural language processing library (spaCy). Based on the analysis results, a generative AI model generates advertising copy.

[0195] Step 2:

[0196] The generated ad copy is analyzed by an emotion engine on the server. The emotion engine uses TextBlob to analyze the sentiment within the text and adjust the tone as needed. This process ensures that emotionally appropriate content that matches the user's intent is output.

[0197] Step 3:

[0198] The device collects past user behavior data and analyzes the optimal posting time based on the accumulated data. This analysis uses scikit-learn to apply machine learning algorithms. This calculates the posting timing that maximizes engagement.

[0199] Step 4:

[0200] The server uses an image processing library (OpenCV) to analyze the visual elements contained in the content. By automatically adjusting the brightness and contrast of images and videos, it outputs content with improved visual appeal.

[0201] Step 5:

[0202] Once the user reviews and approves this content, it will be automatically posted at the optimal time. This posting timing is determined based on the data calculated in step 3.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] [Second Embodiment]

[0207] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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".

[0219] The AI ​​social media manager system of the present invention consists of a server, a terminal, and a user. The server has the ability to automatically generate appropriate content from input data using a natural language processing algorithm and to create posts that conform to the brand strategy specified by the user. For example, based on information about a new product announcement, the server generates a caption that emphasizes the characteristics and benefits of the product.

[0220] By analyzing user behavior data, the server identifies the optimal posting time for the highest engagement and suggests a schedule to users. This allows companies to effectively reach their target audience.

[0221] Furthermore, the server analyzes brand-related posts on social media and categorizes sentiment. This process allows for the rapid detection of negative reactions, enabling users to take appropriate responses based on the situation.

[0222] Based on users' past behavior, the server recommends personalized content to support more effective marketing activities. In addition, image and video recognition algorithms automatically optimize visual content, enhancing the delivery of messages to target audiences.

[0223] The terminal receives user instructions and uses data from the server to provide real-time automated responses. For example, when a user inquires about a product, the terminal can search for the relevant information in the database and provide an answer immediately.

[0224] This system allows users to streamline the management of multiple social media platforms, enabling consistent branding and an optimal approach to their target audience.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The user inputs brand information and target audience data. The server receives this data and begins automatically generating appropriate content using natural language processing.

[0228] Step 2:

[0229] The server analyzes the generated content and identifies the optimal posting time based on user behavior data. Based on this information, the server creates a posting schedule and proposes it to the user.

[0230] Step 3:

[0231] The server analyzes brand-related posting data collected from social media, performs sentiment analysis, and categorizes emotions. If negative reactions are detected, the server sends an alert to the user.

[0232] Step 4:

[0233] The server generates personalized content based on the user's past behavior history and provides the user with a list of recommended content.

[0234] Step 5:

[0235] When image and video data are uploaded, the server recognizes them and optimizes their visual attributes (brightness, contrast, etc.).

[0236] Step 6:

[0237] The terminal receives user inquiries in real time and searches for relevant information in the database provided by the server. The terminal then generates an automated response and sends the answer to the user.

[0238] (Example 1)

[0239] 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."

[0240] In today's information media environment, businesses and individuals are required to efficiently manage large-scale information activities. However, creating information, disseminating it at the optimal time, analyzing received information and its sentiment, and providing personalized information to each individual are all challenging tasks, necessitating an effective management system. Therefore, there is a need for technological means to simultaneously achieve automation and optimization of information operations.

[0241] 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.

[0242] In this invention, the server includes means for automatically generating information from input information using natural language processing, means for analyzing past operator behavior to identify the optimal activity time, and means for analyzing posts on information media and classifying emotions. This enables large-scale automation and individual optimization of information operations.

[0243] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0244] "Automatic information generation" is a process in which a machine automatically constructs new information based on the input information.

[0245] "User behavior" refers to the patterns and history of user actions when using a system, and is data that is useful for system improvement and individual optimization.

[0246] "Optimal activity time" refers to the time period selected based on analysis to maximize the effectiveness of information dissemination.

[0247] An "information medium" is any platform or channel used to transmit, share, or store information.

[0248] "Emotional classification" is the process of categorizing the emotions contained in information or text into positive, negative, neutral, and so on.

[0249] A "still image" refers to a visual representation or photograph that is not moving, and is a form of visual data.

[0250] A "video" is a form of media that expresses movement by having a series of still images play in sequence over time.

[0251] "Visual information optimization" is the process of using algorithms to modify and improve images and videos in order to enhance their appearance and effect.

[0252] "Automatic response to inquiries" refers to a function where a system mechanically provides answers to questions and requests from users based on pre-configured information.

[0253] This system is designed to allow operators to efficiently manage their activities on information media. The system primarily consists of a server, terminals, and operators. The server uses natural language processing algorithms to automatically generate new content based on information provided by the operators. For example, the server uses a generative AI model. Specifically, it leverages widely available generative AI technologies to generate text that highlights product characteristics.

[0254] In addition, the server analyzes past user behavior to identify the optimal posting time. Digital analytics tools and statistical software are used for data analysis. This allows users to post information during times of high engagement, increasing efficiency.

[0255] Furthermore, the server analyzes posts on the information platform and classifies the sentiment (emotions) expressed. This allows for the rapid detection of negative reactions, enabling operators to quickly respond to situations requiring immediate attention. Natural language processing technology is used to classify each post as positive, negative, or neutral.

[0256] In optimizing visual information, the server analyzes images and videos to make adjustments that maintain an optimal appearance. It uses common image processing libraries and visual algorithms to improve visual elements.

[0257] The terminal receives inquiries from the operator and automatically responds based on information provided by the server. For example, the terminal can instantly provide the best answer from a database of pre-configured questions about the product.

[0258] For example, if an operator wants to promote a new product, "EcoPhone," this system can be used to automatically generate posts that effectively highlight the product's features and benefits. Furthermore, if the operator enters a prompt such as, "EcoPhone is made with the latest technology and uses environmentally friendly materials. Please generate a social media post based on this," the AI ​​model will generate a creative message on their behalf.

[0259] This system enables operators to deliver consistent messaging and effectively reach their targets.

[0260] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0261] Step 1:

[0262] The server receives brand strategy and product information provided by the operator and generates prompt messages based on this information. This input includes product characteristics, target audience information, and the purpose of the post. Specifically, the server retrieves product information from the database and creates prompt messages in a format that is easy for the generating AI model to understand.

[0263] Step 2:

[0264] The server inputs prompt text into a generative AI model, which automatically generates content in natural language. Based on the input prompt text, the generative AI model outputs post content that highlights the product's features. The AI ​​model is hosted on the server, and processing takes place on the internal network. Specifically, the generated text is saved as a temporary file and used in subsequent processes.

[0265] Step 3:

[0266] The server analyzes the user's past behavior history and engagement data to calculate the optimal posting time. The input for this step is access data related to past posts, and the output is a suggestion of the optimal time slot. The server uses analytical software to statistically analyze the differences in engagement based on posting timing and reports the derived data to the user.

[0267] Step 4:

[0268] The server analyzes sentiment from posts on information platforms and classifies the emotions they express. The input is recently posted comments and feedback, and the output is whether the content is positive, negative, or neutral. Here, the server uses natural language processing techniques to analyze keywords and context within the text and calculate a sentiment score.

[0269] Step 5:

[0270] The server is responsible for optimizing visual content, analyzing still images and videos to improve their quality. The input for this step is image and video data uploaded by the user, and the output is an improved version with automatically adjusted brightness and contrast. The server utilizes image processing libraries and applies histogram equalization and color correction algorithms.

[0271] Step 6:

[0272] The terminal receives inquiries from the operator in real time and provides automated responses. The input consists of the operator's questions and requests, and the output is a database-based answer. The terminal accesses the database on the server, searches for the most appropriate answer from a pre-configured set of questions and answers, and presents it.

[0273] (Application Example 1)

[0274] 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."

[0275] Modern advertising strategies require effectively reaching target audiences, optimizing visual elements, and maximizing ad effectiveness. Real-time user interaction and results analysis, along with incorporating feedback into future strategies, are also crucial. However, there is a lack of systems to efficiently manage these processes.

[0276] 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.

[0277] In this invention, the server includes means for automatically generating advertising text from input information using natural language processing, means for analyzing past user behavior information to identify the optimal delivery time, and means for analyzing the effectiveness of the delivered advertising campaign and providing feedback for strategic improvement. This enables the planning and execution of efficient and effective advertising strategies.

[0278] "Natural language processing" is a technology that uses computers to analyze and understand human language.

[0279] "Inputted information" refers to data and instructions received from the user.

[0280] "Advertising text" refers to text created for the purpose of promoting a product or service.

[0281] "User behavior information" refers to data about a user's past behavioral history and trends.

[0282] "Delivery time" refers to the optimal time to publish or send advertising content.

[0283] "Visual elements" are the elements contained in images and videos, and are components that appeal to people's vision.

[0284] The "information processing means" is a mechanical or programmatic method for receiving data and performing processing based on it.

[0285] The "effect of an advertising campaign" refers to the impact or results that a promotional activity has on the audience.

[0286] The "feedback for strategic improvement" refers to the improvement points and advice provided by analyzing the results of the implemented advertisements in order to utilize them in the next campaign.

[0287] The system for implementing this invention has a server-centered structure. First, the server analyzes the information input by the user using natural language processing algorithms. As specific software, natural language processing is performed using TensorFlow or PyTorch, and the GPT model of OpenAI is utilized to automatically generate advertising text. The text generated based on the user's instructions and product information is used as part of an advertising campaign.

[0288] Next, the server analyzes the user's past behavior history. In this process, data mining techniques are used to grasp the user's behavior information and trends, and to identify the optimal delivery time. A machine learning library using Python is applied to this data analysis.

[0289] Furthermore, the terminal receives inquiries from the user in real time and refers to a database preset as the information processing means. Thereby, it can immediately respond to the user's questions. As an example, when the user inquires about the details of an advertising campaign, the server quickly retrieves the corresponding information from the database and provides an appropriate answer.

[0290] As a concrete example, consider a marketing campaign for a new sneaker. In this case, the server generates an advertising tagline based on information such as "We want to promote sneakers featuring the latest design and performance." It uses a prompt message such as, "Suggest an effective ad copy and posting time based on the new product launch information." This supports campaign deployment at appropriate times for the target audience of young people.

[0291] This configuration allows advertising strategies to be implemented efficiently and effectively while maintaining consistency.

[0292] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0293] Step 1:

[0294] The server receives advertising campaign information entered by users. This input includes information about product features and target audience. The server analyzes this data using natural language processing algorithms to extract features necessary for generating advertising text. In this process, TensorFlow and GPT models are used to process the text data.

[0295] Step 2:

[0296] The server analyzes collected data by referencing past user behavior history. Input data includes records of past advertising campaigns and user responses. Using a machine learning library based on Python, the server predicts the optimal delivery time based on past trends and generates this as output. This result is used to optimize campaign schedules.

[0297] Step 3:

[0298] The terminal receives user inquiries in real time. Users input questions about specific advertising campaigns into the terminal. The terminal uses a pre-configured database for information processing, instantly retrieving the appropriate answer. This process is performed using a database management system and output as a response to the user.

[0299] Step 4:

[0300] The server integrates generated ad text and delivery time information to optimize ad campaign planning. Input includes past campaign results and newly generated ad content. The server then re-evaluates the overall ad strategy and outputs feedback for the next campaign. Based on this feedback, users can refine their next ad strategy.

[0301] Step 5:

[0302] Users review the feedback and new advertising strategies provided by the server and then execute new campaigns based on that. The input is the feedback information from the server, and the output is the actual advertising execution in the market. Through this process, the effectiveness of the advertising is evaluated by the user and reflected in the strategy.

[0303] 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.

[0304] This invention is a social media management system utilizing AI technology, providing advanced marketing support by combining natural language processing, user behavior analysis, and an emotion engine. The core of the system includes an analysis and generation engine installed on the server, which enables content generation, user emotion recognition, and the provision of optimal posting timing.

[0305] The server first receives the brand information and message theme input by the user and performs basic content generation using natural language processing. In this process, an emotion engine is used in combination to analyze the user's emotional state. The emotion engine analyzes text data and voice data to identify the user's mood. Based on this, it automatically adjusts the tone and style of the generated content to provide a message that best matches the user's intention.

[0306] Furthermore, the server calculates the optimal posting time by analyzing past user behavior data and presents a posting schedule to the user to maximize engagement. The server also utilizes the feedback of the emotion engine in this process to achieve a more personalized strategy.

[0307] Regarding image and video analysis, the server identifies the objects in visual content and automatically adjusts the brightness and contrast to enhance the visual appeal. This function is particularly effective in advertising campaigns and branding.

[0308] The terminal quickly receives the user's inquiries, generates appropriate answers from the database accumulated by the server, and provides them to the user in real time. Through such a process, enterprises can improve the efficiency of customer service.

[0309] As a specific example, when a certain enterprise conducts marketing activities for a new product, the server immediately generates advertising copy based on the product characteristics and market targets provided by the user. The emotion engine selects a positive tone according to the purpose of the campaign and provides a message considering the emotional reaction of the recipient. When the user approves this content, it is posted at the optimal timing. Thereby, the enterprise can efficiently convey the brand value and reach the appropriate customer segments.

[0310] The following describes the processing flow.

[0311] Step 1:

[0312] The user inputs data about brand information, target audience, and message tone into the system. The server receives this input data and activates a natural language processing algorithm.

[0313] Step 2:

[0314] The server uses natural language processing to generate basic content based on the input data. It then automatically verifies whether the generated text aligns with the company's messaging strategy.

[0315] Step 3:

[0316] The server activates an emotion engine, analyzing data provided by the user and past interactions to identify the user's emotional state. Based on this analysis, it optimizes the tone and style of the content it generates.

[0317] Step 4:

[0318] The server analyzes past user behavior data to calculate the optimal posting time that maximizes engagement. Based on this information, it presents a recommended posting schedule to the user.

[0319] Step 5:

[0320] The server analyzes image and video data and identifies objects within it. It also automatically adjusts image brightness and contrast to improve the quality of the visual content.

[0321] Step 6:

[0322] The terminal immediately receives user inquiries and transmits them to the server in real time. The server retrieves the appropriate information from the database and quickly provides the user with an answer through the terminal.

[0323] Step 7:

[0324] After all processing is complete, the user reviews and modifies the plan and content provided by the server and posts to social media at what they deem the optimal time.

[0325] (Example 2)

[0326] 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".

[0327] In today's social media landscape, it's crucial to effectively create personalized marketing content based on user-provided information and deliver it at the right time. However, traditional systems struggle to adequately reflect users' emotional states and behavioral data, making it difficult to optimize content generation and delivery schedules, which hinders engagement.

[0328] 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.

[0329] In this invention, the server includes means for automatically generating content using natural language processing with a generation AI model based on information input from the user, means for analyzing the emotional state of the input data using an emotion engine and adjusting the tone of the content, and means for analyzing past user behavior data to identify the optimal posting timing and present a schedule. This enables the creation of content customized to the user's needs and delivery at the appropriate time.

[0330] A "generative AI model" refers to an algorithm that automatically generates text and other content based on information provided by the user.

[0331] "Natural language processing" refers to the process of analyzing input text and generating appropriate output using technologies that enable computers to understand, generate, and manipulate human language.

[0332] An "emotion engine" refers to a technology that analyzes the user's emotional state and emotional nuances from input data, and adjusts the tone and style of content based on that analysis.

[0333] "User behavior data" refers to data such as users' past activities and engagement patterns on social media, and this data is used to analyze and determine the optimal timing for posting.

[0334] "Visual elements" refer to the constituent elements included in visual content such as images and videos, and optimizing these elements improves the appeal of the information.

[0335] A "response database" refers to a dataset containing a pre-prepared list of answers used to generate appropriate responses to user inquiries.

[0336] This invention provides a method for supporting marketing by combining natural language processing, user behavior analysis, and an emotion engine through a social media management system that utilizes AI technology.

[0337] The server first receives brand information and message themes entered by the user, and then uses a generative AI model to generate content using natural language processing technology. This generative AI model uses text generation algorithms such as GPT.

[0338] Next, the server uses an emotion engine to analyze the emotional state of the input data and adjust the tone of the generated content. The emotion engine identifies emotional nuances from text and audio data and optimizes the content accordingly.

[0339] The server further analyzes past user behavior data to calculate the optimal posting timing to maximize engagement. This data analysis uses machine learning algorithms and takes into account the user's social media activity patterns.

[0340] In addition, the server analyzes image and video content, identifying the visual elements it contains. By automatically adjusting brightness and contrast to enhance visual appeal, it improves the effectiveness of advertisements and branding.

[0341] The terminal plays the role of immediately receiving user inquiries. It can automatically generate appropriate responses from information stored in the server's database and provide them to the user in real time. This allows users to receive efficient support from the company.

[0342] As a concrete example, when a company launches a marketing campaign for a new product, the user inputs information about the product's characteristics and target market as prompts. If the prompt is something like, "Create advertising copy for a new eco-friendly product. The target audience is people in their 20s and 30s who are interested in environmental issues. Use the emotion engine to adjust the message to a positive tone and calculate the optimal posting time," the server will immediately generate marketing copy based on this information and deliver it on an optimized schedule.

[0343] This system enables users to effectively communicate their brand and product information and maximize their reach to their target audience.

[0344] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0345] Step 1:

[0346] The user inputs a prompt message into the server, which includes brand information and a message theme. This prompt message serves as the basis for content generation using a generative AI model. Based on the input information, the server uses natural language processing techniques to generate text. The generated content forms the basis of the message.

[0347] Step 2:

[0348] The server passes the generated content to the emotion engine, which performs sentiment analysis based on the user's intent. The input is the previously generated content, and the output is content optimized for emotional tone and style. Text and audio data are analyzed, and the tone of the message is adjusted based on the desired emotion.

[0349] Step 3:

[0350] The server receives historical user behavior data as input and uses statistical analysis and machine learning algorithms to calculate the optimal posting timing. In this process, it considers the user's activity patterns and engagement data on social media and outputs the optimal posting schedule. As a result, a timeframe for achieving maximum engagement is provided.

[0351] Step 4:

[0352] The server receives image and video data provided by the user as input and performs automatic analysis of its visual elements. This includes adjusting brightness and contrast, resulting in optimized visual content as output. Improvements through visual analysis maximize the visual appeal of the content.

[0353] Step 5:

[0354] The user reviews the generated final content and proposed schedule, makes any necessary revisions, and approves the content. This allows the server to automatically post the content according to the specified schedule. The system is then adjusted to ensure the content is delivered at the optimal time.

[0355] Step 6:

[0356] The terminal receives inquiries from users in real time, and the server generates and outputs appropriate responses from a pre-configured response database. By providing these responses to the user, the terminal enables rapid communication. This allows users to receive feedback and information immediately.

[0357] (Application Example 2)

[0358] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0359] In social media marketing, there is a need to create content that attracts user interest, deliver messages that resonate with user emotions, and optimize posting timing to effectively promote engagement. However, traditional methods only consider these elements individually, making it difficult to achieve a comprehensive and efficient marketing strategy.

[0360] 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.

[0361] In this invention, the server includes means for automatically generating content from input data using natural language processing, means for identifying the optimal posting time by analyzing past user behavior data, and means for analyzing posts on social media and classifying sentiment. This enables the execution of an effective marketing strategy.

[0362] "Natural language processing" is a technology that uses computers to understand human language and automatically generate or analyze it.

[0363] "Automatic content generation" refers to a process where a program automatically creates text and media based on input data.

[0364] "User behavior data" refers to the history of actions and choices taken by users when using a service.

[0365] "Posting time optimization" is a technique that calculates and identifies the optimal time to post information in order to maximize user engagement.

[0366] "Sentiment analysis" is the process of identifying and classifying a user's emotions from text or audio.

[0367] "Tone adjustment" is the process of modifying the style and expression of a message or content to make it more appropriate for its purpose.

[0368] "Machine learning" is a technology that uses algorithms to allow computers to analyze data and learn patterns on their own.

[0369] "Image processing" is a technique that uses computers to analyze images and modify or improve their characteristics as needed.

[0370] "Engagement" is a term that describes the degree of user engagement with posts on social media.

[0371] To implement this invention, the server is equipped with a program that uses natural language processing technology to convert input data into content. This program automatically generates advertising copy and other content using a generative AI model based on brand information and messages entered by the user. The server uses spaCy, a Python natural language processing library, to perform text analysis and generation.

[0372] Furthermore, the device collects user behavior data and provides a function to estimate the optimal posting time based on that history. This utilizes the machine learning library scikit-learn to analyze past posting data and engagement data to calculate the appropriate timing.

[0373] The sentiment engine is also implemented on the server side, using the TextBlob library to perform sentiment analysis on text and identify the user's emotional state. This allows the server to adjust the tone of the content to suit the user's intent and situation.

[0374] For image and video analysis, the server uses OpenCV to optimize visual content. This enhances the visual appeal of advertisements and other content by automatically adjusting the brightness and contrast of images.

[0375] As a concrete example, when a coffee shop advertises a new seasonal beverage, the system can generate advertising copy promoting "a new drink that lets you enjoy the scents and flavors of autumn" using CAMP. The system automatically adjusts the autumn foliage scene as visual content, providing an advertisement with visual appeal. For example, by inputting instructions such as "Generate an advertisement promoting a new autumn-only product" into the server's AI model, it is possible to generate appropriate content.

[0376] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0377] Step 1:

[0378] The server receives brand information and message content provided by the user. Using this input data, it performs basic text analysis using a natural language processing library (spaCy). Based on the analysis results, a generative AI model generates advertising copy.

[0379] Step 2:

[0380] The generated ad copy is analyzed by an emotion engine on the server. The emotion engine uses TextBlob to analyze the sentiment within the text and adjust the tone as needed. This process ensures that emotionally appropriate content that matches the user's intent is output.

[0381] Step 3:

[0382] The device collects past user behavior data and analyzes the optimal posting time based on the accumulated data. This analysis uses scikit-learn to apply machine learning algorithms. This calculates the posting timing that maximizes engagement.

[0383] Step 4:

[0384] The server uses an image processing library (OpenCV) to analyze the visual elements contained in the content. By automatically adjusting the brightness and contrast of images and videos, it outputs content with improved visual appeal.

[0385] Step 5:

[0386] Once the user reviews and approves this content, it will be automatically posted at the optimal time. This posting timing is determined based on the data calculated in step 3.

[0387] 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.

[0388] 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.

[0389] 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.

[0390] [Third Embodiment]

[0391] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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".

[0403] The AI ​​social media manager system of the present invention consists of a server, a terminal, and a user. The server has the ability to automatically generate appropriate content from input data using a natural language processing algorithm and to create posts that conform to the brand strategy specified by the user. For example, based on information about a new product announcement, the server generates a caption that emphasizes the characteristics and benefits of the product.

[0404] By analyzing user behavior data, the server identifies the optimal posting time for the highest engagement and suggests a schedule to users. This allows companies to effectively reach their target audience.

[0405] Furthermore, the server analyzes brand-related posts on social media and categorizes sentiment. This process allows for the rapid detection of negative reactions, enabling users to take appropriate responses based on the situation.

[0406] Based on users' past behavior, the server recommends personalized content to support more effective marketing activities. In addition, image and video recognition algorithms automatically optimize visual content, enhancing the delivery of messages to target audiences.

[0407] The terminal receives user instructions and uses data from the server to provide real-time automated responses. For example, when a user inquires about a product, the terminal can search for the relevant information in the database and provide an answer immediately.

[0408] This system allows users to streamline the management of multiple social media platforms, enabling consistent branding and an optimal approach to their target audience.

[0409] The following describes the processing flow.

[0410] Step 1:

[0411] The user inputs brand information and target audience data. The server receives this data and begins automatically generating appropriate content using natural language processing.

[0412] Step 2:

[0413] The server analyzes the generated content and identifies the optimal posting time based on user behavior data. Based on this information, the server creates a posting schedule and proposes it to the user.

[0414] Step 3:

[0415] The server analyzes brand-related posting data collected from social media, performs sentiment analysis, and categorizes emotions. If negative reactions are detected, the server sends an alert to the user.

[0416] Step 4:

[0417] The server generates personalized content based on the user's past behavior history and provides the user with a list of recommended content.

[0418] Step 5:

[0419] When image and video data are uploaded, the server recognizes them and optimizes their visual attributes (brightness, contrast, etc.).

[0420] Step 6:

[0421] The terminal receives user inquiries in real time and searches for relevant information in the database provided by the server. The terminal then generates an automated response and sends the answer to the user.

[0422] (Example 1)

[0423] 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."

[0424] In today's information media environment, businesses and individuals are required to efficiently manage large-scale information activities. However, creating information, disseminating it at the optimal time, analyzing received information and its sentiment, and providing personalized information to each individual are all challenging tasks, necessitating an effective management system. Therefore, there is a need for technological means to simultaneously achieve automation and optimization of information operations.

[0425] 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.

[0426] In this invention, the server includes means for automatically generating information from input information using natural language processing, means for analyzing past operator behavior to identify the optimal activity time, and means for analyzing posts on information media and classifying emotions. This enables large-scale automation and individual optimization of information operations.

[0427] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0428] "Automatic information generation" is a process in which a machine automatically constructs new information based on the input information.

[0429] "User behavior" refers to the patterns and history of user actions when using a system, and is data that is useful for system improvement and individual optimization.

[0430] "Optimal activity time" refers to the time period selected based on analysis to maximize the effectiveness of information dissemination.

[0431] An "information medium" is any platform or channel used to transmit, share, or store information.

[0432] "Emotional classification" is the process of categorizing the emotions contained in information or text into positive, negative, neutral, and so on.

[0433] A "still image" refers to a visual representation or photograph that is not moving, and is a form of visual data.

[0434] A "video" is a form of media that expresses movement by having a series of still images play in sequence over time.

[0435] "Visual information optimization" is the process of using algorithms to modify and improve images and videos in order to enhance their appearance and effect.

[0436] "Automatic response to inquiries" refers to a function where a system mechanically provides answers to questions and requests from users based on pre-configured information.

[0437] This system is designed to allow operators to efficiently manage their activities on information media. The system primarily consists of a server, terminals, and operators. The server uses natural language processing algorithms to automatically generate new content based on information provided by the operators. For example, the server uses a generative AI model. Specifically, it leverages widely available generative AI technologies to generate text that highlights product characteristics.

[0438] In addition, the server analyzes past user behavior to identify the optimal posting time. Digital analytics tools and statistical software are used for data analysis. This allows users to post information during times of high engagement, increasing efficiency.

[0439] Furthermore, the server analyzes posts on the information platform and classifies the sentiment (emotions) expressed. This allows for the rapid detection of negative reactions, enabling operators to quickly respond to situations requiring immediate attention. Natural language processing technology is used to classify each post as positive, negative, or neutral.

[0440] In optimizing visual information, the server analyzes images and videos to make adjustments that maintain an optimal appearance. It uses common image processing libraries and visual algorithms to improve visual elements.

[0441] The terminal receives inquiries from the operator and automatically responds based on information provided by the server. For example, the terminal can instantly provide the best answer from a database of pre-configured questions about the product.

[0442] For example, if an operator wants to promote a new product, "EcoPhone," this system can be used to automatically generate posts that effectively highlight the product's features and benefits. Furthermore, if the operator enters a prompt such as, "EcoPhone is made with the latest technology and uses environmentally friendly materials. Please generate a social media post based on this," the AI ​​model will generate a creative message on their behalf.

[0443] This system enables operators to deliver consistent messaging and effectively reach their targets.

[0444] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0445] Step 1:

[0446] The server receives brand strategy and product information provided by the operator and generates prompt messages based on this information. This input includes product characteristics, target audience information, and the purpose of the post. Specifically, the server retrieves product information from the database and creates prompt messages in a format that is easy for the generating AI model to understand.

[0447] Step 2:

[0448] The server inputs prompt text into a generative AI model, which automatically generates content in natural language. Based on the input prompt text, the generative AI model outputs post content that highlights the product's features. The AI ​​model is hosted on the server, and processing takes place on the internal network. Specifically, the generated text is saved as a temporary file and used in subsequent processes.

[0449] Step 3:

[0450] The server analyzes the user's past behavior history and engagement data to calculate the optimal posting time. The input for this step is access data related to past posts, and the output is a suggestion of the optimal time slot. The server uses analytical software to statistically analyze the differences in engagement based on posting timing and reports the derived data to the user.

[0451] Step 4:

[0452] The server analyzes sentiment from posts on information platforms and classifies the emotions they express. The input is recently posted comments and feedback, and the output is whether the content is positive, negative, or neutral. Here, the server uses natural language processing techniques to analyze keywords and context within the text and calculate a sentiment score.

[0453] Step 5:

[0454] The server is responsible for optimizing visual content, analyzing still images and videos to improve their quality. The input for this step is image and video data uploaded by the user, and the output is an improved version with automatically adjusted brightness and contrast. The server utilizes image processing libraries and applies histogram equalization and color correction algorithms.

[0455] Step 6:

[0456] The terminal receives inquiries from the operator in real time and provides automated responses. The input consists of the operator's questions and requests, and the output is a database-based answer. The terminal accesses the database on the server, searches for the most appropriate answer from a pre-configured set of questions and answers, and presents it.

[0457] (Application Example 1)

[0458] 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."

[0459] Modern advertising strategies require effectively reaching target audiences, optimizing visual elements, and maximizing ad effectiveness. Real-time user interaction and results analysis, along with incorporating feedback into future strategies, are also crucial. However, there is a lack of systems to efficiently manage these processes.

[0460] 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.

[0461] In this invention, the server includes means for automatically generating advertising text from input information using natural language processing, means for analyzing past user behavior information to identify the optimal delivery time, and means for analyzing the effectiveness of the delivered advertising campaign and providing feedback for strategic improvement. This enables the planning and execution of efficient and effective advertising strategies.

[0462] "Natural language processing" is a technology that uses computers to analyze and understand human language.

[0463] "Inputted information" refers to data and instructions received from the user.

[0464] "Advertising text" refers to text created for the purpose of promoting a product or service.

[0465] "User behavior information" refers to data about a user's past behavioral history and trends.

[0466] "Delivery time" refers to the optimal time to publish or send advertising content.

[0467] "Visual elements" are the elements contained in images and videos, and are components that appeal to people's vision.

[0468] "Information processing means" refers to mechanical or programmed methods for receiving data and processing it.

[0469] "The effectiveness of an advertising campaign" refers to the impact and results that promotional activities have on the audience.

[0470] "Feedback for strategic improvement" refers to the analysis of the results of an advertisement and the suggestions and advice provided to help improve future campaigns.

[0471] The system implementing this invention has a server-centric structure. The server first analyzes information input from the user using a natural language processing algorithm. Specifically, the software uses TensorFlow and PyTorch for natural language processing and leverages OpenAI's GPT model to automatically generate advertising text. The text generated based on user instructions and product information is used as part of an advertising campaign.

[0472] Next, the server analyzes the user's past behavior history. During this process, data mining techniques are used to understand user behavior and trends, and to identify the optimal service time. A machine learning library using Python is applied to this data analysis.

[0473] Furthermore, the terminal receives inquiries from users in real time and refers to a pre-configured database as a means of information processing. This allows for immediate responses to user questions. For example, if a user inquires about the details of an advertising campaign, the server quickly retrieves the relevant information from the database and provides an appropriate answer.

[0474] As a concrete example, consider a marketing campaign for a new sneaker. In this case, the server generates an advertising tagline based on information such as "We want to promote sneakers featuring the latest design and performance." It uses a prompt message such as, "Suggest an effective ad copy and posting time based on the new product launch information." This supports campaign deployment at appropriate times for the target audience of young people.

[0475] This configuration allows advertising strategies to be implemented efficiently and effectively while maintaining consistency.

[0476] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0477] Step 1:

[0478] The server receives advertising campaign information entered by users. This input includes information about product features and target audience. The server analyzes this data using natural language processing algorithms to extract features necessary for generating advertising text. In this process, TensorFlow and GPT models are used to process the text data.

[0479] Step 2:

[0480] The server analyzes collected data by referencing past user behavior history. Input data includes records of past advertising campaigns and user responses. Using a machine learning library based on Python, the server predicts the optimal delivery time based on past trends and generates this as output. This result is used to optimize campaign schedules.

[0481] Step 3:

[0482] The terminal receives user inquiries in real time. Users input questions about specific advertising campaigns into the terminal. The terminal uses a pre-configured database for information processing, instantly retrieving the appropriate answer. This process is performed using a database management system and output as a response to the user.

[0483] Step 4:

[0484] The server integrates generated ad text and delivery time information to optimize ad campaign planning. Input includes past campaign results and newly generated ad content. The server then re-evaluates the overall ad strategy and outputs feedback for the next campaign. Based on this feedback, users can refine their next ad strategy.

[0485] Step 5:

[0486] Users review the feedback and new advertising strategies provided by the server and then execute new campaigns based on that. The input is the feedback information from the server, and the output is the actual advertising execution in the market. Through this process, the effectiveness of the advertising is evaluated by the user and reflected in the strategy.

[0487] 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.

[0488] This invention is a social media management system utilizing AI technology, providing advanced marketing support by combining natural language processing, user behavior analysis, and an emotion engine. The core of the system includes an analysis and generation engine installed on the server, which enables content generation, user emotion recognition, and the provision of optimal posting timing.

[0489] The server first receives brand information and message themes entered by the user and generates basic content using natural language processing. During this process, an emotion engine is also used to analyze the user's emotional state. The emotion engine analyzes text and audio data to identify the user's emotions. Based on this, it automatically adjusts the tone and style of the generated content to provide a message that best matches the user's intent.

[0490] Furthermore, the server analyzes past user behavior data to calculate the optimal posting time and presents users with a posting schedule designed to maximize engagement. The server also utilizes feedback from the sentiment engine in this process to achieve a more personalized strategy.

[0491] Regarding image and video analysis, the server identifies objects in visual content and automatically adjusts brightness and contrast to enhance visual appeal. This feature is particularly effective in advertising campaigns and branding.

[0492] The terminal quickly receives user inquiries, generates appropriate answers from the server's database, and provides them to the user in real time. This process allows companies to improve the efficiency of their customer service.

[0493] As a concrete example, when a company conducts marketing activities for a new product, the server instantly generates ad copy based on the characteristics of the product offered and the target market. The emotion engine selects a positive tone according to the campaign's objectives and delivers a message that takes into account the emotional response of the recipient. Once the user approves this content, it is posted at the optimal time. This allows companies to efficiently communicate their brand value and reach the right customer segments.

[0494] The following describes the processing flow.

[0495] Step 1:

[0496] The user inputs data about brand information, target audience, and message tone into the system. The server receives this input data and activates a natural language processing algorithm.

[0497] Step 2:

[0498] The server uses natural language processing to generate basic content based on the input data. It then automatically verifies whether the generated text aligns with the company's messaging strategy.

[0499] Step 3:

[0500] The server activates an emotion engine, analyzing data provided by the user and past interactions to identify the user's emotional state. Based on this analysis, it optimizes the tone and style of the content it generates.

[0501] Step 4:

[0502] The server analyzes past user behavior data to calculate the optimal posting time that maximizes engagement. Based on this information, it presents a recommended posting schedule to the user.

[0503] Step 5:

[0504] The server analyzes image and video data and identifies objects within it. It also automatically adjusts image brightness and contrast to improve the quality of the visual content.

[0505] Step 6:

[0506] The terminal immediately receives user inquiries and transmits them to the server in real time. The server retrieves the appropriate information from the database and quickly provides the user with an answer through the terminal.

[0507] Step 7:

[0508] After all processing is complete, the user reviews and modifies the plan and content provided by the server and posts to social media at what they deem the optimal time.

[0509] (Example 2)

[0510] 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."

[0511] In today's social media landscape, it's crucial to effectively create personalized marketing content based on user-provided information and deliver it at the right time. However, traditional systems struggle to adequately reflect users' emotional states and behavioral data, making it difficult to optimize content generation and delivery schedules, which hinders engagement.

[0512] 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.

[0513] In this invention, the server includes means for automatically generating content using natural language processing with a generation AI model based on information input from the user, means for analyzing the emotional state of the input data using an emotion engine and adjusting the tone of the content, and means for analyzing past user behavior data to identify the optimal posting timing and present a schedule. This enables the creation of content customized to the user's needs and delivery at the appropriate time.

[0514] A "generative AI model" refers to an algorithm that automatically generates text and other content based on information provided by the user.

[0515] "Natural language processing" refers to the process of analyzing input text and generating appropriate output using technologies that enable computers to understand, generate, and manipulate human language.

[0516] An "emotion engine" refers to a technology that analyzes the user's emotional state and emotional nuances from input data, and adjusts the tone and style of content based on that analysis.

[0517] "User behavior data" refers to data such as users' past activities and engagement patterns on social media, and this data is used to analyze and determine the optimal timing for posting.

[0518] "Visual elements" refer to the constituent elements included in visual content such as images and videos, and optimizing these elements improves the appeal of the information.

[0519] A "response database" refers to a dataset containing a pre-prepared list of answers used to generate appropriate responses to user inquiries.

[0520] This invention provides a method for supporting marketing by combining natural language processing, user behavior analysis, and an emotion engine through a social media management system that utilizes AI technology.

[0521] The server first receives brand information and message themes entered by the user, and then uses a generative AI model to generate content using natural language processing technology. This generative AI model uses text generation algorithms such as GPT.

[0522] Next, the server uses an emotion engine to analyze the emotional state of the input data and adjust the tone of the generated content. The emotion engine identifies emotional nuances from text and audio data and optimizes the content accordingly.

[0523] The server further analyzes past user behavior data to calculate the optimal posting timing to maximize engagement. This data analysis uses machine learning algorithms and takes into account the user's social media activity patterns.

[0524] In addition, the server analyzes image and video content, identifying the visual elements it contains. By automatically adjusting brightness and contrast to enhance visual appeal, it improves the effectiveness of advertisements and branding.

[0525] The terminal plays the role of immediately receiving user inquiries. It can automatically generate appropriate responses from information stored in the server's database and provide them to the user in real time. This allows users to receive efficient support from the company.

[0526] As a concrete example, when a company launches a marketing campaign for a new product, the user inputs information about the product's characteristics and target market as prompts. If the prompt is something like, "Create advertising copy for a new eco-friendly product. The target audience is people in their 20s and 30s who are interested in environmental issues. Use the emotion engine to adjust the message to a positive tone and calculate the optimal posting time," the server will immediately generate marketing copy based on this information and deliver it on an optimized schedule.

[0527] This system enables users to effectively communicate their brand and product information and maximize their reach to their target audience.

[0528] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0529] Step 1:

[0530] The user inputs a prompt message into the server, which includes brand information and a message theme. This prompt message serves as the basis for content generation using a generative AI model. Based on the input information, the server uses natural language processing techniques to generate text. The generated content forms the basis of the message.

[0531] Step 2:

[0532] The server passes the generated content to the emotion engine, which performs sentiment analysis based on the user's intent. The input is the previously generated content, and the output is content optimized for emotional tone and style. Text and audio data are analyzed, and the tone of the message is adjusted based on the desired emotion.

[0533] Step 3:

[0534] The server receives historical user behavior data as input and uses statistical analysis and machine learning algorithms to calculate the optimal posting timing. In this process, it considers the user's activity patterns and engagement data on social media and outputs the optimal posting schedule. As a result, a timeframe for achieving maximum engagement is provided.

[0535] Step 4:

[0536] The server receives image and video data provided by the user as input and performs automatic analysis of its visual elements. This includes adjusting brightness and contrast, resulting in optimized visual content as output. Improvements through visual analysis maximize the visual appeal of the content.

[0537] Step 5:

[0538] The user reviews the generated final content and proposed schedule, makes any necessary revisions, and approves the content. This allows the server to automatically post the content according to the specified schedule. The system is then adjusted to ensure the content is delivered at the optimal time.

[0539] Step 6:

[0540] The terminal receives inquiries from users in real time, and the server generates and outputs appropriate responses from a pre-configured response database. By providing these responses to the user, the terminal enables rapid communication. This allows users to receive feedback and information immediately.

[0541] (Application Example 2)

[0542] 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."

[0543] In social media marketing, there is a need to create content that attracts user interest, deliver messages that resonate with user emotions, and optimize posting timing to effectively promote engagement. However, traditional methods only consider these elements individually, making it difficult to achieve a comprehensive and efficient marketing strategy.

[0544] 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.

[0545] In this invention, the server includes means for automatically generating content from input data using natural language processing, means for identifying the optimal posting time by analyzing past user behavior data, and means for analyzing posts on social media and classifying sentiment. This enables the execution of an effective marketing strategy.

[0546] "Natural language processing" is a technology that uses computers to understand human language and automatically generate or analyze it.

[0547] "Automatic content generation" refers to a process where a program automatically creates text and media based on input data.

[0548] "User behavior data" refers to the history of actions and choices taken by users when using a service.

[0549] "Posting time optimization" is a technique that calculates and identifies the optimal time to post information in order to maximize user engagement.

[0550] "Sentiment analysis" is the process of identifying and classifying a user's emotions from text or audio.

[0551] "Tone adjustment" is the process of modifying the style and expression of a message or content to make it more appropriate for its purpose.

[0552] "Machine learning" is a technology that uses algorithms to allow computers to analyze data and learn patterns on their own.

[0553] "Image processing" is a technique that uses computers to analyze images and modify or improve their characteristics as needed.

[0554] "Engagement" is a term that describes the degree of user engagement with posts on social media.

[0555] To implement this invention, the server is equipped with a program that uses natural language processing technology to convert input data into content. This program automatically generates advertising copy and other content using a generative AI model based on brand information and messages entered by the user. The server uses spaCy, a Python natural language processing library, to perform text analysis and generation.

[0556] Furthermore, the device collects user behavior data and provides a function to estimate the optimal posting time based on that history. This utilizes the machine learning library scikit-learn to analyze past posting data and engagement data to calculate the appropriate timing.

[0557] The sentiment engine is also implemented on the server side, using the TextBlob library to perform sentiment analysis on text and identify the user's emotional state. This allows the server to adjust the tone of the content to suit the user's intent and situation.

[0558] For image and video analysis, the server uses OpenCV to optimize visual content. This enhances the visual appeal of advertisements and other content by automatically adjusting the brightness and contrast of images.

[0559] As a concrete example, when a coffee shop advertises a new seasonal beverage, the system can generate advertising copy promoting "a new drink that lets you enjoy the scents and flavors of autumn" using CAMP. The system automatically adjusts the autumn foliage scene as visual content, providing an advertisement with visual appeal. For example, by inputting instructions such as "Generate an advertisement promoting a new autumn-only product" into the server's AI model, it is possible to generate appropriate content.

[0560] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0561] Step 1:

[0562] The server receives brand information and message content provided by the user. Using this input data, it performs basic text analysis using a natural language processing library (spaCy). Based on the analysis results, a generative AI model generates advertising copy.

[0563] Step 2:

[0564] The generated ad copy is analyzed by an emotion engine on the server. The emotion engine uses TextBlob to analyze the sentiment within the text and adjust the tone as needed. This process ensures that emotionally appropriate content that matches the user's intent is output.

[0565] Step 3:

[0566] The device collects past user behavior data and analyzes the optimal posting time based on the accumulated data. This analysis uses scikit-learn to apply machine learning algorithms. This calculates the posting timing that maximizes engagement.

[0567] Step 4:

[0568] The server uses an image processing library (OpenCV) to analyze the visual elements contained in the content. By automatically adjusting the brightness and contrast of images and videos, it outputs content with improved visual appeal.

[0569] Step 5:

[0570] Once the user reviews and approves this content, it will be automatically posted at the optimal time. This posting timing is determined based on the data calculated in step 3.

[0571] 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.

[0572] 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.

[0573] 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.

[0574] [Fourth Embodiment]

[0575] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0576] 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.

[0577] 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).

[0578] 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.

[0579] 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.

[0580] 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).

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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.

[0586] 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.

[0587] 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".

[0588] The AI ​​social media manager system of the present invention consists of a server, a terminal, and a user. The server has the ability to automatically generate appropriate content from input data using a natural language processing algorithm and to create posts that conform to the brand strategy specified by the user. For example, based on information about a new product announcement, the server generates a caption that emphasizes the characteristics and benefits of the product.

[0589] By analyzing user behavior data, the server identifies the optimal posting time for the highest engagement and suggests a schedule to users. This allows companies to effectively reach their target audience.

[0590] Furthermore, the server analyzes brand-related posts on social media and categorizes sentiment. This process allows for the rapid detection of negative reactions, enabling users to take appropriate responses based on the situation.

[0591] Based on users' past behavior, the server recommends personalized content to support more effective marketing activities. In addition, image and video recognition algorithms automatically optimize visual content, enhancing the delivery of messages to target audiences.

[0592] The terminal receives user instructions and uses data from the server to provide real-time automated responses. For example, when a user inquires about a product, the terminal can search for the relevant information in the database and provide an answer immediately.

[0593] This system allows users to streamline the management of multiple social media platforms, enabling consistent branding and an optimal approach to their target audience.

[0594] The following describes the processing flow.

[0595] Step 1:

[0596] The user inputs brand information and target audience data. The server receives this data and begins automatically generating appropriate content using natural language processing.

[0597] Step 2:

[0598] The server analyzes the generated content and identifies the optimal posting time based on user behavior data. Based on this information, the server creates a posting schedule and proposes it to the user.

[0599] Step 3:

[0600] The server analyzes brand-related posting data collected from social media, performs sentiment analysis, and categorizes emotions. If negative reactions are detected, the server sends an alert to the user.

[0601] Step 4:

[0602] The server generates personalized content based on the user's past behavior history and provides the user with a list of recommended content.

[0603] Step 5:

[0604] When image and video data are uploaded, the server recognizes them and optimizes their visual attributes (brightness, contrast, etc.).

[0605] Step 6:

[0606] The terminal receives user inquiries in real time and searches for relevant information in the database provided by the server. The terminal then generates an automated response and sends the answer to the user.

[0607] (Example 1)

[0608] 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".

[0609] In today's information media environment, businesses and individuals are required to efficiently manage large-scale information activities. However, creating information, disseminating it at the optimal time, analyzing received information and its sentiment, and providing personalized information to each individual are all challenging tasks, necessitating an effective management system. Therefore, there is a need for technological means to simultaneously achieve automation and optimization of information operations.

[0610] 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.

[0611] In this invention, the server includes means for automatically generating information from input information using natural language processing, means for analyzing past operator behavior to identify the optimal activity time, and means for analyzing posts on information media and classifying emotions. This enables large-scale automation and individual optimization of information operations.

[0612] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0613] "Automatic information generation" is a process in which a machine automatically constructs new information based on the input information.

[0614] "User behavior" refers to the patterns and history of user actions when using a system, and is data that is useful for system improvement and individual optimization.

[0615] "Optimal activity time" refers to the time period selected based on analysis to maximize the effectiveness of information dissemination.

[0616] An "information medium" is any platform or channel used to transmit, share, or store information.

[0617] "Emotional classification" is the process of categorizing the emotions contained in information or text into positive, negative, neutral, and so on.

[0618] A "still image" refers to a visual representation or photograph that is not moving, and is a form of visual data.

[0619] A "video" is a form of media that expresses movement by having a series of still images play in sequence over time.

[0620] "Visual information optimization" is the process of using algorithms to modify and improve images and videos in order to enhance their appearance and effect.

[0621] "Automatic response to inquiries" refers to a function where a system mechanically provides answers to questions and requests from users based on pre-configured information.

[0622] This system is designed to allow operators to efficiently manage their activities on information media. The system primarily consists of a server, terminals, and operators. The server uses natural language processing algorithms to automatically generate new content based on information provided by the operators. For example, the server uses a generative AI model. Specifically, it leverages widely available generative AI technologies to generate text that highlights product characteristics.

[0623] In addition, the server analyzes past user behavior to identify the optimal posting time. Digital analytics tools and statistical software are used for data analysis. This allows users to post information during times of high engagement, increasing efficiency.

[0624] Furthermore, the server analyzes posts on the information platform and classifies the sentiment (emotions) expressed. This allows for the rapid detection of negative reactions, enabling operators to quickly respond to situations requiring immediate attention. Natural language processing technology is used to classify each post as positive, negative, or neutral.

[0625] In optimizing visual information, the server analyzes images and videos to make adjustments that maintain an optimal appearance. It uses common image processing libraries and visual algorithms to improve visual elements.

[0626] The terminal receives inquiries from the operator and automatically responds based on information provided by the server. For example, the terminal can instantly provide the best answer from a database of pre-configured questions about the product.

[0627] For example, if an operator wants to promote a new product, "EcoPhone," this system can be used to automatically generate posts that effectively highlight the product's features and benefits. Furthermore, if the operator enters a prompt such as, "EcoPhone is made with the latest technology and uses environmentally friendly materials. Please generate a social media post based on this," the AI ​​model will generate a creative message on their behalf.

[0628] This system enables operators to deliver consistent messaging and effectively reach their targets.

[0629] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0630] Step 1:

[0631] The server receives brand strategy and product information provided by the operator and generates prompt messages based on this information. This input includes product characteristics, target audience information, and the purpose of the post. Specifically, the server retrieves product information from the database and creates prompt messages in a format that is easy for the generating AI model to understand.

[0632] Step 2:

[0633] The server inputs prompt text into a generative AI model, which automatically generates content in natural language. Based on the input prompt text, the generative AI model outputs post content that highlights the product's features. The AI ​​model is hosted on the server, and processing takes place on the internal network. Specifically, the generated text is saved as a temporary file and used in subsequent processes.

[0634] Step 3:

[0635] The server analyzes the user's past behavior history and engagement data to calculate the optimal posting time. The input for this step is access data related to past posts, and the output is a suggestion of the optimal time slot. The server uses analytical software to statistically analyze the differences in engagement based on posting timing and reports the derived data to the user.

[0636] Step 4:

[0637] The server analyzes sentiment from posts on information platforms and classifies the emotions they express. The input is recently posted comments and feedback, and the output is whether the content is positive, negative, or neutral. Here, the server uses natural language processing techniques to analyze keywords and context within the text and calculate a sentiment score.

[0638] Step 5:

[0639] The server is responsible for optimizing visual content, analyzing still images and videos to improve their quality. The input for this step is image and video data uploaded by the user, and the output is an improved version with automatically adjusted brightness and contrast. The server utilizes image processing libraries and applies histogram equalization and color correction algorithms.

[0640] Step 6:

[0641] The terminal receives inquiries from the operator in real time and provides automated responses. The input consists of the operator's questions and requests, and the output is a database-based answer. The terminal accesses the database on the server, searches for the most appropriate answer from a pre-configured set of questions and answers, and presents it.

[0642] (Application Example 1)

[0643] 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".

[0644] Modern advertising strategies require effectively reaching target audiences, optimizing visual elements, and maximizing ad effectiveness. Real-time user interaction and results analysis, along with incorporating feedback into future strategies, are also crucial. However, there is a lack of systems to efficiently manage these processes.

[0645] 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.

[0646] In this invention, the server includes means for automatically generating advertising text from input information using natural language processing, means for analyzing past user behavior information to identify the optimal delivery time, and means for analyzing the effectiveness of the delivered advertising campaign and providing feedback for strategic improvement. This enables the planning and execution of efficient and effective advertising strategies.

[0647] "Natural language processing" is a technology that uses computers to analyze and understand human language.

[0648] "Inputted information" refers to data and instructions received from the user.

[0649] "Advertising text" refers to text created for the purpose of promoting a product or service.

[0650] "User behavior information" refers to data about a user's past behavioral history and trends.

[0651] "Delivery time" refers to the optimal time to publish or send advertising content.

[0652] "Visual elements" are the elements contained in images and videos, and are components that appeal to people's vision.

[0653] "Information processing means" refers to mechanical or programmed methods for receiving data and processing it.

[0654] "The effectiveness of an advertising campaign" refers to the impact and results that promotional activities have on the audience.

[0655] "Feedback for strategic improvement" refers to the analysis of the results of an advertisement and the suggestions and advice provided to help improve future campaigns.

[0656] The system implementing this invention has a server-centric structure. The server first analyzes information input from the user using a natural language processing algorithm. Specifically, the software uses TensorFlow and PyTorch for natural language processing and leverages OpenAI's GPT model to automatically generate advertising text. The text generated based on user instructions and product information is used as part of an advertising campaign.

[0657] Next, the server analyzes the user's past behavior history. During this process, data mining techniques are used to understand user behavior and trends, and to identify the optimal service time. A machine learning library using Python is applied to this data analysis.

[0658] Furthermore, the terminal receives inquiries from users in real time and refers to a pre-configured database as a means of information processing. This allows for immediate responses to user questions. For example, if a user inquires about the details of an advertising campaign, the server quickly retrieves the relevant information from the database and provides an appropriate answer.

[0659] As a concrete example, consider a marketing campaign for a new sneaker. In this case, the server generates an advertising tagline based on information such as "We want to promote sneakers featuring the latest design and performance." It uses a prompt message such as, "Suggest an effective ad copy and posting time based on the new product launch information." This supports campaign deployment at appropriate times for the target audience of young people.

[0660] This configuration allows advertising strategies to be implemented efficiently and effectively while maintaining consistency.

[0661] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0662] Step 1:

[0663] The server receives advertising campaign information entered by users. This input includes information about product features and target audience. The server analyzes this data using natural language processing algorithms to extract features necessary for generating advertising text. In this process, TensorFlow and GPT models are used to process the text data.

[0664] Step 2:

[0665] The server analyzes collected data by referencing past user behavior history. Input data includes records of past advertising campaigns and user responses. Using a machine learning library based on Python, the server predicts the optimal delivery time based on past trends and generates this as output. This result is used to optimize campaign schedules.

[0666] Step 3:

[0667] The terminal receives user inquiries in real time. Users input questions about specific advertising campaigns into the terminal. The terminal uses a pre-configured database for information processing, instantly retrieving the appropriate answer. This process is performed using a database management system and output as a response to the user.

[0668] Step 4:

[0669] The server integrates generated ad text and delivery time information to optimize ad campaign planning. Input includes past campaign results and newly generated ad content. The server then re-evaluates the overall ad strategy and outputs feedback for the next campaign. Based on this feedback, users can refine their next ad strategy.

[0670] Step 5:

[0671] Users review the feedback and new advertising strategies provided by the server and then execute new campaigns based on that. The input is the feedback information from the server, and the output is the actual advertising execution in the market. Through this process, the effectiveness of the advertising is evaluated by the user and reflected in the strategy.

[0672] 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.

[0673] This invention is a social media management system utilizing AI technology, providing advanced marketing support by combining natural language processing, user behavior analysis, and an emotion engine. The core of the system includes an analysis and generation engine installed on the server, which enables content generation, user emotion recognition, and the provision of optimal posting timing.

[0674] The server first receives brand information and message themes entered by the user and generates basic content using natural language processing. During this process, an emotion engine is also used to analyze the user's emotional state. The emotion engine analyzes text and audio data to identify the user's emotions. Based on this, it automatically adjusts the tone and style of the generated content to provide a message that best matches the user's intent.

[0675] Furthermore, the server analyzes past user behavior data to calculate the optimal posting time and presents users with a posting schedule designed to maximize engagement. The server also utilizes feedback from the sentiment engine in this process to achieve a more personalized strategy.

[0676] Regarding image and video analysis, the server identifies objects in visual content and automatically adjusts brightness and contrast to enhance visual appeal. This feature is particularly effective in advertising campaigns and branding.

[0677] The terminal quickly receives user inquiries, generates appropriate answers from the server's database, and provides them to the user in real time. This process allows companies to improve the efficiency of their customer service.

[0678] As a concrete example, when a company conducts marketing activities for a new product, the server instantly generates ad copy based on the characteristics of the product offered and the target market. The emotion engine selects a positive tone according to the campaign's objectives and delivers a message that takes into account the emotional response of the recipient. Once the user approves this content, it is posted at the optimal time. This allows companies to efficiently communicate their brand value and reach the right customer segments.

[0679] The following describes the processing flow.

[0680] Step 1:

[0681] The user inputs data about brand information, target audience, and message tone into the system. The server receives this input data and activates a natural language processing algorithm.

[0682] Step 2:

[0683] The server uses natural language processing to generate basic content based on the input data. It then automatically verifies whether the generated text aligns with the company's messaging strategy.

[0684] Step 3:

[0685] The server activates an emotion engine, analyzing data provided by the user and past interactions to identify the user's emotional state. Based on this analysis, it optimizes the tone and style of the content it generates.

[0686] Step 4:

[0687] The server analyzes past user behavior data to calculate the optimal posting time that maximizes engagement. Based on this information, it presents a recommended posting schedule to the user.

[0688] Step 5:

[0689] The server analyzes image and video data and identifies objects within it. It also automatically adjusts image brightness and contrast to improve the quality of the visual content.

[0690] Step 6:

[0691] The terminal immediately receives user inquiries and transmits them to the server in real time. The server retrieves the appropriate information from the database and quickly provides the user with an answer through the terminal.

[0692] Step 7:

[0693] After all processing is complete, the user reviews and modifies the plan and content provided by the server and posts to social media at what they deem the optimal time.

[0694] (Example 2)

[0695] 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".

[0696] In today's social media landscape, it's crucial to effectively create personalized marketing content based on user-provided information and deliver it at the right time. However, traditional systems struggle to adequately reflect users' emotional states and behavioral data, making it difficult to optimize content generation and delivery schedules, which hinders engagement.

[0697] 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.

[0698] In this invention, the server includes means for automatically generating content using natural language processing with a generation AI model based on information input from the user, means for analyzing the emotional state of the input data using an emotion engine and adjusting the tone of the content, and means for analyzing past user behavior data to identify the optimal posting timing and present a schedule. This enables the creation of content customized to the user's needs and delivery at the appropriate time.

[0699] A "generative AI model" refers to an algorithm that automatically generates text and other content based on information provided by the user.

[0700] "Natural language processing" refers to the process of analyzing input text and generating appropriate output using technologies that enable computers to understand, generate, and manipulate human language.

[0701] An "emotion engine" refers to a technology that analyzes the user's emotional state and emotional nuances from input data, and adjusts the tone and style of content based on that analysis.

[0702] "User behavior data" refers to data such as users' past activities and engagement patterns on social media, and this data is used to analyze and determine the optimal timing for posting.

[0703] "Visual elements" refer to the constituent elements included in visual content such as images and videos, and optimizing these elements improves the appeal of the information.

[0704] A "response database" refers to a dataset containing a pre-prepared list of answers used to generate appropriate responses to user inquiries.

[0705] This invention provides a method for supporting marketing by combining natural language processing, user behavior analysis, and an emotion engine through a social media management system that utilizes AI technology.

[0706] The server first receives brand information and message themes entered by the user, and then uses a generative AI model to generate content using natural language processing technology. This generative AI model uses text generation algorithms such as GPT.

[0707] Next, the server uses an emotion engine to analyze the emotional state of the input data and adjust the tone of the generated content. The emotion engine identifies emotional nuances from text and audio data and optimizes the content accordingly.

[0708] The server further analyzes past user behavior data to calculate the optimal posting timing to maximize engagement. This data analysis uses machine learning algorithms and takes into account the user's social media activity patterns.

[0709] In addition, the server analyzes image and video content, identifying the visual elements it contains. By automatically adjusting brightness and contrast to enhance visual appeal, it improves the effectiveness of advertisements and branding.

[0710] The terminal plays the role of immediately receiving user inquiries. It can automatically generate appropriate responses from information stored in the server's database and provide them to the user in real time. This allows users to receive efficient support from the company.

[0711] As a concrete example, when a company launches a marketing campaign for a new product, the user inputs information about the product's characteristics and target market as prompts. If the prompt is something like, "Create advertising copy for a new eco-friendly product. The target audience is people in their 20s and 30s who are interested in environmental issues. Use the emotion engine to adjust the message to a positive tone and calculate the optimal posting time," the server will immediately generate marketing copy based on this information and deliver it on an optimized schedule.

[0712] This system enables users to effectively communicate their brand and product information and maximize their reach to their target audience.

[0713] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0714] Step 1:

[0715] The user inputs a prompt message into the server, which includes brand information and a message theme. This prompt message serves as the basis for content generation using a generative AI model. Based on the input information, the server uses natural language processing techniques to generate text. The generated content forms the basis of the message.

[0716] Step 2:

[0717] The server passes the generated content to the emotion engine, which performs sentiment analysis based on the user's intent. The input is the previously generated content, and the output is content optimized for emotional tone and style. Text and audio data are analyzed, and the tone of the message is adjusted based on the desired emotion.

[0718] Step 3:

[0719] The server receives historical user behavior data as input and uses statistical analysis and machine learning algorithms to calculate the optimal posting timing. In this process, it considers the user's activity patterns and engagement data on social media and outputs the optimal posting schedule. As a result, a timeframe for achieving maximum engagement is provided.

[0720] Step 4:

[0721] The server receives image and video data provided by the user as input and performs automatic analysis of its visual elements. This includes adjusting brightness and contrast, resulting in optimized visual content as output. Improvements through visual analysis maximize the visual appeal of the content.

[0722] Step 5:

[0723] The user reviews the generated final content and proposed schedule, makes any necessary revisions, and approves the content. This allows the server to automatically post the content according to the specified schedule. The system is then adjusted to ensure the content is delivered at the optimal time.

[0724] Step 6:

[0725] The terminal receives inquiries from users in real time, and the server generates and outputs appropriate responses from a pre-configured response database. By providing these responses to the user, the terminal enables rapid communication. This allows users to receive feedback and information immediately.

[0726] (Application Example 2)

[0727] 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".

[0728] In social media marketing, there is a need to create content that attracts user interest, deliver messages that resonate with user emotions, and optimize posting timing to effectively promote engagement. However, traditional methods only consider these elements individually, making it difficult to achieve a comprehensive and efficient marketing strategy.

[0729] 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.

[0730] In this invention, the server includes means for automatically generating content from input data using natural language processing, means for identifying the optimal posting time by analyzing past user behavior data, and means for analyzing posts on social media and classifying sentiment. This enables the execution of an effective marketing strategy.

[0731] "Natural language processing" is a technology that uses computers to understand human language and automatically generate or analyze it.

[0732] "Automatic content generation" refers to a process where a program automatically creates text and media based on input data.

[0733] "User behavior data" refers to the history of actions and choices taken by users when using a service.

[0734] "Posting time optimization" is a technique that calculates and identifies the optimal time to post information in order to maximize user engagement.

[0735] "Sentiment analysis" is the process of identifying and classifying a user's emotions from text or audio.

[0736] "Tone adjustment" is the process of modifying the style and expression of a message or content to make it more appropriate for its purpose.

[0737] "Machine learning" is a technology that uses algorithms to allow computers to analyze data and learn patterns on their own.

[0738] "Image processing" is a technique that uses computers to analyze images and modify or improve their characteristics as needed.

[0739] "Engagement" is a term that describes the degree of user engagement with posts on social media.

[0740] To implement this invention, the server is equipped with a program that uses natural language processing technology to convert input data into content. This program automatically generates advertising copy and other content using a generative AI model based on brand information and messages entered by the user. The server uses spaCy, a Python natural language processing library, to perform text analysis and generation.

[0741] Furthermore, the device collects user behavior data and provides a function to estimate the optimal posting time based on that history. This utilizes the machine learning library scikit-learn to analyze past posting data and engagement data to calculate the appropriate timing.

[0742] The sentiment engine is also implemented on the server side, using the TextBlob library to perform sentiment analysis on text and identify the user's emotional state. This allows the server to adjust the tone of the content to suit the user's intent and situation.

[0743] For image and video analysis, the server uses OpenCV to optimize visual content. This enhances the visual appeal of advertisements and other content by automatically adjusting the brightness and contrast of images.

[0744] As a concrete example, when a coffee shop advertises a new seasonal beverage, the system can generate advertising copy promoting "a new drink that lets you enjoy the scents and flavors of autumn" using CAMP. The system automatically adjusts the autumn foliage scene as visual content, providing an advertisement with visual appeal. For example, by inputting instructions such as "Generate an advertisement promoting a new autumn-only product" into the server's AI model, it is possible to generate appropriate content.

[0745] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0746] Step 1:

[0747] The server receives brand information and message content provided by the user. Using this input data, it performs basic text analysis using a natural language processing library (spaCy). Based on the analysis results, a generative AI model generates advertising copy.

[0748] Step 2:

[0749] The generated ad copy is analyzed by an emotion engine on the server. The emotion engine uses TextBlob to analyze the sentiment within the text and adjust the tone as needed. This process ensures that emotionally appropriate content that matches the user's intent is output.

[0750] Step 3:

[0751] The device collects past user behavior data and analyzes the optimal posting time based on the accumulated data. This analysis uses scikit-learn to apply machine learning algorithms. This calculates the posting timing that maximizes engagement.

[0752] Step 4:

[0753] The server uses an image processing library (OpenCV) to analyze the visual elements contained in the content. By automatically adjusting the brightness and contrast of images and videos, it outputs content with improved visual appeal.

[0754] Step 5:

[0755] Once the user reviews and approves this content, it will be automatically posted at the optimal time. This posting timing is determined based on the data calculated in step 3.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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."

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] The following is further disclosed regarding the embodiments described above.

[0778] (Claim 1)

[0779] A method for automatically generating content from input data using natural language processing,

[0780] A method for identifying the optimal posting time by analyzing past user behavior data,

[0781] A method for analyzing social media posts and classifying emotions,

[0782] A means of individually optimizing content based on the user's past behavior history,

[0783] A means for analyzing images and videos to optimize visual content,

[0784] A machine equipped with a system that automatically responds to user inquiries,

[0785] A system that includes this.

[0786] (Claim 2)

[0787] The system according to claim 1, which optimizes visual content by identifying objects in an image or video and automatically adjusting their brightness or contrast.

[0788] (Claim 3)

[0789] The system according to claim 1, which receives user inquiries in real time and provides appropriate answers from a pre-configured response database.

[0790] "Example 1"

[0791] (Claim 1)

[0792] A means of automatically generating information from input information using natural language processing,

[0793] A means of identifying the optimal activity time by analyzing past operator behavior,

[0794] A method for analyzing posts on information media and classifying emotions,

[0795] A means of individually optimizing information based on the operator's past behavioral history,

[0796] A means for analyzing still images and videos to optimize visual information,

[0797] A processing means that automatically responds to inquiries from the operator,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, which optimizes visual information by identifying a subject in a still image or video and automatically adjusting its brightness or contrast.

[0801] (Claim 3)

[0802] The system according to claim 1, which receives an inquiry from an operator in real time and provides an appropriate answer from pre-configured response information.

[0803] "Application Example 1"

[0804] (Claim 1)

[0805] A method for automatically generating advertising text from input information using natural language processing,

[0806] A method for identifying the optimal service time by analyzing past user behavior data,

[0807] A means of analyzing posts on social media and classifying emotions,

[0808] A means of individually optimizing information based on the user's past behavioral history,

[0809] A means for analyzing video and images to optimize visual elements,

[0810] An information processing system that automatically responds to inquiries from users,

[0811] A means of analyzing the effectiveness of the provided advertising campaigns and providing feedback for strategic improvement,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, which optimizes visual elements by identifying a subject in an image or video and automatically adjusting its brightness or contrast.

[0815] (Claim 3)

[0816] The system according to claim 1, which receives user inquiries in real time and provides appropriate answers from a pre-configured response information database.

[0817] "Example 2 of combining an emotion engine"

[0818] (Claim 1)

[0819] A method for automatically generating content using natural language processing with an AI model based on information input by the user,

[0820] A means of analyzing the emotional state of input data using an emotion engine and adjusting the tone of the content,

[0821] A method to analyze past user behavior data to identify the optimal posting timing and present a schedule,

[0822] A means for analyzing images and videos, adjusting visual elements, and optimizing visual information,

[0823] A means of receiving user inquiries in real time and automatically generating appropriate responses from the database,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, which identifies objects in an image or video and optimizes visual information by automatically adjusting brightness and contrast.

[0827] (Claim 3)

[0828] The system according to claim 1, which receives inquiries from users in real time and provides appropriate responses from a pre-configured response database.

[0829] "Application example 2 when combining with an emotional engine"

[0830] (Claim 1)

[0831] A method for automatically generating content from input data using natural language processing,

[0832] A method for identifying the optimal posting time by analyzing past user behavior data,

[0833] A method for analyzing social media posts and classifying emotions,

[0834] A means of individually optimizing content based on the user's past behavior history,

[0835] A means for analyzing images and videos to optimize visual content,

[0836] A machine equipped with a system that automatically responds to user inquiries,

[0837] A means of providing content by performing sentiment analysis and adjusting the tone,

[0838] A method of analyzing data using machine learning to increase engagement,

[0839] Image processing means for optimizing the brightness and contrast of visual content,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, which optimizes visual content by identifying objects in an image or video and automatically adjusting their brightness or contrast.

[0843] (Claim 3)

[0844] The system according to claim 1, which receives user inquiries in real time and provides appropriate answers from a pre-configured response database. [Explanation of symbols]

[0845] 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. A method for automatically generating advertising text from input information using natural language processing, A method for identifying the optimal service time by analyzing past user behavior data, A means of analyzing posts on social media and classifying emotions, A means of individually optimizing information based on the user's past behavioral history, A means for analyzing video and images to optimize visual elements, An information processing system that automatically responds to inquiries from users, A means of analyzing the effectiveness of the provided advertising campaigns and providing feedback for strategic improvement, A system that includes this.

2. The system according to claim 1, which optimizes visual elements by identifying a subject in an image or video and automatically adjusting its brightness or contrast.

3. The system according to claim 1, which receives user inquiries in real time and provides appropriate answers from a pre-configured response information database.

Images