system

Abstract

Provide a system. , , , 【Solution means】 Means for acquiring past social networking service data and learning patterns based on the relevant data; Means for generating new content based on the learning results; Means for automatically publishing the generated content on the social networking service; Means for collecting and analyzing engagement data after publication; Means for optimizing the publication schedule and content based on the analysis results; Means for managing and optimizing SNS advertising campaigns using a mobile information terminal; Means for monitoring engagement data in real time and providing information for improving advertising effects; 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, 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 marketing activities using social networking services, it often costs a large amount of money to operate a proven account with a wide follower base. Also, there is a problem that it is difficult for companies without know-how on effective follower acquisition methods to operate efficiently. The present invention aims to solve such problems and support companies to have a wide follower base on SNS at low cost.

Means for Solving the Problems

[0005] The present invention is a system that includes means for learning patterns by acquiring past social networking service data, means for generating new content based on the learning results, and means for automatically publishing the generated content. Furthermore, by including means for collecting and analyzing engagement data after publication, and means for optimizing the publication schedule and content based on the analysis results, the system provides a system that efficiently and effectively increases SNS followers while supporting marketing activities.

[0006] "Social networking service data" refers to a collection of digital information related to user actions such as posts, comments, likes, and shares generated within social networking services.

[0007] "Pattern learning" refers to the process of identifying useful trends and characteristics from past data and using them to build algorithms and models that predict future actions.

[0008] "Generating new content" refers to creating new information and media that can be used as posts or messages for target users, based on existing data and learning results.

[0009] "Automatically publishing" refers to the distribution of content generated mechanically and programmatically based on predetermined conditions onto social networking services, without human intervention.

[0010] "Engagement data" refers to metrics that show user reactions to posts on social networking services, and specifically includes likes, comments, shares, and clicks.

[0011] "Analyzing" refers to the process of extracting and understanding the underlying meanings and trends within collected data by processing it numerically and logically.

[0012] "Optimization" refers to adjusting and improving processes and elements in order to maximize results or minimize costs and risks in relation to set goals and constraints. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

[0016] In the following embodiments, a 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), and the like.

[0017] 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.

[0018] 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.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention provides an influencer AI agent system for automatically and efficiently conducting marketing activities using social networking services. This system utilizes past social networking service data and learns patterns to generate new content and automate posting. Furthermore, it analyzes engagement data to suggest optimal content and schedules.

[0035] Data collection and learning

[0036] The server utilizes the APIs of social media platforms to retrieve data on past posts and user actions. This includes posts related to specific hashtags and keywords. The server stores this data in a database and uses pattern recognition technology for learning.

[0037] Content generation

[0038] The server automatically generates new posted content based on the learning results. The generation process uses natural language processing technology to provide diverse content that takes into account the season and the latest trends. This includes, for example, product promotional content and user-participation campaign content.

[0039] Automated posting and management

[0040] The device automatically posts content provided by the server to social media based on a pre-set schedule. This eliminates the need for companies to manually post content and maximizes the potential for follower growth at specific times.

[0041] Engagement analysis and optimization

[0042] The server collects engagement data (likes, comments, shares, etc.) after a post is published. This allows the server to analyze the performance of each post and monitor user behavior. Based on the results, the server suggests more effective posting schedules and content, optimizing the process.

[0043] Through the dashboard, users can view real-time engagement data and follower growth, and adjust their marketing strategies accordingly. This is extremely helpful for companies lacking the necessary expertise to conduct effective influencer marketing at a low cost.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server uses the APIs of social networking services to collect past posting data. Specifically, it targets posts related to certain keywords or hashtags and collects engagement metrics (e.g., likes, comments, shares) for these posts.

[0047] Step 2:

[0048] The server collects data and stores it in a database. Then, the stored data is analyzed, and machine learning models are used to extract patterns and features that are effective for gaining followers. This process utilizes natural language processing techniques.

[0049] Step 3:

[0050] The server generates new content based on learned patterns. This generation takes into account specific themes and trends to create content that will interest followers. The generated content can be tested with different variations.

[0051] Step 4:

[0052] The server determines the optimal posting schedule based on the content it generates. Based on the determined schedule, the device automatically posts to the corresponding SNS account.

[0053] Step 5:

[0054] The server collects engagement data (e.g., number of likes, shares, and comments) again after a post is published. This makes it possible to measure the effectiveness of each post.

[0055] Step 6:

[0056] The server analyzes the collected engagement data and extracts optimization patterns for future posts. Based on these results, the system is updated and fed back into the generation of the next post.

[0057] Step 7:

[0058] Users can use the server-provided dashboard to monitor engagement results and follower growth for all their posts. This allows users to adjust their marketing strategies accordingly.

[0059] (Example 1)

[0060] 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."

[0061] Modern businesses are required to identify trends and effective strategies from vast amounts of data in order to conduct effective marketing activities on information exchange services. However, manually collecting and analyzing data is extremely time-consuming and labor-intensive, making it difficult to implement optimal strategies in real time. In particular, there is a need for rapid feedback and quick strategic adjustments based on that data, but there has been a lack of systems to efficiently accomplish this.

[0062] 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.

[0063] In this invention, the server includes means for acquiring past information exchange service data and learning trends based on that data, means for generating new information based on the learning results, and means for automatically publishing the generated information on the information exchange service. This enables efficient and automated data analysis and information generation.

[0064] An "information exchange service" is a platform where individuals and organizations can post and share information online.

[0065] "Data" refers to information posted on information exchange services and records of user behavior.

[0066] A "trend" refers to a general pattern or flow of behavior extracted from past data.

[0067] "Means of learning" refers to technologies and methods that enable machines to automatically analyze collected data and understand patterns.

[0068] "Means of generating information" refers to technologies and methods for automatically creating new content and information by utilizing learned trends and patterns.

[0069] "Methods for automatic publication" refer to technologies and methods for automatically posting generated information to information exchange services based on pre-set conditions and schedules.

[0070] "Participation data" refers to an indicator that shows the degree of user response to and involvement in posts published on an information exchange service.

[0071] "Optimization methods" refer to techniques and methods used to improve the content and timing of future posts and increase efficiency, based on the collected participation data.

[0072] This invention provides an automated system for facilitating marketing activities on an information exchange service. The system includes a series of processes for acquiring data from the information exchange service, performing analysis based on that data, and generating optimal marketing content.

[0073] The server collects past posting data and user interaction data via the information exchange service's API. This includes posts containing specific hashtags and keywords. The collected data is stored in a database, and machine learning algorithms are used for analysis. This allows the server to learn trends from past successes and use them to inform future marketing strategies.

[0074] The server automatically generates new content using a generative AI model based on the learning results. This generation is performed based on specified prompts, enabling the creation of posts that reflect the creator's intentions based on user input.

[0075] For example, if the server receives the prompt "Introducing family activities to enjoy on the weekend," the generative AI model will create post content that aligns with this theme. This content may include information relevant to the season and local events.

[0076] The device automatically posts content provided by the server to an information exchange service based on a set time. This allows users to efficiently reach their target audience through an automated process.

[0077] Furthermore, the server collects and analyzes participation data for published content in real time. Based on this analysis, future posts and schedules can be optimized to achieve greater effectiveness. Users can use the dashboard to review this data and fine-tune their strategies.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The server collects past posting data and user behavior data based on specific hashtags and keywords through an information exchange service API. The input is the specified hashtags and keywords, and the output is the corresponding dataset. Data processing includes filtering and cleansing of irrelevant data.

[0081] Step 2:

[0082] The server stores the collected data in a database and applies data analysis and machine learning algorithms to learn trends. The input here is a processed dataset, and the output is an extracted pattern or trend model. Specifically, the server uses certain analytical tools to identify data clusters.

[0083] Step 3:

[0084] The server uses a generative AI model based on the learning results to automatically generate new posted content. The input is a trend model and a prompt sentence for generation, and the output is the generated content text. Specifically, the server calls the AI ​​model to execute the natural language generation process based on the prompt sentence.

[0085] Step 4:

[0086] The server generates content and sends it to the terminal based on a pre-configured schedule for preparation. The input is the generated content text and schedule information, and the output is the terminal's readiness status for posting. The terminal then verifies its settings to ensure posting can be done at the specified time.

[0087] Step 5:

[0088] The device automatically posts content to an information exchange service at a specified time. The input consists of content ready for posting and schedule information, while the output is the actual posted content. Specifically, the device executes the posting via an API and verifies the posting success.

[0089] Step 6:

[0090] The server collects and analyzes participation data for published posts in real time. The input is user reaction data to the posts (e.g., number of likes, number of comments), and the output is analyzed performance evaluation data. Specifically, the server aggregates and compares participation data to identify effective posting patterns.

[0091] Step 7:

[0092] The server proposes new, optimized content and posting schedules based on the analysis results. The input is performance evaluation data, and the output is an optimized marketing plan. Specifically, the server automatically generates suggestions based on the analysis results and notifies the user.

[0093] (Application Example 1)

[0094] 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."

[0095] Traditional marketing activities using social networking services suffer from inefficiencies due to the reliance on manual management and optimization of advertising campaigns. Furthermore, the lack of real-time data analysis and content optimization prevents advertisers from maximizing their effectiveness.

[0096] 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.

[0097] In this invention, the server includes means for acquiring historical data and learning patterns, means for generating new content, and means for providing content and information from a mobile device. This enables efficient management of advertising campaigns, real-time data analysis, and rapid content optimization.

[0098] "Past social networking service data" refers to information including text, images, videos, and accompanying user reactions posted on social networking services within a specific period of time prior to the current date.

[0099] "Methods for learning patterns" refer to algorithms and techniques for analyzing past data to identify relevant information and trends.

[0100] "Means of generating new content" refers to the process of creating new posts by utilizing algorithms and generative models based on past learning results.

[0101] "Methods for automatically publishing on social networking services" refer to methods of posting generated content to social networking services (SNS) at a set time without requiring manual operation.

[0102] "Means for collecting and analyzing engagement data" refers to technologies that capture and analyze user reactions and actions (likes, comments, shares, etc.) to posts on social media.

[0103] "Optimization methods" refer to techniques used to improve effectiveness by adjusting the content and timing of subsequent posts based on collected data.

[0104] A "portable information terminal" refers to a portable electronic device such as a smartphone or tablet that can display and operate information.

[0105] "Methods for managing and optimizing social media advertising campaigns" refers to the process of planning, implementing, and evaluating advertising activities conducted on social media, and making adjustments to enhance their effectiveness.

[0106] "A means of monitoring in real time and providing information to improve advertising effectiveness" refers to a method of immediately grasping the results of advertising and providing information to be used for improvement and future strategies based on that evaluation.

[0107] In this invention, the server uses the API of a social networking service to retrieve historical data. It primarily collects data on posts, user reactions, and behavior, and stores this data in a database. Using a cloud database such as Amazon RDS allows for secure and efficient data management. Based on the collected data, the server performs machine learning using Google Cloud AI to learn patterns. This enables it to recognize trends and patterns derived from the data and generate new content.

[0108] The generated content incorporates seasonal and trending elements based on natural language processing technology, creating content suitable for advertising campaigns. The server then automatically publishes the generated content to social networking services at the optimal time. Devices, such as smartphones and tablets, are equipped with applications to manage and optimize this content, allowing users to check the schedule and content.

[0109] After posting, the server monitors engagement data in real time. It analyzes data such as the number of likes, comments, and shares, and based on the results, provides users with optimized advertising campaign suggestions. This enables efficient and effective marketing activities.

[0110] As a concrete example, when conducting a campaign to promote a new product for the winter season, the server analyzes winter consumer trends based on past data and generates optimal content based on that analysis. Then, it posts to social media at a specified time and tracks user reactions in real time to suggest further optimizations.

[0111] An example of a prompt to input into a generative AI model is, "Based on past winter promotion data, suggest the best social media campaign for this winter."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server retrieves historical data via the APIs of social networking services. Inputs include conditions based on specific keywords and hashtags, and output includes relevant posts and user response data. This data is then stored in a cloud database using Amazon RDS. This process is designed to improve the efficiency of data collection and prepare for subsequent analysis.

[0115] Step 2:

[0116] The server learns patterns using data stored in a cloud database. The input data consists of past posts and engagement information, which are used to perform machine learning using Google Cloud AI. The learned patterns are output and used as foundational information for analyzing new trends and user behavior.

[0117] Step 3:

[0118] The server generates new content using a pre-trained model. This process involves receiving seasonal information, recent trends, and target product details as input, which is then used by a generative AI model employing natural language processing techniques to create advertising content. The output consists of text and visuals suitable for the campaign, preparing for the next posting schedule.

[0119] Step 4:

[0120] The device, specifically the user's smartphone, receives generated content sent from the server and allows the user to review it. The user reviews the schedule and content on the screen and makes adjustments or approvals as needed. The input is the generated content, and the user's actions are sent to the server as feedback.

[0121] Step 5:

[0122] The server automatically posts user-approved content to social networking services at the optimal time set. In this process, the input is user approval information and generated content, and the output is posting to social networking services. This enables efficient campaign deployment.

[0123] Step 6:

[0124] The server collects and analyzes engagement data in real time after a post is made. Input includes user reactions such as likes, comments, and shares, which are then analyzed using analytics tools like Google Analytics. Output provides insights to optimize future advertising activities and is provided as feedback to the user.

[0125] 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.

[0126] This invention provides an influencer AI agent system that integrates an emotion engine to recognize user emotions. This system enables effective marketing activities using social networking services by improving the accuracy and effectiveness of content through pattern learning based on past data, automatic generation of new content, and post optimization, as well as analyzing user emotions.

[0127] Data collection and pattern learning

[0128] The server retrieves past posting data from social networking services and stores it in a database. The server then uses this data to learn posting performance patterns. Natural language processing techniques are employed for pattern learning to extract effective content features.

[0129] Emotional analysis using an emotion engine

[0130] The server's sentiment engine analyzes post and comment data and automatically extracts user sentiment. This sentiment data is crucial for understanding how a particular post evokes certain emotions in users.

[0131] New content creation and posting

[0132] The server generates new content optimized for the target market based on learned patterns and extracted sentiment data. The generated content includes elements that take into account the emotional resonance of each user.

[0133] The device automatically posts content received from the server at a specified time, maximizing follower engagement.

[0134] Engagement data collection and optimization

[0135] The server collects and analyzes engagement metrics (e.g., likes, comments, shares) after a post is published. Furthermore, by analyzing this data in conjunction with sentiment data accumulated by the sentiment engine, it optimizes content and scheduling.

[0136] Users can utilize an intuitive dashboard to observe how content is being received and how emotional responses are changing, allowing them to dynamically adjust their marketing strategies. This system provides an environment where deep user understanding and efficient marketing activities can coexist.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The server uses the API of social networking services to collect past posting data. This data includes text content, posting time, number of likes, number of comments, etc. The server filters and stores the data based on specific criteria.

[0140] Step 2:

[0141] The server uses collected data to perform pattern learning. Natural language processing algorithms are used to analyze the linguistic features and success patterns of posts, training the model. The model identifies the characteristics of posts that are effective in gaining followers.

[0142] Step 3:

[0143] The server's sentiment engine analyzes the text data of posts and comments to extract user emotions. For example, it categorizes them into emotional categories such as "happy," "sad," and "interested." This sentiment data is stored as an important indicator for understanding user reactions.

[0144] Step 4:

[0145] The server generates new post content based on pattern learning results and sentiment data. During generation, it considers emotional resonance and incorporates content that is more likely to resonate with the target user.

[0146] Step 5:

[0147] The device retrieves content sent from the server and automatically posts it to social networking services according to a specified schedule. This ensures the optimal timing for posting.

[0148] Step 6:

[0149] The server collects engagement data after a post is published (e.g., number of likes, shares, and comments). This allows for a quantitative measurement of the user response generated by each post.

[0150] Step 7:

[0151] The server integrates engagement data and sentiment analysis results to analyze the effectiveness of posts. Based on these analysis results, a strategy is developed to optimize future content creation and posting schedules.

[0152] Step 8:

[0153] Users can view post performance data and sentiment analysis results via a dashboard. Based on this, users can improve their marketing strategies and provide feedback.

[0154] (Example 2)

[0155] 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".

[0156] In today's communication infrastructure, there is a demand for providing effective content based on user interests and emotions to maximize response, but achieving this requires considerable effort and experience. In particular, understanding user emotions in real time and optimizing content based on them is not easy. Furthermore, traditional methods suffer from reduced efficiency because content generation and posting schedule optimization are performed separately.

[0157] 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.

[0158] In this invention, the server includes means for acquiring past electronic data via a communication network and learning performance patterns based on that data; means for extracting the user's emotions from text data using an emotion analysis device; and means for adjusting presentations that take emotional resonance into consideration based on the emotion data and response indicators. This makes it possible to generate optimal content according to the user's emotions and adjust the delivery schedule efficiently.

[0159] A "communication network" refers to a structure in which several devices and systems are interconnected in order to exchange information with each other.

[0160] "Electronic data" refers to information that is stored and transmitted in digital format, and this includes text, images, and audio data.

[0161] "Performance patterns" refer to trends and regularities in content and user responses derived from past data.

[0162] "Presentation" refers to content and information provided to the user, including text, images, and videos.

[0163] "Electronic communication infrastructure" refers to the infrastructure and services used to send and receive information in digital format.

[0164] A "release schedule" refers to a plan or timeline of when and how specific content will be published.

[0165] An "emotion analysis device" refers to a device or software that analyzes text data and flow data to automatically determine a person's emotions and emotional tendencies.

[0166] "Response metrics" are numerical representations of user reactions to content, such as the number of "likes" or "comments."

[0167] "Emotional resonance" refers to the emotional impact and degree of empathy that content has on users.

[0168] This invention relates to a system for users to effectively deliver content on existing electronic communication infrastructure. The server acquires past electronic data through the communication network and learns performance patterns based on it. This learning utilizes natural language processing technology and generative AI models, such as the Python NLP libraries spaCy and NLTK, or OpenAI's GPT-3® as a generative AI model. This allows the system to predict user reactions from past content and automatically generate effective new content.

[0169] The server uses an emotion analysis device to extract user emotions from text data and combines this emotion data with generated content to adjust the optimal presentation to evoke emotional resonance in the target user. The terminal automatically transmits the content received from the server over the electronic communication infrastructure according to a specific transmission schedule. This allows users to efficiently publish content and obtain the maximum response.

[0170] For example, suppose a user wants to promote eco-friendly products to followers who are interested in environmental protection. In this case, they can input the following prompt into the AI ​​model to generate new content.

[0171] "Create emotionally resonant content about our new eco-friendly product. The target audience is followers who are interested in environmental issues."

[0172] This system allows users to provide content based on a deeper understanding and to conduct effective marketing activities targeting their audience.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The server retrieves historical electronic data from social networking platforms via a communication network. The input consists of past posts and comments. The server uses an API to collect this data and store it in a database. During this process, the data includes the timestamp of each post, the user ID, and the number of interactions that occurred. The output is the stored database entries.

[0176] Step 2:

[0177] The server learns performance patterns based on stored historical data. The input is the data stored in step 1. The server analyzes the data using natural language processing techniques and extracts frequently occurring keywords and features of posts that elicited positive responses. The output is the extracted feature patterns. For example, the Python NLP library spaCy is used to identify keywords from the text of posts.

[0178] Step 3:

[0179] The server uses an emotion analyzer to extract user emotions from text data. The input is the posts and comments obtained in step 1. Sentiment analysis classifies the text as either positive, negative, or neutral. A machine learning algorithm is used in this process to calculate an emotion score. The output is emotion data indicating the user's emotions.

[0180] Step 4:

[0181] The server inputs prompt sentences into a generative AI model based on learned patterns and sentiment data, generating new content. The input consists of patterns from step 2 and sentiment data from step 3. The server uses a generative AI model (e.g., GPT-3) to generate content tailored to the user's target market and adjusts it to enhance emotional resonance. The output is the newly generated content.

[0182] Step 5:

[0183] The device automatically posts new content received from the server to the social networking platform according to the posting schedule. The input consists of the content generated in step 4 and the optimized posting schedule. The device uses a scheduling system to post content during times when followers are most active. The output is the published content.

[0184] Step 6:

[0185] The server collects and analyzes reaction metrics available after posting. Inputs include reaction metrics such as likes, comments, and shares. The server uses this data to further optimize future content creation and posting schedules. The output is optimized strategic data, which is then used to improve future posting activities.

[0186] (Application Example 2)

[0187] 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".

[0188] In modern communication services, it is crucial that advertisements are delivered to users in an effective and targeted manner. However, conventional systems do not adequately consider users' emotions and psychological states when selecting advertisements, making it difficult to maximize the effectiveness of advertising.

[0189] 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. In this invention, the server includes means for acquiring past communication data and learning patterns based on the relevant data, means for automatically publishing the generated information on the communication service, and emotion analysis means for analyzing the user's emotions. This makes it possible to select and display advertisements that are appropriate to the user's current situation in real time.

[0190] "Communication data" refers to information about a user's activities on a communication service.

[0191] "Means for learning patterns" refer to methods and devices for analyzing features in past communication data and extracting regularities.

[0192] "Means of generating new information" refers to functions that create content and advertisements for users based on learned patterns.

[0193] "Methods for automatic publication" refer to a mechanism for automatically distributing generated information over a communication service based on set conditions.

[0194] "Engagement data" refers to data about user reactions and behaviors obtained after information is made public.

[0195] "Methods for optimizing the release schedule and information content based on analysis results" refers to methods for analyzing collected engagement data and adjusting the timing and content of information distribution.

[0196] "Emotional analysis means" refers to a technology or device that determines a user's emotional state from their words, actions, and facial expressions.

[0197] "Means of selecting and displaying advertisements" refers to a system that selects and provides advertisements that are appropriate to the user's emotional state.

[0198] This invention relates to a system for delivering advertisements that are adapted to the emotional state of users. To realize this system, the following specific configurations and procedures are included.

[0199] The server acquires data from past communication services and learns patterns based on that information. This involves using natural language processing techniques and machine learning algorithms to analyze specific regularities and user trends. Specifically, it utilizes Python's NLTK and various machine learning libraries.

[0200] Based on the learned results, new content and advertisements are generated. Using a generative AI model, information tailored to the user's interests and emotions is automatically created. The generated information is delivered via smartphones and smart glasses according to set conditions. Communication service APIs and advertising delivery systems are utilized for information distribution.

[0201] The terminal monitors user reactions and collects engagement data after the information is released. This data includes the number of ratings, responses, and shares, and serves as material for data analysis. The server analyzes the collected data and optimizes the distribution schedule and information content.

[0202] Furthermore, the device uses its camera and microphone to perform emotion analysis of the user. Specifically, it analyzes facial expressions and voice using face recognition APIs and voice analysis APIs to identify emotional states. For example, it can perform emotion analysis in real time by utilizing Google's Face Detection API and Speech-to-Text API.

[0203] Based on the analysis results, the server selects and displays the most relevant advertisements to the user. By providing the selected advertisements with content and timing tailored to the user, it is possible to enhance the effectiveness of the advertisements.

[0204] As a concrete example, if a user is browsing the news through smart glasses and an expression of surprise is detected, an advertisement for a new product corresponding to that emotion will be automatically displayed. The generative AI model supporting this mechanism uses prompts such as, "Analyze the user's emotions in real time and suggest advertising content that matches their emotional state." This improves the accuracy of ad delivery and user engagement.

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The server retrieves past communication data through the communication service's API. This retrieved data includes user posts and responses. Using this data, the server employs natural language processing techniques to learn patterns. This pattern learning analyzes information trends and user behavior patterns, which are then used as input for the next step.

[0208] Step 2:

[0209] The server uses a generative AI model to generate new information based on learned patterns. In this process, the generative AI model is input with the prompt, "Analyze the user's emotions in real time and suggest advertising content that matches their emotional state." Based on this, the model outputs content that resonates with the user's expectations and emotions.

[0210] Step 3:

[0211] The server automatically publishes the generated information over the communication service. The timing of information publication is determined based on conditions pre-configured by the server. This publication displays the information on the user's device, initiating the first stage of engagement.

[0212] Step 4:

[0213] The device monitors user behavior after publication and collects engagement data. This data includes ratings, reactions, and shares. The device sends this data to a server for use in the next analysis step.

[0214] Step 5:

[0215] The server analyzes the collected engagement data. This analysis uses data processing techniques to evaluate the degree of engagement and effectiveness. Based on the analysis results, the server optimizes the information release schedule and content again. This will be reflected in the next information distribution.

[0216] Step 6:

[0217] The device uses its camera and microphone to analyze the user's emotions in real time. A facial recognition API and a voice analysis API analyze this data to identify the user's current emotional state. This emotional state is sent to a server and used as a reference for ad selection.

[0218] Step 7:

[0219] Based on the sentiment analysis results received, the server selects the most suitable advertisement for the user and determines which advertisement to display. In this process, the server selects the appropriate content from a pre-generated list of advertisements and displays it on the user's device. As a result, the advertisement deemed most effective for the user is delivered.

[0220] 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.

[0221] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), 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.

[0222] 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.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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".

[0236] This invention provides an influencer AI agent system for automatically and efficiently conducting marketing activities using social networking services. This system utilizes past social networking service data and learns patterns to generate new content and automate posting. Furthermore, it analyzes engagement data to suggest optimal content and schedules.

[0237] Data collection and learning

[0238] The server utilizes the APIs of social media platforms to retrieve data on past posts and user actions. This includes posts related to specific hashtags and keywords. The server stores this data in a database and uses pattern recognition technology for learning.

[0239] Content generation

[0240] The server automatically generates new posted content based on the learning results. The generation process uses natural language processing technology to provide diverse content that takes into account the season and the latest trends. This includes, for example, product promotional content and user-participation campaign content.

[0241] Automated posting and management

[0242] The device automatically posts content provided by the server to social media based on a pre-set schedule. This eliminates the need for companies to manually post content and maximizes the potential for follower growth at specific times.

[0243] Engagement analysis and optimization

[0244] The server collects engagement data (likes, comments, shares, etc.) after a post is published. This allows the server to analyze the performance of each post and monitor user behavior. Based on the results, the server suggests more effective posting schedules and content, optimizing the process.

[0245] Through the dashboard, users can view real-time engagement data and follower growth, and adjust their marketing strategies accordingly. This is extremely helpful for companies lacking the necessary expertise to conduct effective influencer marketing at a low cost.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The server uses the APIs of social networking services to collect past posting data. Specifically, it targets posts related to certain keywords or hashtags and collects engagement metrics (e.g., likes, comments, shares) for these posts.

[0249] Step 2:

[0250] The server collects data and stores it in a database. Then, the stored data is analyzed, and machine learning models are used to extract patterns and features that are effective for gaining followers. This process utilizes natural language processing techniques.

[0251] Step 3:

[0252] The server generates new content based on learned patterns. This generation takes into account specific themes and trends to create content that will interest followers. The generated content can be tested with different variations.

[0253] Step 4:

[0254] The server determines the optimal posting schedule based on the content it generates. Based on the determined schedule, the device automatically posts to the corresponding SNS account.

[0255] Step 5:

[0256] The server collects engagement data (e.g., number of likes, shares, and comments) again after a post is published. This makes it possible to measure the effectiveness of each post.

[0257] Step 6:

[0258] The server analyzes the collected engagement data and extracts optimization patterns for future posts. Based on these results, the system is updated and fed back into the generation of the next post.

[0259] Step 7:

[0260] Users can use the server-provided dashboard to monitor engagement results and follower growth for all their posts. This allows users to adjust their marketing strategies accordingly.

[0261] (Example 1)

[0262] 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."

[0263] Modern businesses are required to identify trends and effective strategies from vast amounts of data in order to conduct effective marketing activities on information exchange services. However, manually collecting and analyzing data is extremely time-consuming and labor-intensive, making it difficult to implement optimal strategies in real time. In particular, there is a need for rapid feedback and quick strategic adjustments based on that data, but there has been a lack of systems to efficiently accomplish this.

[0264] 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.

[0265] In this invention, the server includes means for acquiring past information exchange service data and learning trends based on that data, means for generating new information based on the learning results, and means for automatically publishing the generated information on the information exchange service. This enables efficient and automated data analysis and information generation.

[0266] An "information exchange service" is a platform where individuals and organizations can post and share information online.

[0267] "Data" refers to information posted on information exchange services and records of user behavior.

[0268] A "trend" refers to a general pattern or flow of behavior extracted from past data.

[0269] "Means of learning" refers to technologies and methods that enable machines to automatically analyze collected data and understand patterns.

[0270] "Means of generating information" refers to technologies and methods for automatically creating new content and information by utilizing learned trends and patterns.

[0271] "Methods for automatic publication" refer to technologies and methods for automatically posting generated information to information exchange services based on pre-set conditions and schedules.

[0272] "Participation data" refers to an indicator that shows the degree of user response to and involvement in posts published on an information exchange service.

[0273] "Optimization methods" refer to techniques and methods used to improve the content and timing of future posts and increase efficiency, based on the collected participation data.

[0274] This invention provides an automated system for facilitating marketing activities on an information exchange service. The system includes a series of processes for acquiring data from the information exchange service, performing analysis based on that data, and generating optimal marketing content.

[0275] The server collects past posting data and user interaction data via the information exchange service's API. This includes posts containing specific hashtags and keywords. The collected data is stored in a database, and machine learning algorithms are used for analysis. This allows the server to learn trends from past successes and use them to inform future marketing strategies.

[0276] The server automatically generates new content using a generative AI model based on the learning results. This generation is performed based on specified prompts, enabling the creation of posts that reflect the creator's intentions based on user input.

[0277] For example, if the server receives the prompt "Introducing family activities to enjoy on the weekend," the generative AI model will create post content that aligns with this theme. This content may include information relevant to the season and local events.

[0278] The device automatically posts content provided by the server to an information exchange service based on a set time. This allows users to efficiently reach their target audience through an automated process.

[0279] Furthermore, the server collects and analyzes participation data for published content in real time. Based on this analysis, future posts and schedules can be optimized to achieve greater effectiveness. Users can use the dashboard to review this data and fine-tune their strategies.

[0280] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0281] Step 1:

[0282] The server collects past posting data and user behavior data based on specific hash tags or keywords through the API of the information exchange service. The input is the specified hash tags or keywords, and the output is the corresponding data set. As data processing, filtering and cleansing of irrelevant data are performed.

[0283] Step 2:

[0284] The server stores the collected data in a database and applies data analysis and machine learning algorithms to perform trend learning. The input here is the processed data set, and the output is the extracted patterns and trend models. As a specific operation, the server uses specific analysis tools to identify data clusters.

[0285] Step 3:

[0286] The server uses the generated AI model based on the learning results to automatically generate new posting content. The input is the trend model and the prompt text for generation, and the output is the generated content text. As a specific operation, the server calls the AI model to execute a natural language generation process based on the prompt text.

[0287] Step 4:

[0288] The server transmits the generated content to the terminal based on a pre-set schedule and makes preparations. The input is the generated content text and the schedule information, and the output is the posting preparation status by the terminal. The terminal performs the operation of checking the settings so that posting can be done at a specific time.

[0289] Step 5:

[0290] The device automatically posts content to an information exchange service at a specified time. The input consists of content ready for posting and schedule information, while the output is the actual posted content. Specifically, the device executes the posting via an API and verifies the posting success.

[0291] Step 6:

[0292] The server collects and analyzes participation data for published posts in real time. The input is user reaction data to the posts (e.g., number of likes, number of comments), and the output is analyzed performance evaluation data. Specifically, the server aggregates and compares participation data to identify effective posting patterns.

[0293] Step 7:

[0294] The server proposes new, optimized content and posting schedules based on the analysis results. The input is performance evaluation data, and the output is an optimized marketing plan. Specifically, the server automatically generates suggestions based on the analysis results and notifies the user.

[0295] (Application Example 1)

[0296] 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."

[0297] Traditional marketing activities using social networking services suffer from inefficiencies due to the reliance on manual management and optimization of advertising campaigns. Furthermore, the lack of real-time data analysis and content optimization prevents advertisers from maximizing their effectiveness.

[0298] 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.

[0299] In this invention, the server includes means for acquiring historical data and learning patterns, means for generating new content, and means for providing content and information from a mobile device. This enables efficient management of advertising campaigns, real-time data analysis, and rapid content optimization.

[0300] "Past social networking service data" refers to information including text, images, videos, and accompanying user reactions posted on social networking services within a specific period of time prior to the current date.

[0301] "Methods for learning patterns" refer to algorithms and techniques for analyzing past data to identify relevant information and trends.

[0302] "Means of generating new content" refers to the process of creating new posts by utilizing algorithms and generative models based on past learning results.

[0303] "Methods for automatically publishing on social networking services" refer to methods of posting generated content to social networking services (SNS) at a set time without requiring manual operation.

[0304] "Means for collecting and analyzing engagement data" refers to technologies that capture and analyze user reactions and actions (likes, comments, shares, etc.) to posts on social media.

[0305] "Optimization methods" refer to techniques used to improve effectiveness by adjusting the content and timing of subsequent posts based on collected data.

[0306] A "portable information terminal" refers to a portable electronic device such as a smartphone or tablet that can display and operate information.

[0307] The means for managing and optimizing SNS advertising campaigns is a process of planning, implementing, evaluating advertising activities on SNS, and making adjustments to enhance their effectiveness.

[0308] The means for providing information for real-time monitoring and improving advertising effects is a method of immediately grasping the results of advertisements and providing information that can be utilized for improvement points and next strategies based on the evaluation.

[0309] In this invention, the server utilizes the API of the social networking service to obtain past data. It mainly collects data related to post content, user reactions, and actions, and stores it in a database. By using a cloud database such as Amazon RDS as the database, data can be managed safely and efficiently. Based on the collected data, the server performs machine learning using Google Cloud AI to learn patterns. As a result, it has the ability to recognize trends and patterns obtained from the data and generate new content.

[0310] The generated content incorporates seasons and trends based on natural language processing technology, and content suitable for the advertising campaign is created. Then, the server automatically publishes the generated content to the social networking service at an optimal time. The terminal, such as a smartphone or tablet, has an application for managing and optimizing this content, and it is possible to allow the user to check the schedule and content.

[0311] After posting, the server monitors engagement data in real time. It analyzes data such as the number of likes, comments, and shares, and based on the results, provides the user with an optimization plan for the advertising campaign. As a result, marketing activities can be carried out efficiently and effectively.

[0312] As a concrete example, when conducting a campaign to promote a new product for the winter season, the server analyzes winter consumer trends based on past data and generates optimal content based on that analysis. Then, it posts to social media at a specified time and tracks user reactions in real time to suggest further optimizations.

[0313] An example of a prompt to input into a generative AI model is, "Based on past winter promotion data, suggest the best social media campaign for this winter."

[0314] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0315] Step 1:

[0316] The server retrieves historical data via the APIs of social networking services. Inputs include conditions based on specific keywords and hashtags, and output includes relevant posts and user response data. This data is then stored in a cloud database using Amazon RDS. This process is designed to improve the efficiency of data collection and prepare for subsequent analysis.

[0317] Step 2:

[0318] The server learns patterns using data stored in a cloud database. The input data consists of past posts and engagement information, which are used to perform machine learning using Google Cloud AI. The learned patterns are output and used as foundational information for analyzing new trends and user behavior.

[0319] Step 3:

[0320] The server generates new content using a pre-trained model. This process involves receiving seasonal information, recent trends, and target product details as input, which is then used by a generative AI model employing natural language processing techniques to create advertising content. The output consists of text and visuals suitable for the campaign, preparing for the next posting schedule.

[0321] Step 4:

[0322] The device, specifically the user's smartphone, receives generated content sent from the server and allows the user to review it. The user reviews the schedule and content on the screen and makes adjustments or approvals as needed. The input is the generated content, and the user's actions are sent to the server as feedback.

[0323] Step 5:

[0324] The server automatically posts user-approved content to social networking services at the optimal time set. In this process, the input is user approval information and generated content, and the output is posting to social networking services. This enables efficient campaign deployment.

[0325] Step 6:

[0326] The server collects and analyzes engagement data in real time after a post is made. Input includes user reactions such as likes, comments, and shares, which are then analyzed using analytics tools like Google Analytics. Output provides insights to optimize future advertising activities and is provided as feedback to the user.

[0327] 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.

[0328] This invention provides an influencer AI agent system that integrates an emotion engine to recognize user emotions. This system enables effective marketing activities using social networking services by improving the accuracy and effectiveness of content through pattern learning based on past data, automatic generation of new content, and post optimization, as well as analyzing user emotions.

[0329] Data collection and pattern learning

[0330] The server retrieves past posting data from social networking services and stores it in a database. The server then uses this data to learn posting performance patterns. Natural language processing techniques are employed for pattern learning to extract effective content features.

[0331] Emotional analysis using an emotion engine

[0332] The server's sentiment engine analyzes post and comment data and automatically extracts user sentiment. This sentiment data is crucial for understanding how a particular post evokes certain emotions in users.

[0333] New content creation and posting

[0334] The server generates new content optimized for the target market based on learned patterns and extracted sentiment data. The generated content includes elements that take into account the emotional resonance of each user.

[0335] The device automatically posts content received from the server at a specified time, maximizing follower engagement.

[0336] Engagement data collection and optimization

[0337] The server collects and analyzes engagement metrics (e.g., likes, comments, shares) after a post is published. Furthermore, by analyzing this data in conjunction with sentiment data accumulated by the sentiment engine, it optimizes content and scheduling.

[0338] Users can utilize an intuitive dashboard to observe how content is being received and how emotional responses are changing, allowing them to dynamically adjust their marketing strategies. This system provides an environment where deep user understanding and efficient marketing activities can coexist.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] The server uses the API of social networking services to collect past posting data. This data includes text content, posting time, number of likes, number of comments, etc. The server filters and stores the data based on specific criteria.

[0342] Step 2:

[0343] The server uses collected data to perform pattern learning. Natural language processing algorithms are used to analyze the linguistic features and success patterns of posts, training the model. The model identifies the characteristics of posts that are effective in gaining followers.

[0344] Step 3:

[0345] The server's sentiment engine analyzes the text data of posts and comments to extract user emotions. For example, it categorizes them into emotional categories such as "happy," "sad," and "interested." This sentiment data is stored as an important indicator for understanding user reactions.

[0346] Step 4:

[0347] The server generates new post content based on pattern learning results and sentiment data. During generation, it considers emotional resonance and incorporates content that is more likely to resonate with the target user.

[0348] Step 5:

[0349] The device retrieves content sent from the server and automatically posts it to social networking services according to a specified schedule. This ensures the optimal timing for posting.

[0350] Step 6:

[0351] The server collects engagement data after a post is published (e.g., number of likes, shares, and comments). This allows for a quantitative measurement of the user response generated by each post.

[0352] Step 7:

[0353] The server integrates engagement data and sentiment analysis results to analyze the effectiveness of posts. Based on these analysis results, a strategy is developed to optimize future content creation and posting schedules.

[0354] Step 8:

[0355] Users can view post performance data and sentiment analysis results via a dashboard. Based on this, users can improve their marketing strategies and provide feedback.

[0356] (Example 2)

[0357] 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".

[0358] In today's communication infrastructure, there is a demand for providing effective content based on user interests and emotions to maximize response, but achieving this requires considerable effort and experience. In particular, understanding user emotions in real time and optimizing content based on them is not easy. Furthermore, traditional methods suffer from reduced efficiency because content generation and posting schedule optimization are performed separately.

[0359] 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.

[0360] In this invention, the server includes means for acquiring past electronic data via a communication network and learning performance patterns based on that data; means for extracting the user's emotions from text data using an emotion analysis device; and means for adjusting presentations that take emotional resonance into consideration based on the emotion data and response indicators. This makes it possible to generate optimal content according to the user's emotions and adjust the delivery schedule efficiently.

[0361] A "communication network" refers to a structure in which several devices and systems are interconnected in order to exchange information with each other.

[0362] "Electronic data" refers to information that is stored and transmitted in digital format, and this includes text, images, and audio data.

[0363] "Performance patterns" refer to trends and regularities in content and user responses derived from past data.

[0364] "Presentation" refers to content and information provided to the user, including text, images, and videos.

[0365] "Electronic communication infrastructure" refers to the infrastructure and services used to send and receive information in digital format.

[0366] A "release schedule" refers to a plan or timeline of when and how specific content will be published.

[0367] An "emotion analysis device" refers to a device or software that analyzes text data and flow data to automatically determine a person's emotions and emotional tendencies.

[0368] "Response metrics" are numerical representations of user reactions to content, such as the number of "likes" or "comments."

[0369] "Emotional resonance" refers to the emotional impact and degree of empathy that content has on users.

[0370] This invention relates to a system for users to effectively deliver content on existing electronic communication infrastructure. The server acquires past electronic data through the communication network and learns performance patterns based on it. This learning utilizes natural language processing technology and generative AI models, such as the Python NLP libraries spaCy and NLTK, or OpenAI's GPT-3 as a generative AI model. This allows the system to predict user reactions from past content and automatically generate effective new content.

[0371] The server uses an emotion analysis device to extract user emotions from text data and combines this emotion data with generated content to adjust the optimal presentation to evoke emotional resonance in the target user. The terminal automatically transmits the content received from the server over the electronic communication infrastructure according to a specific transmission schedule. This allows users to efficiently publish content and obtain the maximum response.

[0372] For example, suppose a user wants to promote eco-friendly products to followers who are interested in environmental protection. In this case, they can input the following prompt into the AI ​​model to generate new content.

[0373] "Create emotionally resonant content about our new eco-friendly product. The target audience is followers who are interested in environmental issues."

[0374] This system allows users to provide content based on a deeper understanding and to conduct effective marketing activities targeting their audience.

[0375] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0376] Step 1:

[0377] The server retrieves historical electronic data from social networking platforms via a communication network. The input consists of past posts and comments. The server uses an API to collect this data and store it in a database. During this process, the data includes the timestamp of each post, the user ID, and the number of interactions that occurred. The output is the stored database entries.

[0378] Step 2:

[0379] The server learns performance patterns based on stored historical data. The input is the data stored in step 1. The server analyzes the data using natural language processing techniques and extracts frequently occurring keywords and features of posts that elicited positive responses. The output is the extracted feature patterns. For example, the Python NLP library spaCy is used to identify keywords from the text of posts.

[0380] Step 3:

[0381] The server uses an emotion analyzer to extract user emotions from text data. The input is the posts and comments obtained in step 1. Sentiment analysis classifies the text as either positive, negative, or neutral. A machine learning algorithm is used in this process to calculate an emotion score. The output is emotion data indicating the user's emotions.

[0382] Step 4:

[0383] The server inputs prompt sentences into a generative AI model based on learned patterns and sentiment data, generating new content. The input consists of patterns from step 2 and sentiment data from step 3. The server uses a generative AI model (e.g., GPT-3) to generate content tailored to the user's target market and adjusts it to enhance emotional resonance. The output is the newly generated content.

[0384] Step 5:

[0385] The device automatically posts new content received from the server to the social networking platform according to the posting schedule. The input consists of the content generated in step 4 and the optimized posting schedule. The device uses a scheduling system to post content during times when followers are most active. The output is the published content.

[0386] Step 6:

[0387] The server collects and analyzes reaction metrics available after posting. Inputs include reaction metrics such as likes, comments, and shares. The server uses this data to further optimize future content creation and posting schedules. The output is optimized strategic data, which is then used to improve future posting activities.

[0388] (Application Example 2)

[0389] 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."

[0390] In modern communication services, it is crucial that advertisements are delivered to users in an effective and targeted manner. However, conventional systems do not adequately consider users' emotions and psychological states when selecting advertisements, making it difficult to maximize the effectiveness of advertising.

[0391] 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. In this invention, the server includes means for acquiring past communication data and learning patterns based on the relevant data, means for automatically publishing the generated information on the communication service, and emotion analysis means for analyzing the user's emotions. This makes it possible to select and display advertisements that are appropriate to the user's current situation in real time.

[0392] "Communication data" refers to information about a user's activities on a communication service.

[0393] "Means for learning patterns" refer to methods and devices for analyzing features in past communication data and extracting regularities.

[0394] "Means of generating new information" refers to functions that create content and advertisements for users based on learned patterns.

[0395] "Methods for automatic publication" refer to a mechanism for automatically distributing generated information over a communication service based on set conditions.

[0396] "Engagement data" refers to data about user reactions and behaviors obtained after information is made public.

[0397] "Methods for optimizing the release schedule and information content based on analysis results" refers to methods for analyzing collected engagement data and adjusting the timing and content of information distribution.

[0398] "Emotional analysis means" refers to a technology or device that determines a user's emotional state from their words, actions, and facial expressions.

[0399] "Means of selecting and displaying advertisements" refers to a system that selects and provides advertisements that are appropriate to the user's emotional state.

[0400] This invention relates to a system for delivering advertisements that are adapted to the emotional state of users. To realize this system, the following specific configurations and procedures are included.

[0401] The server acquires data from past communication services and learns patterns based on that information. This involves using natural language processing techniques and machine learning algorithms to analyze specific regularities and user trends. Specifically, it utilizes Python's NLTK and various machine learning libraries.

[0402] Based on the learned results, new content and advertisements are generated. Using a generative AI model, information tailored to the user's interests and emotions is automatically created. The generated information is delivered via smartphones and smart glasses according to set conditions. Communication service APIs and advertising delivery systems are utilized for information distribution.

[0403] The terminal monitors user reactions and collects engagement data after the information is released. This data includes the number of ratings, responses, and shares, and serves as material for data analysis. The server analyzes the collected data and optimizes the distribution schedule and information content.

[0404] Furthermore, the device uses its camera and microphone to perform emotion analysis of the user. Specifically, it analyzes facial expressions and voice using face recognition APIs and voice analysis APIs to identify emotional states. For example, it can perform emotion analysis in real time by utilizing Google's Face Detection API and Speech-to-Text API.

[0405] Based on the analysis results, the server selects and displays the most relevant advertisements to the user. By providing the selected advertisements with content and timing tailored to the user, it is possible to enhance the effectiveness of the advertisements.

[0406] As a concrete example, if a user is browsing the news through smart glasses and an expression of surprise is detected, an advertisement for a new product corresponding to that emotion will be automatically displayed. The generative AI model supporting this mechanism uses prompts such as, "Analyze the user's emotions in real time and suggest advertising content that matches their emotional state." This improves the accuracy of ad delivery and user engagement.

[0407] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0408] Step 1:

[0409] The server retrieves past communication data through the communication service's API. This retrieved data includes user posts and responses. Using this data, the server employs natural language processing techniques to learn patterns. This pattern learning analyzes information trends and user behavior patterns, which are then used as input for the next step.

[0410] Step 2:

[0411] The server uses a generative AI model to generate new information based on learned patterns. In this process, the generative AI model is input with the prompt, "Analyze the user's emotions in real time and suggest advertising content that matches their emotional state." Based on this, the model outputs content that resonates with the user's expectations and emotions.

[0412] Step 3:

[0413] The server automatically publishes the generated information over the communication service. The timing of information publication is determined based on conditions pre-configured by the server. This publication displays the information on the user's device, initiating the first stage of engagement.

[0414] Step 4:

[0415] The device monitors user behavior after publication and collects engagement data. This data includes ratings, reactions, and shares. The device sends this data to a server for use in the next analysis step.

[0416] Step 5:

[0417] The server analyzes the collected engagement data. This analysis uses data processing techniques to evaluate the degree of engagement and effectiveness. Based on the analysis results, the server optimizes the information release schedule and content again. This will be reflected in the next information distribution.

[0418] Step 6:

[0419] The device uses its camera and microphone to analyze the user's emotions in real time. A facial recognition API and a voice analysis API analyze this data to identify the user's current emotional state. This emotional state is sent to a server and used as a reference for ad selection.

[0420] Step 7:

[0421] Based on the sentiment analysis results received, the server selects the most suitable advertisement for the user and determines which advertisement to display. In this process, the server selects the appropriate content from a pre-generated list of advertisements and displays it on the user's device. As a result, the advertisement deemed most effective for the user is delivered.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] [Third Embodiment]

[0426] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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).

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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".

[0438] This invention provides an influencer AI agent system for automatically and efficiently conducting marketing activities using social networking services. This system utilizes past social networking service data and learns patterns to generate new content and automate posting. Furthermore, it analyzes engagement data to suggest optimal content and schedules.

[0439] Data collection and learning

[0440] The server utilizes the APIs of social media platforms to retrieve data on past posts and user actions. This includes posts related to specific hashtags and keywords. The server stores this data in a database and uses pattern recognition technology for learning.

[0441] Content generation

[0442] The server automatically generates new posted content based on the learning results. The generation process uses natural language processing technology to provide diverse content that takes into account the season and the latest trends. This includes, for example, product promotional content and user-participation campaign content.

[0443] Automated posting and management

[0444] The device automatically posts content provided by the server to social media based on a pre-set schedule. This eliminates the need for companies to manually post content and maximizes the potential for follower growth at specific times.

[0445] Engagement analysis and optimization

[0446] The server collects engagement data (likes, comments, shares, etc.) after a post is published. This allows the server to analyze the performance of each post and monitor user behavior. Based on the results, the server suggests more effective posting schedules and content, optimizing the process.

[0447] Through the dashboard, users can view real-time engagement data and follower growth, and adjust their marketing strategies accordingly. This is extremely helpful for companies lacking the necessary expertise to conduct effective influencer marketing at a low cost.

[0448] The following describes the processing flow.

[0449] Step 1:

[0450] The server uses the APIs of social networking services to collect past posting data. Specifically, it targets posts related to certain keywords or hashtags and collects engagement metrics (e.g., likes, comments, shares) for these posts.

[0451] Step 2:

[0452] The server collects data and stores it in a database. Then, the stored data is analyzed, and machine learning models are used to extract patterns and features that are effective for gaining followers. This process utilizes natural language processing techniques.

[0453] Step 3:

[0454] The server generates new content based on learned patterns. This generation takes into account specific themes and trends to create content that will interest followers. The generated content can be tested with different variations.

[0455] Step 4:

[0456] The server determines the optimal posting schedule based on the content it generates. Based on the determined schedule, the device automatically posts to the corresponding SNS account.

[0457] Step 5:

[0458] The server collects engagement data (e.g., number of likes, shares, and comments) again after a post is published. This makes it possible to measure the effectiveness of each post.

[0459] Step 6:

[0460] The server analyzes the collected engagement data and extracts optimization patterns for future posts. Based on these results, the system is updated and fed back into the generation of the next post.

[0461] Step 7:

[0462] Users can use the server-provided dashboard to monitor engagement results and follower growth for all their posts. This allows users to adjust their marketing strategies accordingly.

[0463] (Example 1)

[0464] 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."

[0465] Modern businesses are required to identify trends and effective strategies from vast amounts of data in order to conduct effective marketing activities on information exchange services. However, manually collecting and analyzing data is extremely time-consuming and labor-intensive, making it difficult to implement optimal strategies in real time. In particular, there is a need for rapid feedback and quick strategic adjustments based on that data, but there has been a lack of systems to efficiently accomplish this.

[0466] 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.

[0467] In this invention, the server includes means for acquiring past information exchange service data and learning trends based on that data, means for generating new information based on the learning results, and means for automatically publishing the generated information on the information exchange service. This enables efficient and automated data analysis and information generation.

[0468] An "information exchange service" is a platform where individuals and organizations can post and share information online.

[0469] "Data" refers to information posted on information exchange services and records of user behavior.

[0470] A "trend" refers to a general pattern or flow of behavior extracted from past data.

[0471] "Means of learning" refers to technologies and methods that enable machines to automatically analyze collected data and understand patterns.

[0472] "Means of generating information" refers to technologies and methods for automatically creating new content and information by utilizing learned trends and patterns.

[0473] "Methods for automatic publication" refer to technologies and methods for automatically posting generated information to information exchange services based on pre-set conditions and schedules.

[0474] "Participation data" refers to an indicator that shows the degree of user response to and involvement in posts published on an information exchange service.

[0475] "Optimization methods" refer to techniques and methods used to improve the content and timing of future posts and increase efficiency, based on the collected participation data.

[0476] This invention provides an automated system for facilitating marketing activities on an information exchange service. The system includes a series of processes for acquiring data from the information exchange service, performing analysis based on that data, and generating optimal marketing content.

[0477] The server collects past posting data and user interaction data via the information exchange service's API. This includes posts containing specific hashtags and keywords. The collected data is stored in a database, and machine learning algorithms are used for analysis. This allows the server to learn trends from past successes and use them to inform future marketing strategies.

[0478] The server automatically generates new content using a generative AI model based on the learning results. This generation is performed based on specified prompts, enabling the creation of posts that reflect the creator's intentions based on user input.

[0479] For example, if the server receives the prompt "Introducing family activities to enjoy on the weekend," the generative AI model will create post content that aligns with this theme. This content may include information relevant to the season and local events.

[0480] The device automatically posts content provided by the server to an information exchange service based on a set time. This allows users to efficiently reach their target audience through an automated process.

[0481] Furthermore, the server collects and analyzes participation data for published content in real time. Based on this analysis, future posts and schedules can be optimized to achieve greater effectiveness. Users can use the dashboard to review this data and fine-tune their strategies.

[0482] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0483] Step 1:

[0484] The server collects past posting data and user behavior data based on specific hashtags and keywords through an information exchange service API. The input is the specified hashtags and keywords, and the output is the corresponding dataset. Data processing includes filtering and cleansing of irrelevant data.

[0485] Step 2:

[0486] The server stores the collected data in a database and applies data analysis and machine learning algorithms to learn trends. The input here is a processed dataset, and the output is an extracted pattern or trend model. Specifically, the server uses certain analytical tools to identify data clusters.

[0487] Step 3:

[0488] The server uses a generative AI model based on the learning results to automatically generate new posted content. The input is a trend model and a prompt sentence for generation, and the output is the generated content text. Specifically, the server calls the AI ​​model to execute the natural language generation process based on the prompt sentence.

[0489] Step 4:

[0490] The server generates content and sends it to the terminal based on a pre-configured schedule for preparation. The input is the generated content text and schedule information, and the output is the terminal's readiness status for posting. The terminal then verifies its settings to ensure posting can be done at the specified time.

[0491] Step 5:

[0492] The device automatically posts content to an information exchange service at a specified time. The input consists of content ready for posting and schedule information, while the output is the actual posted content. Specifically, the device executes the posting via an API and verifies the posting success.

[0493] Step 6:

[0494] The server collects and analyzes participation data for published posts in real time. The input is user reaction data to the posts (e.g., number of likes, number of comments), and the output is analyzed performance evaluation data. Specifically, the server aggregates and compares participation data to identify effective posting patterns.

[0495] Step 7:

[0496] The server proposes new, optimized content and posting schedules based on the analysis results. The input is performance evaluation data, and the output is an optimized marketing plan. Specifically, the server automatically generates suggestions based on the analysis results and notifies the user.

[0497] (Application Example 1)

[0498] 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."

[0499] Traditional marketing activities using social networking services suffer from inefficiencies due to the reliance on manual management and optimization of advertising campaigns. Furthermore, the lack of real-time data analysis and content optimization prevents advertisers from maximizing their effectiveness.

[0500] 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.

[0501] In this invention, the server includes means for acquiring historical data and learning patterns, means for generating new content, and means for providing content and information from a mobile device. This enables efficient management of advertising campaigns, real-time data analysis, and rapid content optimization.

[0502] "Past social networking service data" refers to information including text, images, videos, and accompanying user reactions posted on social networking services within a specific period of time prior to the current date.

[0503] "Methods for learning patterns" refer to algorithms and techniques for analyzing past data to identify relevant information and trends.

[0504] "Means of generating new content" refers to the process of creating new posts by utilizing algorithms and generative models based on past learning results.

[0505] "Methods for automatically publishing on social networking services" refer to methods of posting generated content to social networking services (SNS) at a set time without requiring manual operation.

[0506] "Means for collecting and analyzing engagement data" refers to technologies that capture and analyze user reactions and actions (likes, comments, shares, etc.) to posts on social media.

[0507] "Optimization methods" refer to techniques used to improve effectiveness by adjusting the content and timing of subsequent posts based on collected data.

[0508] A "portable information terminal" refers to a portable electronic device such as a smartphone or tablet that can display and operate information.

[0509] "Methods for managing and optimizing social media advertising campaigns" refers to the process of planning, implementing, and evaluating advertising activities conducted on social media, and making adjustments to enhance their effectiveness.

[0510] "A means of monitoring in real time and providing information to improve advertising effectiveness" refers to a method of immediately grasping the results of advertising and providing information to be used for improvement and future strategies based on that evaluation.

[0511] In this invention, the server uses the API of a social networking service to retrieve historical data. It primarily collects data on posts, user reactions, and behavior, and stores this data in a database. Using a cloud database such as Amazon RDS allows for secure and efficient data management. Based on the collected data, the server uses Google Cloud AI to perform machine learning and learn patterns. This enables it to recognize trends and patterns derived from the data and generate new content.

[0512] The generated content incorporates seasonal and trending elements based on natural language processing technology, creating content suitable for advertising campaigns. The server then automatically publishes the generated content to social networking services at the optimal time. Devices, such as smartphones and tablets, are equipped with applications to manage and optimize this content, allowing users to check the schedule and content.

[0513] After posting, the server monitors engagement data in real time. It analyzes data such as the number of likes, comments, and shares, and based on the results, provides users with optimized advertising campaign suggestions. This enables efficient and effective marketing activities.

[0514] As a concrete example, when conducting a campaign to promote a new product for the winter season, the server analyzes winter consumer trends based on past data and generates optimal content based on that analysis. Then, it posts to social media at a specified time and tracks user reactions in real time to suggest further optimizations.

[0515] An example of a prompt to input into a generative AI model is, "Based on past winter promotion data, suggest the best social media campaign for this winter."

[0516] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0517] Step 1:

[0518] The server retrieves historical data via the APIs of social networking services. Inputs include conditions based on specific keywords and hashtags, and output includes relevant posts and user response data. This data is then stored in a cloud database using Amazon RDS. This process is designed to improve the efficiency of data collection and prepare for subsequent analysis.

[0519] Step 2:

[0520] The server learns patterns using data stored in a cloud database. The input data consists of past posts and engagement information, which are used to perform machine learning using Google Cloud AI. The learned patterns are output and used as foundational information for analyzing new trends and user behavior.

[0521] Step 3:

[0522] The server generates new content using a pre-trained model. This process involves receiving seasonal information, recent trends, and target product details as input, which is then used by a generative AI model employing natural language processing techniques to create advertising content. The output consists of text and visuals suitable for the campaign, preparing for the next posting schedule.

[0523] Step 4:

[0524] The device, specifically the user's smartphone, receives generated content sent from the server and allows the user to review it. The user reviews the schedule and content on the screen and makes adjustments or approvals as needed. The input is the generated content, and the user's actions are sent to the server as feedback.

[0525] Step 5:

[0526] The server automatically posts user-approved content to social networking services at the optimal time set. In this process, the input is user approval information and generated content, and the output is posting to social networking services. This enables efficient campaign deployment.

[0527] Step 6:

[0528] The server collects and analyzes engagement data in real time after a post is made. Input includes user reactions such as likes, comments, and shares, which are then analyzed using analytics tools like Google Analytics. Output provides insights to optimize future advertising activities and is provided as feedback to the user.

[0529] 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.

[0530] This invention provides an influencer AI agent system that integrates an emotion engine to recognize user emotions. This system enables effective marketing activities using social networking services by improving the accuracy and effectiveness of content through pattern learning based on past data, automatic generation of new content, and post optimization, as well as analyzing user emotions.

[0531] Data collection and pattern learning

[0532] The server retrieves past posting data from social networking services and stores it in a database. The server then uses this data to learn posting performance patterns. Natural language processing techniques are employed for pattern learning to extract effective content features.

[0533] Emotional analysis using an emotion engine

[0534] The server's sentiment engine analyzes post and comment data and automatically extracts user sentiment. This sentiment data is crucial for understanding how a particular post evokes certain emotions in users.

[0535] New content creation and posting

[0536] The server generates new content optimized for the target market based on learned patterns and extracted sentiment data. The generated content includes elements that take into account the emotional resonance of each user.

[0537] The device automatically posts content received from the server at a specified time, maximizing follower engagement.

[0538] Engagement data collection and optimization

[0539] The server collects and analyzes engagement metrics (e.g., likes, comments, shares) after a post is published. Furthermore, by analyzing this data in conjunction with sentiment data accumulated by the sentiment engine, it optimizes content and scheduling.

[0540] Users can utilize an intuitive dashboard to observe how content is being received and how emotional responses are changing, allowing them to dynamically adjust their marketing strategies. This system provides an environment where deep user understanding and efficient marketing activities can coexist.

[0541] The following describes the processing flow.

[0542] Step 1:

[0543] The server uses the API of social networking services to collect past posting data. This data includes text content, posting time, number of likes, number of comments, etc. The server filters and stores the data based on specific criteria.

[0544] Step 2:

[0545] The server uses collected data to perform pattern learning. Natural language processing algorithms are used to analyze the linguistic features and success patterns of posts, training the model. The model identifies the characteristics of posts that are effective in gaining followers.

[0546] Step 3:

[0547] The server's sentiment engine analyzes the text data of posts and comments to extract user emotions. For example, it categorizes them into emotional categories such as "happy," "sad," and "interested." This sentiment data is stored as an important indicator for understanding user reactions.

[0548] Step 4:

[0549] The server generates new post content based on pattern learning results and sentiment data. During generation, it considers emotional resonance and incorporates content that is more likely to resonate with the target user.

[0550] Step 5:

[0551] The device retrieves content sent from the server and automatically posts it to social networking services according to a specified schedule. This ensures the optimal timing for posting.

[0552] Step 6:

[0553] The server collects engagement data after a post is published (e.g., number of likes, shares, and comments). This allows for a quantitative measurement of the user response generated by each post.

[0554] Step 7:

[0555] The server integrates engagement data and sentiment analysis results to analyze the effectiveness of posts. Based on these analysis results, a strategy is developed to optimize future content creation and posting schedules.

[0556] Step 8:

[0557] Users can view post performance data and sentiment analysis results via a dashboard. Based on this, users can improve their marketing strategies and provide feedback.

[0558] (Example 2)

[0559] 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."

[0560] In today's communication infrastructure, there is a demand for providing effective content based on user interests and emotions to maximize response, but achieving this requires considerable effort and experience. In particular, understanding user emotions in real time and optimizing content based on them is not easy. Furthermore, traditional methods suffer from reduced efficiency because content generation and posting schedule optimization are performed separately.

[0561] 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.

[0562] In this invention, the server includes means for acquiring past electronic data via a communication network and learning performance patterns based on that data; means for extracting the user's emotions from text data using an emotion analysis device; and means for adjusting presentations that take emotional resonance into consideration based on the emotion data and response indicators. This makes it possible to generate optimal content according to the user's emotions and adjust the delivery schedule efficiently.

[0563] A "communication network" refers to a structure in which several devices and systems are interconnected in order to exchange information with each other.

[0564] "Electronic data" refers to information that is stored and transmitted in digital format, and this includes text, images, and audio data.

[0565] "Performance patterns" refer to trends and regularities in content and user responses derived from past data.

[0566] "Presentation" refers to content and information provided to the user, including text, images, and videos.

[0567] "Electronic communication infrastructure" refers to the infrastructure and services used to send and receive information in digital format.

[0568] A "release schedule" refers to a plan or timeline of when and how specific content will be published.

[0569] An "emotion analysis device" refers to a device or software that analyzes text data and flow data to automatically determine a person's emotions and emotional tendencies.

[0570] "Response metrics" are numerical representations of user reactions to content, such as the number of "likes" or "comments."

[0571] "Emotional resonance" refers to the emotional impact and degree of empathy that content has on users.

[0572] This invention relates to a system for users to effectively deliver content on existing electronic communication infrastructure. The server acquires past electronic data through the communication network and learns performance patterns based on it. This learning utilizes natural language processing technology and generative AI models, such as the Python NLP libraries spaCy and NLTK, or OpenAI's GPT-3 as a generative AI model. This allows the system to predict user reactions from past content and automatically generate effective new content.

[0573] The server uses an emotion analysis device to extract user emotions from text data and combines this emotion data with generated content to adjust the optimal presentation to evoke emotional resonance in the target user. The terminal automatically transmits the content received from the server over the electronic communication infrastructure according to a specific transmission schedule. This allows users to efficiently publish content and obtain the maximum response.

[0574] For example, suppose a user wants to promote eco-friendly products to followers who are interested in environmental protection. In this case, they can input the following prompt into the AI ​​model to generate new content.

[0575] "Create emotionally resonant content about our new eco-friendly product. The target audience is followers who are interested in environmental issues."

[0576] This system allows users to provide content based on a deeper understanding and to conduct effective marketing activities targeting their audience.

[0577] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0578] Step 1:

[0579] The server retrieves historical electronic data from social networking platforms via a communication network. The input consists of past posts and comments. The server uses an API to collect this data and store it in a database. During this process, the data includes the timestamp of each post, the user ID, and the number of interactions that occurred. The output is the stored database entries.

[0580] Step 2:

[0581] The server learns performance patterns based on stored historical data. The input is the data stored in step 1. The server analyzes the data using natural language processing techniques and extracts frequently occurring keywords and features of posts that elicited positive responses. The output is the extracted feature patterns. For example, the Python NLP library spaCy is used to identify keywords from the text of posts.

[0582] Step 3:

[0583] The server uses an emotion analyzer to extract user emotions from text data. The input is the posts and comments obtained in step 1. Sentiment analysis classifies the text as either positive, negative, or neutral. A machine learning algorithm is used in this process to calculate an emotion score. The output is emotion data indicating the user's emotions.

[0584] Step 4:

[0585] The server inputs prompt sentences into a generative AI model based on learned patterns and sentiment data, generating new content. The input consists of patterns from step 2 and sentiment data from step 3. The server uses a generative AI model (e.g., GPT-3) to generate content tailored to the user's target market and adjusts it to enhance emotional resonance. The output is the newly generated content.

[0586] Step 5:

[0587] The device automatically posts new content received from the server to the social networking platform according to the posting schedule. The input consists of the content generated in step 4 and the optimized posting schedule. The device uses a scheduling system to post content during times when followers are most active. The output is the published content.

[0588] Step 6:

[0589] The server collects and analyzes reaction metrics available after posting. Inputs include reaction metrics such as likes, comments, and shares. The server uses this data to further optimize future content creation and posting schedules. The output is optimized strategic data, which is then used to improve future posting activities.

[0590] (Application Example 2)

[0591] 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."

[0592] In modern communication services, it is crucial that advertisements are delivered to users in an effective and targeted manner. However, conventional systems do not adequately consider users' emotions and psychological states when selecting advertisements, making it difficult to maximize the effectiveness of advertising.

[0593] 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. In this invention, the server includes means for acquiring past communication data and learning patterns based on the relevant data, means for automatically publishing the generated information on the communication service, and emotion analysis means for analyzing the user's emotions. This makes it possible to select and display advertisements that are appropriate to the user's current situation in real time.

[0594] "Communication data" refers to information about a user's activities on a communication service.

[0595] "Means for learning patterns" refer to methods and devices for analyzing features in past communication data and extracting regularities.

[0596] "Means of generating new information" refers to functions that create content and advertisements for users based on learned patterns.

[0597] "Methods for automatic publication" refer to a mechanism for automatically distributing generated information over a communication service based on set conditions.

[0598] "Engagement data" refers to data about user reactions and behaviors obtained after information is made public.

[0599] "Methods for optimizing the release schedule and information content based on analysis results" refers to methods for analyzing collected engagement data and adjusting the timing and content of information distribution.

[0600] "Emotional analysis means" refers to a technology or device that determines a user's emotional state from their words, actions, and facial expressions.

[0601] "Means of selecting and displaying advertisements" refers to a system that selects and provides advertisements that are appropriate to the user's emotional state.

[0602] This invention relates to a system for delivering advertisements that are adapted to the emotional state of users. To realize this system, the following specific configurations and procedures are included.

[0603] The server acquires data from past communication services and learns patterns based on that information. This involves using natural language processing techniques and machine learning algorithms to analyze specific regularities and user trends. Specifically, it utilizes Python's NLTK and various machine learning libraries.

[0604] Based on the learned results, new content and advertisements are generated. Using a generative AI model, information tailored to the user's interests and emotions is automatically created. The generated information is delivered via smartphones and smart glasses according to set conditions. Communication service APIs and advertising delivery systems are utilized for information distribution.

[0605] The terminal monitors user reactions and collects engagement data after the information is released. This data includes the number of ratings, responses, and shares, and serves as material for data analysis. The server analyzes the collected data and optimizes the distribution schedule and information content.

[0606] Furthermore, the device uses its camera and microphone to perform emotion analysis of the user. Specifically, it analyzes facial expressions and voice using face recognition APIs and voice analysis APIs to identify emotional states. For example, it can perform emotion analysis in real time by utilizing Google's Face Detection API and Speech-to-Text API.

[0607] Based on the analysis results, the server selects and displays the most relevant advertisements to the user. By providing the selected advertisements with content and timing tailored to the user, it is possible to enhance the effectiveness of the advertisements.

[0608] As a concrete example, if a user is browsing the news through smart glasses and an expression of surprise is detected, an advertisement for a new product corresponding to that emotion will be automatically displayed. The generative AI model supporting this mechanism uses prompts such as, "Analyze the user's emotions in real time and suggest advertising content that matches their emotional state." This improves the accuracy of ad delivery and user engagement.

[0609] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0610] Step 1:

[0611] The server retrieves past communication data through the communication service's API. This retrieved data includes user posts and responses. Using this data, the server employs natural language processing techniques to learn patterns. This pattern learning analyzes information trends and user behavior patterns, which are then used as input for the next step.

[0612] Step 2:

[0613] The server uses a generative AI model to generate new information based on learned patterns. In this process, the generative AI model is input with the prompt, "Analyze the user's emotions in real time and suggest advertising content that matches their emotional state." Based on this, the model outputs content that resonates with the user's expectations and emotions.

[0614] Step 3:

[0615] The server automatically publishes the generated information over the communication service. The timing of information publication is determined based on conditions pre-configured by the server. This publication displays the information on the user's device, initiating the first stage of engagement.

[0616] Step 4:

[0617] The device monitors user behavior after publication and collects engagement data. This data includes ratings, reactions, and shares. The device sends this data to a server for use in the next analysis step.

[0618] Step 5:

[0619] The server analyzes the collected engagement data. This analysis uses data processing techniques to evaluate the degree of engagement and effectiveness. Based on the analysis results, the server optimizes the information release schedule and content again. This will be reflected in the next information distribution.

[0620] Step 6:

[0621] The device uses its camera and microphone to analyze the user's emotions in real time. A facial recognition API and a voice analysis API analyze this data to identify the user's current emotional state. This emotional state is sent to a server and used as a reference for ad selection.

[0622] Step 7:

[0623] Based on the sentiment analysis results received, the server selects the most suitable advertisement for the user and determines which advertisement to display. In this process, the server selects the appropriate content from a pre-generated list of advertisements and displays it on the user's device. As a result, the advertisement deemed most effective for the user is delivered.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] [Fourth Embodiment]

[0628] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0629] 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.

[0630] 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).

[0631] 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.

[0632] 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.

[0633] 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).

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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".

[0641] This invention provides an influencer AI agent system for automatically and efficiently conducting marketing activities using social networking services. This system utilizes past social networking service data and learns patterns to generate new content and automate posting. Furthermore, it analyzes engagement data to suggest optimal content and schedules.

[0642] Data collection and learning

[0643] The server utilizes the APIs of social media platforms to retrieve data on past posts and user actions. This includes posts related to specific hashtags and keywords. The server stores this data in a database and uses pattern recognition technology for learning.

[0644] Content generation

[0645] The server automatically generates new posted content based on the learning results. The generation process uses natural language processing technology to provide diverse content that takes into account the season and the latest trends. This includes, for example, product promotional content and user-participation campaign content.

[0646] Automated posting and management

[0647] The device automatically posts content provided by the server to social media based on a pre-set schedule. This eliminates the need for companies to manually post content and maximizes the potential for follower growth at specific times.

[0648] Engagement analysis and optimization

[0649] The server collects engagement data (likes, comments, shares, etc.) after a post is published. This allows the server to analyze the performance of each post and monitor user behavior. Based on the results, the server suggests more effective posting schedules and content, optimizing the process.

[0650] Through the dashboard, users can view real-time engagement data and follower growth, and adjust their marketing strategies accordingly. This is extremely helpful for companies lacking the necessary expertise to conduct effective influencer marketing at a low cost.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] The server uses the APIs of social networking services to collect past posting data. Specifically, it targets posts related to certain keywords or hashtags and collects engagement metrics (e.g., likes, comments, shares) for these posts.

[0654] Step 2:

[0655] The server collects data and stores it in a database. Then, the stored data is analyzed, and machine learning models are used to extract patterns and features that are effective for gaining followers. This process utilizes natural language processing techniques.

[0656] Step 3:

[0657] The server generates new content based on learned patterns. This generation takes into account specific themes and trends to create content that will interest followers. The generated content can be tested with different variations.

[0658] Step 4:

[0659] The server determines the optimal posting schedule based on the content it generates. Based on the determined schedule, the device automatically posts to the corresponding SNS account.

[0660] Step 5:

[0661] The server collects engagement data (e.g., number of likes, shares, and comments) again after a post is published. This makes it possible to measure the effectiveness of each post.

[0662] Step 6:

[0663] The server analyzes the collected engagement data and extracts optimization patterns for future posts. Based on these results, the system is updated and fed back into the generation of the next post.

[0664] Step 7:

[0665] Users can use the server-provided dashboard to monitor engagement results and follower growth for all their posts. This allows users to adjust their marketing strategies accordingly.

[0666] (Example 1)

[0667] 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".

[0668] Modern businesses are required to identify trends and effective strategies from vast amounts of data in order to conduct effective marketing activities on information exchange services. However, manually collecting and analyzing data is extremely time-consuming and labor-intensive, making it difficult to implement optimal strategies in real time. In particular, there is a need for rapid feedback and quick strategic adjustments based on that data, but there has been a lack of systems to efficiently accomplish this.

[0669] 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.

[0670] In this invention, the server includes means for acquiring past information exchange service data and learning trends based on that data, means for generating new information based on the learning results, and means for automatically publishing the generated information on the information exchange service. This enables efficient and automated data analysis and information generation.

[0671] An "information exchange service" is a platform where individuals and organizations can post and share information online.

[0672] "Data" refers to information posted on information exchange services and records of user behavior.

[0673] A "trend" refers to a general pattern or flow of behavior extracted from past data.

[0674] "Means of learning" refers to technologies and methods that enable machines to automatically analyze collected data and understand patterns.

[0675] "Means of generating information" refers to technologies and methods for automatically creating new content and information by utilizing learned trends and patterns.

[0676] "Methods for automatic publication" refer to technologies and methods for automatically posting generated information to information exchange services based on pre-set conditions and schedules.

[0677] "Participation data" refers to an indicator that shows the degree of user response to and involvement in posts published on an information exchange service.

[0678] "Optimization methods" refer to techniques and methods used to improve the content and timing of future posts and increase efficiency, based on the collected participation data.

[0679] This invention provides an automated system for facilitating marketing activities on an information exchange service. The system includes a series of processes for acquiring data from the information exchange service, performing analysis based on that data, and generating optimal marketing content.

[0680] The server collects past posting data and user interaction data via the information exchange service's API. This includes posts containing specific hashtags and keywords. The collected data is stored in a database, and machine learning algorithms are used for analysis. This allows the server to learn trends from past successes and use them to inform future marketing strategies.

[0681] The server automatically generates new content using a generative AI model based on the learning results. This generation is performed based on specified prompts, enabling the creation of posts that reflect the creator's intentions based on user input.

[0682] For example, if the server receives the prompt "Introducing family activities to enjoy on the weekend," the generative AI model will create post content that aligns with this theme. This content may include information relevant to the season and local events.

[0683] The device automatically posts content provided by the server to an information exchange service based on a set time. This allows users to efficiently reach their target audience through an automated process.

[0684] Furthermore, the server collects and analyzes participation data for published content in real time. Based on this analysis, future posts and schedules can be optimized to achieve greater effectiveness. Users can use the dashboard to review this data and fine-tune their strategies.

[0685] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0686] Step 1:

[0687] The server collects past posting data and user behavior data based on specific hashtags and keywords through an information exchange service API. The input is the specified hashtags and keywords, and the output is the corresponding dataset. Data processing includes filtering and cleansing of irrelevant data.

[0688] Step 2:

[0689] The server stores the collected data in a database and applies data analysis and machine learning algorithms to learn trends. The input here is a processed dataset, and the output is an extracted pattern or trend model. Specifically, the server uses certain analytical tools to identify data clusters.

[0690] Step 3:

[0691] The server uses a generative AI model based on the learning results to automatically generate new posted content. The input is a trend model and a prompt sentence for generation, and the output is the generated content text. Specifically, the server calls the AI ​​model to execute the natural language generation process based on the prompt sentence.

[0692] Step 4:

[0693] The server generates content and sends it to the terminal based on a pre-configured schedule for preparation. The input is the generated content text and schedule information, and the output is the terminal's readiness status for posting. The terminal then verifies its settings to ensure posting can be done at the specified time.

[0694] Step 5:

[0695] The device automatically posts content to an information exchange service at a specified time. The input consists of content ready for posting and schedule information, while the output is the actual posted content. Specifically, the device executes the posting via an API and verifies the posting success.

[0696] Step 6:

[0697] The server collects and analyzes participation data for published posts in real time. The input is user reaction data to the posts (e.g., number of likes, number of comments), and the output is analyzed performance evaluation data. Specifically, the server aggregates and compares participation data to identify effective posting patterns.

[0698] Step 7:

[0699] The server proposes new, optimized content and posting schedules based on the analysis results. The input is performance evaluation data, and the output is an optimized marketing plan. Specifically, the server automatically generates suggestions based on the analysis results and notifies the user.

[0700] (Application Example 1)

[0701] 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".

[0702] Traditional marketing activities using social networking services suffer from inefficiencies due to the reliance on manual management and optimization of advertising campaigns. Furthermore, the lack of real-time data analysis and content optimization prevents advertisers from maximizing their effectiveness.

[0703] 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.

[0704] In this invention, the server includes means for acquiring historical data and learning patterns, means for generating new content, and means for providing content and information from a mobile device. This enables efficient management of advertising campaigns, real-time data analysis, and rapid content optimization.

[0705] "Past social networking service data" refers to information including text, images, videos, and accompanying user reactions posted on social networking services within a specific period of time prior to the current date.

[0706] "Methods for learning patterns" refer to algorithms and techniques for analyzing past data to identify relevant information and trends.

[0707] "Means of generating new content" refers to the process of creating new posts by utilizing algorithms and generative models based on past learning results.

[0708] "Methods for automatically publishing on social networking services" refer to methods of posting generated content to social networking services (SNS) at a set time without requiring manual operation.

[0709] "Means for collecting and analyzing engagement data" refers to technologies that capture and analyze user reactions and actions (likes, comments, shares, etc.) to posts on social media.

[0710] "Optimization methods" refer to techniques used to improve effectiveness by adjusting the content and timing of subsequent posts based on collected data.

[0711] A "portable information terminal" refers to a portable electronic device such as a smartphone or tablet that can display and operate information.

[0712] "Methods for managing and optimizing social media advertising campaigns" refers to the process of planning, implementing, and evaluating advertising activities conducted on social media, and making adjustments to enhance their effectiveness.

[0713] "A means of monitoring in real time and providing information to improve advertising effectiveness" refers to a method of immediately grasping the results of advertising and providing information to be used for improvement and future strategies based on that evaluation.

[0714] In this invention, the server uses the API of a social networking service to retrieve historical data. It primarily collects data on posts, user reactions, and behavior, and stores this data in a database. Using a cloud database such as Amazon RDS allows for secure and efficient data management. Based on the collected data, the server uses Google Cloud AI to perform machine learning and learn patterns. This enables it to recognize trends and patterns derived from the data and generate new content.

[0715] The generated content incorporates seasonal and trending elements based on natural language processing technology, creating content suitable for advertising campaigns. The server then automatically publishes the generated content to social networking services at the optimal time. Devices, such as smartphones and tablets, are equipped with applications to manage and optimize this content, allowing users to check the schedule and content.

[0716] After posting, the server monitors engagement data in real time. It analyzes data such as the number of likes, comments, and shares, and based on the results, provides users with optimized advertising campaign suggestions. This enables efficient and effective marketing activities.

[0717] As a concrete example, when conducting a campaign to promote a new product for the winter season, the server analyzes winter consumer trends based on past data and generates optimal content based on that analysis. Then, it posts to social media at a specified time and tracks user reactions in real time to suggest further optimizations.

[0718] An example of a prompt to input into a generative AI model is, "Based on past winter promotion data, suggest the best social media campaign for this winter."

[0719] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0720] Step 1:

[0721] The server retrieves historical data via the APIs of social networking services. Inputs include conditions based on specific keywords and hashtags, and output includes relevant posts and user response data. This data is then stored in a cloud database using Amazon RDS. This process is designed to improve the efficiency of data collection and prepare for subsequent analysis.

[0722] Step 2:

[0723] The server learns patterns using data stored in a cloud database. The input data consists of past posts and engagement information, which are used to perform machine learning using Google Cloud AI. The learned patterns are output and used as foundational information for analyzing new trends and user behavior.

[0724] Step 3:

[0725] The server generates new content using a pre-trained model. This process involves receiving seasonal information, recent trends, and target product details as input, which is then used by a generative AI model employing natural language processing techniques to create advertising content. The output consists of text and visuals suitable for the campaign, preparing for the next posting schedule.

[0726] Step 4:

[0727] The device, specifically the user's smartphone, receives generated content sent from the server and allows the user to review it. The user reviews the schedule and content on the screen and makes adjustments or approvals as needed. The input is the generated content, and the user's actions are sent to the server as feedback.

[0728] Step 5:

[0729] The server automatically posts user-approved content to social networking services at the optimal time set. In this process, the input is user approval information and generated content, and the output is posting to social networking services. This enables efficient campaign deployment.

[0730] Step 6:

[0731] The server collects and analyzes engagement data in real time after a post is made. Input includes user reactions such as likes, comments, and shares, which are then analyzed using analytics tools like Google Analytics. Output provides insights to optimize future advertising activities and is provided as feedback to the user.

[0732] 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.

[0733] This invention provides an influencer AI agent system that integrates an emotion engine to recognize user emotions. This system enables effective marketing activities using social networking services by improving the accuracy and effectiveness of content through pattern learning based on past data, automatic generation of new content, and post optimization, as well as analyzing user emotions.

[0734] Data collection and pattern learning

[0735] The server retrieves past posting data from social networking services and stores it in a database. The server then uses this data to learn posting performance patterns. Natural language processing techniques are employed for pattern learning to extract effective content features.

[0736] Emotional analysis using an emotion engine

[0737] The server's sentiment engine analyzes post and comment data and automatically extracts user sentiment. This sentiment data is crucial for understanding how a particular post evokes certain emotions in users.

[0738] New content creation and posting

[0739] The server generates new content optimized for the target market based on learned patterns and extracted sentiment data. The generated content includes elements that take into account the emotional resonance of each user.

[0740] The device automatically posts content received from the server at a specified time, maximizing follower engagement.

[0741] Engagement data collection and optimization

[0742] The server collects and analyzes engagement metrics (e.g., likes, comments, shares) after a post is published. Furthermore, by analyzing this data in conjunction with sentiment data accumulated by the sentiment engine, it optimizes content and scheduling.

[0743] Users can utilize an intuitive dashboard to observe how content is being received and how emotional responses are changing, allowing them to dynamically adjust their marketing strategies. This system provides an environment where deep user understanding and efficient marketing activities can coexist.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] The server uses the API of social networking services to collect past posting data. This data includes text content, posting time, number of likes, number of comments, etc. The server filters and stores the data based on specific criteria.

[0747] Step 2:

[0748] The server uses collected data to perform pattern learning. Natural language processing algorithms are used to analyze the linguistic features and success patterns of posts, training the model. The model identifies the characteristics of posts that are effective in gaining followers.

[0749] Step 3:

[0750] The server's sentiment engine analyzes the text data of posts and comments to extract user emotions. For example, it categorizes them into emotional categories such as "happy," "sad," and "interested." This sentiment data is stored as an important indicator for understanding user reactions.

[0751] Step 4:

[0752] The server generates new post content based on pattern learning results and sentiment data. During generation, it considers emotional resonance and incorporates content that is more likely to resonate with the target user.

[0753] Step 5:

[0754] The device retrieves content sent from the server and automatically posts it to social networking services according to a specified schedule. This ensures the optimal timing for posting.

[0755] Step 6:

[0756] The server collects engagement data after a post is published (e.g., number of likes, shares, and comments). This allows for a quantitative measurement of the user response generated by each post.

[0757] Step 7:

[0758] The server integrates engagement data and sentiment analysis results to analyze the effectiveness of posts. Based on these analysis results, a strategy is developed to optimize future content creation and posting schedules.

[0759] Step 8:

[0760] Users can view post performance data and sentiment analysis results via a dashboard. Based on this, users can improve their marketing strategies and provide feedback.

[0761] (Example 2)

[0762] 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".

[0763] In today's communication infrastructure, there is a demand for providing effective content based on user interests and emotions to maximize response, but achieving this requires considerable effort and experience. In particular, understanding user emotions in real time and optimizing content based on them is not easy. Furthermore, traditional methods suffer from reduced efficiency because content generation and posting schedule optimization are performed separately.

[0764] 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.

[0765] In this invention, the server includes means for acquiring past electronic data via a communication network and learning performance patterns based on that data; means for extracting the user's emotions from text data using an emotion analysis device; and means for adjusting presentations that take emotional resonance into consideration based on the emotion data and response indicators. This makes it possible to generate optimal content according to the user's emotions and adjust the delivery schedule efficiently.

[0766] A "communication network" refers to a structure in which several devices and systems are interconnected in order to exchange information with each other.

[0767] "Electronic data" refers to information that is stored and transmitted in digital format, and this includes text, images, and audio data.

[0768] "Performance patterns" refer to trends and regularities in content and user responses derived from past data.

[0769] "Presentation" refers to content and information provided to the user, including text, images, and videos.

[0770] "Electronic communication infrastructure" refers to the infrastructure and services used to send and receive information in digital format.

[0771] A "release schedule" refers to a plan or timeline of when and how specific content will be published.

[0772] An "emotion analysis device" refers to a device or software that analyzes text data and flow data to automatically determine a person's emotions and emotional tendencies.

[0773] "Response metrics" are numerical representations of user reactions to content, such as the number of "likes" or "comments."

[0774] "Emotional resonance" refers to the emotional impact and degree of empathy that content has on users.

[0775] This invention relates to a system for users to effectively deliver content on existing electronic communication infrastructure. The server acquires past electronic data through the communication network and learns performance patterns based on it. This learning utilizes natural language processing technology and generative AI models, such as the Python NLP libraries spaCy and NLTK, or OpenAI's GPT-3 as a generative AI model. This allows the system to predict user reactions from past content and automatically generate effective new content.

[0776] The server uses an emotion analysis device to extract user emotions from text data and combines this emotion data with generated content to adjust the optimal presentation to evoke emotional resonance in the target user. The terminal automatically transmits the content received from the server over the electronic communication infrastructure according to a specific transmission schedule. This allows users to efficiently publish content and obtain the maximum response.

[0777] For example, suppose a user wants to promote eco-friendly products to followers who are interested in environmental protection. In this case, they can input the following prompt into the AI ​​model to generate new content.

[0778] "Create emotionally resonant content about our new eco-friendly product. The target audience is followers who are interested in environmental issues."

[0779] This system allows users to provide content based on a deeper understanding and to conduct effective marketing activities targeting their audience.

[0780] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0781] Step 1:

[0782] The server retrieves historical electronic data from social networking platforms via a communication network. The input consists of past posts and comments. The server uses an API to collect this data and store it in a database. During this process, the data includes the timestamp of each post, the user ID, and the number of interactions that occurred. The output is the stored database entries.

[0783] Step 2:

[0784] The server learns performance patterns based on stored historical data. The input is the data stored in step 1. The server analyzes the data using natural language processing techniques and extracts frequently occurring keywords and features of posts that elicited positive responses. The output is the extracted feature patterns. For example, the Python NLP library spaCy is used to identify keywords from the text of posts.

[0785] Step 3:

[0786] The server uses an emotion analyzer to extract user emotions from text data. The input is the posts and comments obtained in step 1. Sentiment analysis classifies the text as either positive, negative, or neutral. A machine learning algorithm is used in this process to calculate an emotion score. The output is emotion data indicating the user's emotions.

[0787] Step 4:

[0788] The server inputs prompt sentences into a generative AI model based on learned patterns and sentiment data, generating new content. The input consists of patterns from step 2 and sentiment data from step 3. The server uses a generative AI model (e.g., GPT-3) to generate content tailored to the user's target market and adjusts it to enhance emotional resonance. The output is the newly generated content.

[0789] Step 5:

[0790] The device automatically posts new content received from the server to the social networking platform according to the posting schedule. The input consists of the content generated in step 4 and the optimized posting schedule. The device uses a scheduling system to post content during times when followers are most active. The output is the published content.

[0791] Step 6:

[0792] The server collects and analyzes reaction metrics available after posting. Inputs include reaction metrics such as likes, comments, and shares. The server uses this data to further optimize future content creation and posting schedules. The output is optimized strategic data, which is then used to improve future posting activities.

[0793] (Application Example 2)

[0794] 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".

[0795] In modern communication services, it is crucial that advertisements are delivered to users in an effective and targeted manner. However, conventional systems do not adequately consider users' emotions and psychological states when selecting advertisements, making it difficult to maximize the effectiveness of advertising.

[0796] 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. In this invention, the server includes means for acquiring past communication data and learning patterns based on the relevant data, means for automatically publishing the generated information on the communication service, and emotion analysis means for analyzing the user's emotions. This makes it possible to select and display advertisements that are appropriate to the user's current situation in real time.

[0797] "Communication data" refers to information about a user's activities on a communication service.

[0798] "Means for learning patterns" refer to methods and devices for analyzing features in past communication data and extracting regularities.

[0799] "Means of generating new information" refers to functions that create content and advertisements for users based on learned patterns.

[0800] "Methods for automatic publication" refer to a mechanism for automatically distributing generated information over a communication service based on set conditions.

[0801] "Engagement data" refers to data about user reactions and behaviors obtained after information is made public.

[0802] "Methods for optimizing the release schedule and information content based on analysis results" refers to methods for analyzing collected engagement data and adjusting the timing and content of information distribution.

[0803] "Emotional analysis means" refers to a technology or device that determines a user's emotional state from their words, actions, and facial expressions.

[0804] "Means of selecting and displaying advertisements" refers to a system that selects and provides advertisements that are appropriate to the user's emotional state.

[0805] This invention relates to a system for delivering advertisements that are adapted to the emotional state of users. To realize this system, the following specific configurations and procedures are included.

[0806] The server acquires data from past communication services and learns patterns based on that information. This involves using natural language processing techniques and machine learning algorithms to analyze specific regularities and user trends. Specifically, it utilizes Python's NLTK and various machine learning libraries.

[0807] Based on the learned results, new content and advertisements are generated. Using a generative AI model, information tailored to the user's interests and emotions is automatically created. The generated information is delivered via smartphones and smart glasses according to set conditions. Communication service APIs and advertising delivery systems are utilized for information distribution.

[0808] The terminal monitors user reactions and collects engagement data after the information is released. This data includes the number of ratings, responses, and shares, and serves as material for data analysis. The server analyzes the collected data and optimizes the distribution schedule and information content.

[0809] Furthermore, the device uses its camera and microphone to perform emotion analysis of the user. Specifically, it analyzes facial expressions and voice using face recognition APIs and voice analysis APIs to identify emotional states. For example, it can perform emotion analysis in real time by utilizing Google's Face Detection API and Speech-to-Text API.

[0810] Based on the analysis results, the server selects and displays the most relevant advertisements to the user. By providing the selected advertisements with content and timing tailored to the user, it is possible to enhance the effectiveness of the advertisements.

[0811] As a concrete example, if a user is browsing the news through smart glasses and an expression of surprise is detected, an advertisement for a new product corresponding to that emotion will be automatically displayed. The generative AI model supporting this mechanism uses prompts such as, "Analyze the user's emotions in real time and suggest advertising content that matches their emotional state." This improves the accuracy of ad delivery and user engagement.

[0812] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0813] Step 1:

[0814] The server retrieves past communication data through the communication service's API. This retrieved data includes user posts and responses. Using this data, the server employs natural language processing techniques to learn patterns. This pattern learning analyzes information trends and user behavior patterns, which are then used as input for the next step.

[0815] Step 2:

[0816] The server uses a generative AI model to generate new information based on learned patterns. In this process, the generative AI model is input with the prompt, "Analyze the user's emotions in real time and suggest advertising content that matches their emotional state." Based on this, the model outputs content that resonates with the user's expectations and emotions.

[0817] Step 3:

[0818] The server automatically publishes the generated information over the communication service. The timing of information publication is determined based on conditions pre-configured by the server. This publication displays the information on the user's device, initiating the first stage of engagement.

[0819] Step 4:

[0820] The device monitors user behavior after publication and collects engagement data. This data includes ratings, reactions, and shares. The device sends this data to a server for use in the next analysis step.

[0821] Step 5:

[0822] The server analyzes the collected engagement data. This analysis uses data processing techniques to evaluate the degree of engagement and effectiveness. Based on the analysis results, the server optimizes the information release schedule and content again. This will be reflected in the next information distribution.

[0823] Step 6:

[0824] The device uses its camera and microphone to analyze the user's emotions in real time. A facial recognition API and a voice analysis API analyze this data to identify the user's current emotional state. This emotional state is sent to a server and used as a reference for ad selection.

[0825] Step 7:

[0826] Based on the sentiment analysis results received, the server selects the most suitable advertisement for the user and determines which advertisement to display. In this process, the server selects the appropriate content from a pre-generated list of advertisements and displays it on the user's device. As a result, the advertisement deemed most effective for the user is delivered.

[0827] 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.

[0828] 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.

[0829] 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 robot 414.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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."

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] The following is further disclosed regarding the embodiments described above.

[0849] (Claim 1)

[0850] A method for acquiring past social networking service data and learning patterns based on that data,

[0851] A means for generating new content based on the aforementioned learning results,

[0852] A means of automatically publishing the generated content on social networking services,

[0853] Methods for collecting and analyzing engagement data after launch,

[0854] Methods to optimize the publication schedule and content based on the analysis results,

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, wherein the acquisition of social networking service data targets past posts based on specific conditions.

[0858] (Claim 3)

[0859] The system according to claim 1, wherein the analysis of the engagement data includes the number of likes, comments, and shares.

[0860] "Example 1"

[0861] (Claim 1)

[0862] A means of acquiring past information exchange service data and learning trends based on that data,

[0863] A means for generating new information based on the aforementioned learning results,

[0864] A means of automatically publishing the generated information on an information exchange service,

[0865] Methods for collecting and analyzing participation data after publication,

[0866] A means to optimize the release schedule and information content based on the analysis results,

[0867] A means for users to check data in real time and adjust their strategies,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, wherein the acquisition of the aforementioned information exchange service data targets past posts based on specific criteria.

[0871] (Claim 3)

[0872] The system according to claim 1, wherein the analysis of the participation data includes the number of approvals, the number of opinions, and the number of shares.

[0873] "Application Example 1"

[0874] (Claim 1)

[0875] A method for acquiring past social networking service data and learning patterns based on that data,

[0876] A means for generating new content based on the aforementioned learning results,

[0877] A means of automatically publishing the generated content on social networking services,

[0878] Methods for collecting and analyzing engagement data after launch,

[0879] Methods to optimize the publication schedule and content based on the analysis results,

[0880] A means of managing and optimizing SNS advertising campaigns using mobile devices,

[0881] A means of monitoring engagement data in real time and providing information to improve advertising effectiveness,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, wherein the acquisition of social networking service data targets past posts based on specific conditions and notifies the user of content suggestions via a mobile device.

[0885] (Claim 3)

[0886] The system according to claim 1, wherein the analysis of engagement data includes, in addition to the number of likes, comments, and shares, optimization suggestions are made using real-time engagement data.

[0887] "Example 2 of combining an emotion engine"

[0888] (Claim 1)

[0889] A means of acquiring past electronic data via a communication network and learning performance patterns based on that data,

[0890] A means of using a computing device to automatically generate presentations based on the aforementioned learning results,

[0891] A means of automatically transmitting the generated presentation on an electronic communication infrastructure,

[0892] A means of collecting and analyzing user response indicators after transmission,

[0893] A means to optimize the communication schedule and content of presentations based on the analysis results,

[0894] A means of extracting a user's emotions from text data using an emotion analysis device,

[0895] A means for adjusting presentations that take emotional resonance into account based on emotional data and response indicators,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, wherein the acquisition of the electronic data targets past information based on specific conditions.

[0899] (Claim 3)

[0900] The system according to claim 1, wherein the analysis of the response indicators includes the number of approvals, the number of opinions, and the number of disseminations.

[0901] "Application example 2 when combining with an emotional engine"

[0902] (Claim 1)

[0903] A means of acquiring past communication data and learning patterns based on that data,

[0904] A means for generating new information based on the aforementioned learning results,

[0905] A means of automatically publishing the generated information on a communication service,

[0906] Methods for collecting and analyzing engagement data after publication,

[0907] A means to optimize the release schedule and information content based on the analysis results,

[0908] A means of analyzing the emotions of users,

[0909] A means for selecting and displaying the most appropriate advertisement using the aforementioned sentiment analysis results,

[0910] A system that includes this.

[0911] (Claim 2)

[0912] The system according to claim 1, wherein the acquisition of the aforementioned communication data targets past information based on specific conditions.

[0913] (Claim 3)

[0914] The system according to claim 1, wherein the analysis of the involvement data includes the number of evaluations, the number of responses, and the number of shares. [Explanation of Symbols]

[0915] 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 acquiring past social networking service data and learning patterns based on that data, A means for generating new content based on the aforementioned learning results, A means of automatically publishing the generated content on social networking services, Methods for collecting and analyzing engagement data after launch, Methods to optimize the publication schedule and content based on the analysis results, A means of managing and optimizing SNS advertising campaigns using mobile devices, A means of monitoring engagement data in real time and providing information to improve advertising effectiveness, A system that includes this.

2. The system according to claim 1, wherein the acquisition of social networking service data targets past posts based on specific conditions and notifies the user of content suggestions via a mobile device.

3. The system according to claim 1, wherein the analysis of the engagement data includes, in addition to the number of likes, comments, and shares, it uses real-time engagement data to make optimization suggestions.

Images