system

Abstract

We provide the system. [Solution] A means for generating information based on user-defined goals and target information using generative artificial intelligence, A means of automatically disseminating generated information to multiple social communication platforms, A means for collecting and analyzing user response data to determine the optimal transmission time and frequency, A means by which the generated information is regenerated or modified based on the user's will, A means of analyzing the results data after the information is sent and creating a report, A system that includes means for calculating a transmission schedule using historical time-series data.

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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 and branding activities that utilize current social communication networks, the time for content creation has increased and the dependence on external resources has grown, while problems such as flaming due to inappropriate posted content frequently occur. In such a situation, there is a need for a method to efficiently and safely operate social communication networks and comprehensively solve those problems.

Means for Solving the Problems

[0005] This invention provides a system that automatically generates engaging content using artificial intelligence based on user-defined goals and target information. Furthermore, this system automatically posts the generated content to multiple social networking sites and analyzes interaction data to determine the optimal posting time and frequency. In addition, the generated content can be regenerated or modified according to user requests, and subsequent performance data can be acquired and analyzed to generate reports, thereby enabling the proposal of effective posting strategies.

[0006] "Generative artificial intelligence" is an artificial intelligence technology that has the ability to automatically generate content based on user input.

[0007] A "user" is an entity that uses the system to create and post content through social networking.

[0008] "Content" refers to information media such as text, images, and videos posted on social networking platforms.

[0009] A "social network" is an online platform where people can share information and communicate with each other.

[0010] "Interaction data" refers to data related to user activities such as viewing, reacting to, and commenting on posted content.

[0011] "Automated posting" is the process of mechanically posting generated content to a specific platform according to a schedule.

[0012] A "report" is a document that analyzes the performance and impact of content and presents a summary of the results.

[0013] "Performance data" refers to various metrics collected to evaluate the effectiveness of posted content. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

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

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

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The system of the present invention operates by integrating various elements in order to effectively carry out the automatic generation and management of content through social interaction networks. At the heart of the system is a content generation process that utilizes generative artificial intelligence, which automatically generates posts and images that are suitable for the goals and target information specified by the user.

[0036] Users first access the management screen via their device and enter campaign and marketing activity goals, target audience, and other relevant information. This input data is sent to the server and used as the basis for content generation by the generative AI.

[0037] The server runs a generative AI that generates multiple content suggestions based on user input. This allows users to choose the best option from several choices and post it to social networks. The generated content is filtered and adjusted to match the characteristics of the platform used and the interests of the target audience.

[0038] The server then analyzes past user interaction data to calculate the optimal timing for posting. This analysis includes content impressions, engagement rates, and the effectiveness of different posting times, which automatically determine the posting schedule.

[0039] The actual posting is done automatically by the server to various social networking networks according to a predetermined schedule. This process saves time and effort that would otherwise be spent manually, and also improves the accuracy of the posts.

[0040] After submission, the server automatically analyzes the acquired performance data and provides the user with a detailed report. This report includes the results and areas for improvement of the initiative and will be used to formulate future strategies.

[0041] As a concrete example, when a user launches a new product campaign, this system allows them to easily manage everything from content creation and posting to performance analysis in a single, streamlined process. The user simply specifies their target audience and inputs the product's features, and the AI ​​automatically creates compelling ad copy and delivers it at the optimal time. In this way, users can focus on other marketing activities while continuously conducting high-quality promotions.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The device displays the posting campaign settings screen to the user, who then enters information such as goals, target audience, and post theme.

[0045] Step 2:

[0046] Information entered by the user through the terminal is sent to the server, which retrieves it and prepares it as input data for the generating AI.

[0047] Step 3:

[0048] The server runs a generation AI and generates content variations based on the input goal and target information. The generated content is temporarily stored in a database.

[0049] Step 4:

[0050] The server uses analytical tools to analyze past user interaction data and calculate the optimal posting time and frequency.

[0051] Step 5:

[0052] The server creates a series of posting schedules and sets up automated posting tasks based on those schedules.

[0053] Step 6:

[0054] When the scheduled posting time arrives, the server automatically calls the API of the selected social networking service and posts the generated content.

[0055] Step 7:

[0056] Once a post is submitted, the server retrieves interaction data from the social network to measure the effectiveness of the post.

[0057] Step 8:

[0058] The server analyzes the interaction data it acquires using an analysis tool and provides feedback to the user in the form of a report.

[0059] Step 9:

[0060] Users can request content regeneration or modification via their devices as needed, and the server will initiate the regeneration process based on this feedback.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] Traditional content creation and posting processes require users to manually create content tailored to their goals and target audience, and then post it to various social networks at the appropriate time, which is time-consuming and laborious. Furthermore, the cycle of analyzing post-post performance and using that analysis to improve future content tends to be lengthy.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes means for utilizing artificial intelligence to create content based on user-defined goals and target information, means for automatically posting the created content to a network of numerous social interaction groups, and means for collecting and analyzing user response data to determine the optimal posting timing and frequency. This enables users to efficiently create content tailored to their goals and post it to social interaction networks at the optimal time, while also allowing for rapid analysis of post-posting performance and reflection of the results in future work.

[0066] A "user" is someone who utilizes this system, inputting goal and target information and selecting the generated content.

[0067] "Goals" refer to the objectives or results that users hope to achieve when using this system.

[0068] "Target information" refers to data that indicates what audience the content to be generated is intended to appeal to.

[0069] "Content" refers to all material created and posted using generative AI, specifically informational media such as images and text.

[0070] "Generative AI" refers to an artificial intelligence model that automatically generates content based on user input.

[0071] A "social interaction network" refers to an online platform where information is shared and interactions take place among individual users.

[0072] "Posting" refers to the act of making generated content publicly available on a social network.

[0073] "Interaction data" refers to information about user reactions and engagement with posted content.

[0074] "Performance data" refers to information that numerically shows the results and effects of posted content.

[0075] A "report" is a document created based on collected and analyzed data, and includes the results of the campaign and proposals for future strategies.

[0076] The embodiments for carrying out the present invention will be described below.

[0077] This system allows users to easily and automatically generate content based on their self-defined goals and target information. Users first access the system's management screen via their device and input the information necessary for their campaigns and marketing activities. This information serves as the foundational data for content generation using the AI.

[0078] The terminal transmits user input data to the server in real time. The server uses partnered generative AI software to generate content based on the pre-entered information. This generative AI incorporates a large text database and can generate several optimal content options using natural language processing technology.

[0079] The server provides users with generated content proposals, allowing them to select the most suitable content based on their target audience and the characteristics of the social network they use. The server then analyzes past user interaction data to automatically calculate the best timing for posting. This data analysis includes content views, engagement rates, and posting dates.

[0080] Servers with automated posting capabilities post selected content to various social networking networks according to a predetermined schedule. This significantly reduces user effort and enables efficient content management.

[0081] After posting, the server automatically analyzes the acquired performance data and provides the user with a detailed report. This report allows the user to understand the results of their posts and use that information to inform their future marketing strategies.

[0082] For example, a user running a campaign to launch a new sneaker product can simply set their target audience to "men in their 20s" and input the sneaker's features, and the AI ​​will automatically generate compelling ad copy. An example of a prompt might be, "Generate ad copy for this season's new sneakers that will appeal to men in their 20s."

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] Users log in to the system's administration screen via their device and input information about the goals and target audience of their campaign or marketing activity. This input data includes product features, price range, and timing of advertising. This information is then transmitted to the server via the device as basic data for content generation.

[0086] Step 2:

[0087] The server activates a generative AI model based on the user's input data. The server inputs this as a prompt to the generative AI, which then begins generating content suggestions tailored to the user's needs. For example, the prompt "Generate advertising copy for sneakers that appeals to men in their 20s" might be input to the generative AI. The generative AI then uses natural language processing techniques to create the advertising copy. In this step, the output is the generated content suggestion.

[0088] Step 3:

[0089] The generated content proposals are presented to the user by the server, and a preview is displayed for the user to evaluate the options. This allows the user to compare different content proposals and select the one that best suits their needs. The selected content proposal is then considered ready for publication.

[0090] Step 4:

[0091] The server collects and analyzes historical user interaction data. This allows the server to consider the historical performance data of posted content and calculate the optimal posting time. Factors such as impression count, engagement rate, and the impact of posting time are used in the calculation. The calculated optimal posting time is output as scheduling information.

[0092] Step 5:

[0093] The server automatically posts selected content to the social network based on a predetermined schedule. The output here is the actual post on the network. This step eliminates manual effort and enables efficient information distribution.

[0094] Step 6:

[0095] After posting is complete, the server automatically collects and analyzes the post's performance data. This evaluates the post's effectiveness and areas for improvement, and generates a detailed report. This report includes data such as views, click-through rates, and conversion rates, and is provided to the user as reference information for future marketing strategies.

[0096] (Application Example 1)

[0097] 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."

[0098] In recent years, with the diversification of information dissemination strategies, there has been a growing demand for efficient and effective information dissemination techniques. However, traditional methods require considerable effort to optimize the quality and timing of generated information, and human resources tend to increase, especially when launching new products or campaigns. Furthermore, it has been difficult to design efficient schedules using past data, which has resulted in the inability to maximize the effectiveness of information dissemination.

[0099] 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.

[0100] In this invention, the server includes means for collecting and analyzing user response data to determine the optimal transmission time and frequency, means for regenerating or modifying the generated information based on the user's wishes, and means for calculating the transmission schedule using past time-series data. This reduces the effort required to optimize the quality and timing of information transmission, enabling effective and efficient information dissemination.

[0101] "Generative artificial intelligence" is a technology that automatically generates information based on the goals and target information set by the user.

[0102] "Information" refers to content and data generated by generative artificial intelligence and delivered to a dissemination platform.

[0103] A "social interaction platform" is a general term for online platforms that allow users to share information and interact with one another.

[0104] "Response data" refers to data about the recipient's response and interaction to information transmitted by a user.

[0105] A "dissemination schedule" is a plan that determines the most effective timing for disseminating information based on past time-series data.

[0106] "Outcome data" refers to data collected after information has been disseminated, concerning the effects and impacts achieved by that information.

[0107] The system that realizes this invention mainly consists of a server, a terminal, and a generative AI model. The server generates information using generative artificial intelligence based on goal and target information received from the user. The terminal is a device for the user to access the server and input information. The execution of this program uses commonly used artificial intelligence technologies as the generative AI model (e.g., GPT model).

[0108] The server collects and analyzes response data set by the user. This allows for the calculation of an optimal transmission schedule, making information dissemination more efficient. After transmission, the server collects performance data and reports it to the user. This provides data to optimize future information dissemination.

[0109] As a concrete example, when a store promotes a new product, this system can be used to automatically design an effective communication strategy. If the user sets the target customer as "men in their 30s living in urban areas" and the product's characteristics as "high-performance and well-designed," the AI ​​will generate optimal information content and suggest the timing of its release. An example of a prompt message would be, "Please generate advertising copy for a new product promotion. The target audience is men in their 30s living in urban areas, and the product's characteristics are 'high-performance and well-designed.' Please provide specific and compelling text."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] Users access the management screen via their device and enter the advertising campaign goals, target audience, and product features. This input data is sent to the server as foundational data for the generating AI model to operate.

[0113] Step 2:

[0114] The server runs a generative AI model and generates multiple pieces of information based on data received from the user. The generative AI model processes the input data (e.g., target information, product features) and outputs compelling advertisements and visual content. The output information is evaluated by an algorithm, and the most suitable option is suggested to the user.

[0115] Step 3:

[0116] The user selects the most suitable option from several suggested pieces of information and sends their selection to the server. The selected information is stored on the server, and the process proceeds to the next stage.

[0117] Step 4:

[0118] Based on past response data acquired to date, the server uses a machine learning algorithm to calculate the sending schedule. The response data includes past interaction data (e.g., views, click-through rates, user engagement information), and the optimal sending time is calculated based on this data. The calculated schedule is then reserved for automated sending.

[0119] Step 5:

[0120] The server automatically transmits selected information to various social communication platforms according to a specified schedule. This process is carried out through the platform's API and is completely automated.

[0121] Step 6:

[0122] After the information is sent, the server collects performance data. This data includes the number of views, engagement rate, and conversion rate. This data is then analyzed to generate a detailed report.

[0123] Step 7:

[0124] The server provides the user with the generated report and feedback to optimize the next communication strategy. Users can use this report to adjust their next campaign plan.

[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 combines an emotion engine with a system for generating and optimizing content for posting to social networking sites, enabling the automatic generation of content tailored to the user's emotional state and preferences, thereby facilitating more personalized marketing activities.

[0127] Users can access a settings screen through their device to view the tone and style options for posts suggested by the sentiment engine. When a user enters goals and targeting information into the system, the server retrieves this information, activates the sentiment engine, and analyzes the user's emotional state.

[0128] The server uses acquired sentiment data to assist the generative AI in generating content with a tone and style appropriate to the user's current emotions. For example, if positive emotions are recognized, content containing bright and optimistic expressions will be generated. The generated content is stored in a database and used to create a schedule for optimal posting timing.

[0129] The server incorporates feedback from the emotion engine and analyzes past interaction data in detail. This analysis helps understand how content is received in relation to the user's emotional state and optimizes the strategy for future posts.

[0130] As a concrete example, when a company runs a campaign for a new product, if the emotion engine recognizes that the target audience is feeling excitement and anticipation, the server generates content incorporating stories and images that enhance that excitement and posts it at the optimal time. As a result, user engagement improves and product awareness expands effectively.

[0131] This system enables users to automate the optimization of the content they need, achieve a high level of personalization, and as a result, improve the effectiveness of their marketing activities on social networks.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The device displays a settings screen for the posting campaign, including sentiment recognition options, where the user enters information such as goals, target audience, and desired sentiment state.

[0135] Step 2:

[0136] The terminal receives user input and sends the data to the server. The server analyzes the received data, activates the emotion engine, and determines the user's emotional state.

[0137] Step 3:

[0138] The server collects the user's emotional state, as recognized by the emotion engine, and uses it as input parameters for the generative AI. Based on this information, the generative AI generates content appropriate to the user's emotions.

[0139] Step 4:

[0140] The server temporarily stores the generated content in a database and sends feedback to the device to verify whether the content aligns with the user's intent.

[0141] Step 5:

[0142] Users can preview content through their devices and optionally request adjustments to emotional tone or regeneration. This feedback is sent to the server, and the content is regenerated as needed.

[0143] Step 6:

[0144] The server analyzes past interaction data and sentiment recognition results to determine the optimal posting schedule. It then sets a schedule to ensure posts are made at the optimal time and frequency.

[0145] Step 7:

[0146] The server automatically posts content via the social network's API at scheduled times. During this time, content that has been adjusted to match the user's emotions is effectively shared.

[0147] Step 8:

[0148] After posting, the server retrieves interaction data and performs another analysis using the sentiment engine. Based on this data, the effectiveness of the post and the emotional tone of the response are evaluated.

[0149] Step 9:

[0150] The server compiles the analysis results into a report and sends it to the user's terminal. The user can then refer to the report to inform their next posting strategy.

[0151] (Example 2)

[0152] 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".

[0153] The problem of decreased user engagement stems from a lack of personalized information generation tailored to users' emotional states and preferences in information dissemination on social networking platforms. Furthermore, conventional methods have made it difficult to determine the appropriate timing and frequency of information transmission, resulting in the inability to maximize the effectiveness of information dissemination.

[0154] 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.

[0155] In this invention, the server includes means for analyzing the user's emotional state and personalizing the information generated based on the results; means for generating information based on the user's set goals and target information using generative artificial intelligence; and means for acquiring and analyzing user interaction data and determining appropriate transmission time and frequency. This enables personalized and effective information delivery to users, maximizing engagement and the effectiveness of marketing activities.

[0156] "Generative artificial intelligence" is an artificial intelligence technology that generates information based on goals and target information set by the user.

[0157] "User's emotional state" refers to the emotional state information that users exhibit when sharing information on social networking platforms, and it is a factor used to personalize information based on this state.

[0158] "Methods for personalizing information" refer to the process of adjusting the tone and content of the information generated according to the user's emotional state and preferences.

[0159] "Interaction data" refers to data about the actions and reactions that users perform on social interaction networks, and is used to optimize the timing of information generation and transmission.

[0160] "Appropriate transmission time and frequency" refers to the optimal timing and frequency for information to be received by users in the most effective way.

[0161] "Performance data" refers to data that shows how effective transmitted information was on social networking.

[0162] This invention is a system for optimizing information dissemination in social networking, and its main components are a server, a terminal, and a generative AI model.

[0163] Users can access the system's settings screen using their devices and input their goals and target information. This clearly indicates the type of information the user is seeking and their target audience.

[0164] The server utilizes various software to process data received from users. Specifically, it employs natural language processing (NLP) techniques to analyze emotional states and uses machine learning frameworks such as TENSORFLOW® and PyTorch. This allows for accurate evaluation of the user's emotional state and appropriate adjustment of the tone and style of the information generated.

[0165] Furthermore, the server uses a generative AI model, such as OpenAI®, as its generative artificial intelligence. The generative AI generates customized information by taking prompts based on the user's goals and emotional state. This information is stored in a database and transmitted to the social network at the appropriate time.

[0166] For example, the following prompt statements can be used for a generative AI model:

[0167] "Please create a positive and exciting story for our new product campaign post. Our target audience is working women in their 20s and 30s."

[0168] The server further analyzes user interaction data to determine the optimal transmission time and frequency. This process utilizes Python's Pandas and Scikit-learn as data analysis tools to learn from past data and optimize future information dissemination strategies.

[0169] In this way, this system can provide users with highly personalized information and enhance their presence within social networking networks.

[0170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0171] Step 1:

[0172] The user accesses the system's settings screen using their device. Here, they enter their goals and target information. The input data includes an overview of the target campaign and the characteristics of the target audience. This information is sent to the server as input.

[0173] Step 2:

[0174] The server receives input data from the user and begins data analysis. Based on the received data, it analyzes the user's emotional state using natural language processing techniques. Specifically, it extracts emotional characteristics from the input text data. As output, numerical data representing the user's emotional state is generated.

[0175] Step 3:

[0176] The server generates information using a generative AI model based on the analysis results. It takes emotional characteristic data as input, provides prompts to the generative AI model, and generates personalized information. The generative AI model, for example, creates text adjusted to the tone and style desired by the user. The output of this step is the generated content.

[0177] Step 4:

[0178] The server saves the generated content to a database. The saved data is managed efficiently for use in subsequent processes. Specific operations include storage operations using a database management system (DBMS).

[0179] Step 5:

[0180] The server analyzes past interaction data to determine the optimal transmission time and frequency. It learns from historical data using Python's Pandas and Scikit-learn libraries and applies optimization algorithms. This process provides output for building future information dissemination strategies.

[0181] Step 6:

[0182] The server transmits the generated information to the social network according to the determined transmission schedule. Transmission takes place via network APIs. As a result of transmission, the information is delivered to the appropriate recipients. The output of this step is the transmission completion status.

[0183] (Application Example 2)

[0184] 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".

[0185] Advertising and marketing activities on information exchange networks require the provision of personalized content that takes into account the emotional state of users. However, conventional systems have difficulty generating content in real time that responds to users' emotions, making it challenging to achieve effective user engagement.

[0186] 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.

[0187] In this invention, the server includes means for sensing the user's emotional state and designing advertisements based on it, means for generating content based on the user's set goals and target information using generative artificial intelligence, and means for automatically posting the generated content to multiple information exchange networks. This makes it possible to provide advertisements that match the user's emotional state in real time and achieve effective marketing results.

[0188] "Means for sensing the user's emotional state" refers to a function that identifies and analyzes the user's emotions using information entered by the user and sensor data.

[0189] "A means of designing advertisements" refers to a function that generates and optimizes the tone and content of advertisements based on the user's emotional state.

[0190] "Generative artificial intelligence" is an advanced computing technology that uses natural language processing and image generation techniques to create information tailored to the user.

[0191] An "information exchange network" is a platform where multiple users share content and communicate with each other.

[0192] "Means for acquiring and analyzing interaction data" refers to a function that aggregates user operation history and responses and analyzes that data.

[0193] "Means for determining the optimal posting time and frequency" refers to a function that uses acquired data to determine the most effective time of day and frequency for posting content.

[0194] "Means for analyzing performance data and generating reports" refers to a function that evaluates the effectiveness of advertisements after posting and compiles the results into a report.

[0195] The system that realizes this invention includes a process for accurately sensing the user's emotional state and designing personalized advertisements based on that state. A smartphone is typically used as the hardware for this purpose. On the device, an emotion engine operates that analyzes emotions based on user input.

[0196] The server receives emotional data from users and generates advertising content using generative artificial intelligence (generative AI model). By applying natural language processing technology, it designs ads with a tone and visual style that matches the user's current emotional state. For example, if the server detects that the user is in a calm mood, ads related to relaxation products will be generated. Throughout this process, the emotional engine constantly receives feedback to improve the quality of the generated content.

[0197] Furthermore, the server analyzes the acquired performance data to optimize future content strategies. This data provides important indicators for, for example, improving user engagement and expanding product awareness. The generated advertisements are effectively distributed within the information exchange network.

[0198] For example, if a user is perceived as being in a "calm mood," the generative AI model will construct relevant advertisements based on a prompt such as, "Here are some great ways to spend your weekend for relaxation." Advertisements generated based on this prompt are more likely to interest the user, thus improving marketing effectiveness.

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The user accesses the emotion input module using a terminal and inputs their current emotional state. The input data records the user's emotional status. As output, emotion data is generated and sent to the server.

[0202] Step 2:

[0203] The server analyzes the received emotional data using an emotion engine. In this step, the emotion engine uses natural language processing techniques to identify the user's mood and state. The output of the analysis is an analysis result indicating the user's emotional state.

[0204] Step 3:

[0205] The server uses generative artificial intelligence (generative AI model) to generate ad prompts based on the analysis results. This process designs ad content with appropriate tone and style based on sentiment data. The output is the generated prompt text.

[0206] Step 4:

[0207] The generative AI model receives a prompt and generates ad copy and related visuals based on it. The data calculation performed here is to create the optimal ad by utilizing the model's training data. The generated ad is obtained as the output.

[0208] Step 5:

[0209] The server uses the generated advertisement to post it to the user information exchange network. In this process, posting is executed through an appropriate application program interface, and the advertisement is published on the network. The output confirms the completion of the posting.

[0210] Step 6:

[0211] After posting, the server collects user reactions and interaction data and analyzes performance data. At this stage, it measures the effectiveness of the advertisement and generates information that can be used to improve future campaigns. The output is a report of the analysis results.

[0212] 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.

[0213] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0214] 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.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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".

[0228] The system of the present invention operates by integrating various elements in order to effectively carry out the automatic generation and management of content through social interaction networks. At the heart of the system is a content generation process that utilizes generative artificial intelligence, which automatically generates posts and images that are suitable for the goals and target information specified by the user.

[0229] Users first access the management screen via their device and enter campaign and marketing activity goals, target audience, and other relevant information. This input data is sent to the server and used as the basis for content generation by the generative AI.

[0230] The server runs a generative AI that generates multiple content suggestions based on user input. This allows users to choose the best option from several choices and post it to social networks. The generated content is filtered and adjusted to match the characteristics of the platform used and the interests of the target audience.

[0231] The server then analyzes past user interaction data to calculate the optimal timing for posting. This analysis includes content impressions, engagement rates, and the effectiveness of different posting times, which automatically determine the posting schedule.

[0232] The actual posting is done automatically by the server to various social networking networks according to a predetermined schedule. This process saves time and effort that would otherwise be spent manually, and also improves the accuracy of the posts.

[0233] After submission, the server automatically analyzes the acquired performance data and provides the user with a detailed report. This report includes the results and areas for improvement of the initiative and will be used to formulate future strategies.

[0234] As a concrete example, when a user launches a new product campaign, this system allows them to easily manage everything from content creation and posting to performance analysis in a single, streamlined process. The user simply specifies their target audience and inputs the product's features, and the AI ​​automatically creates compelling ad copy and delivers it at the optimal time. In this way, users can focus on other marketing activities while continuously conducting high-quality promotions.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The device displays the posting campaign settings screen to the user, who then enters information such as goals, target audience, and post theme.

[0238] Step 2:

[0239] Information entered by the user through the terminal is sent to the server, which retrieves it and prepares it as input data for the generating AI.

[0240] Step 3:

[0241] The server runs a generation AI and generates content variations based on the input goal and target information. The generated content is temporarily stored in a database.

[0242] Step 4:

[0243] The server uses analytical tools to analyze past user interaction data and calculate the optimal posting time and frequency.

[0244] Step 5:

[0245] The server creates a series of posting schedules and sets up automated posting tasks based on those schedules.

[0246] Step 6:

[0247] When the scheduled posting time arrives, the server automatically calls the API of the selected social networking service and posts the generated content.

[0248] Step 7:

[0249] Once a post is submitted, the server retrieves interaction data from the social network to measure the effectiveness of the post.

[0250] Step 8:

[0251] The server analyzes the interaction data it acquires using an analysis tool and provides feedback to the user in the form of a report.

[0252] Step 9:

[0253] Users can request content regeneration or modification via their devices as needed, and the server will initiate the regeneration process based on this feedback.

[0254] (Example 1)

[0255] 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".

[0256] Traditional content creation and posting processes require users to manually create content tailored to their goals and target audience, and then post it to various social networks at the appropriate time, which is time-consuming and laborious. Furthermore, the cycle of analyzing post-post performance and using that analysis to improve future content tends to be lengthy.

[0257] 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.

[0258] In this invention, the server includes means for utilizing artificial intelligence to create content based on user-defined goals and target information, means for automatically posting the created content to a network of numerous social interaction groups, and means for collecting and analyzing user response data to determine the optimal posting timing and frequency. This enables users to efficiently create content tailored to their goals and post it to social interaction networks at the optimal time, while also allowing for rapid analysis of post-posting performance and reflection of the results in future work.

[0259] A "user" is someone who utilizes this system, inputting goal and target information and selecting the generated content.

[0260] "Goals" refer to the objectives or results that users hope to achieve when using this system.

[0261] "Target information" refers to data that indicates what audience the content to be generated is intended to appeal to.

[0262] "Content" refers to all material created and posted using generative AI, specifically informational media such as images and text.

[0263] "Generative AI" refers to an artificial intelligence model that automatically generates content based on user input.

[0264] A "social interaction network" refers to an online platform where information is shared and interactions take place among individual users.

[0265] "Posting" refers to the act of making generated content publicly available on a social network.

[0266] "Interaction data" refers to information about user reactions and engagement with posted content.

[0267] "Performance data" refers to information that numerically shows the results and effects of posted content.

[0268] A "report" is a document created based on collected and analyzed data, and includes the results of the campaign and proposals for future strategies.

[0269] The embodiments for carrying out the present invention will be described below.

[0270] This system allows users to easily and automatically generate content based on their self-defined goals and target information. Users first access the system's management screen via their device and input the information necessary for their campaigns and marketing activities. This information serves as the foundational data for content generation using the AI.

[0271] The terminal transmits user input data to the server in real time. The server uses partnered generative AI software to generate content based on the pre-entered information. This generative AI incorporates a large text database and can generate several optimal content options using natural language processing technology.

[0272] The server provides users with generated content proposals, allowing them to select the most suitable content based on their target audience and the characteristics of the social network they use. The server then analyzes past user interaction data to automatically calculate the best timing for posting. This data analysis includes content views, engagement rates, and posting dates.

[0273] Servers with automated posting capabilities post selected content to various social networking networks according to a predetermined schedule. This significantly reduces user effort and enables efficient content management.

[0274] After posting, the server automatically analyzes the acquired performance data and provides the user with a detailed report. This report allows the user to understand the results of their posts and use that information to inform their future marketing strategies.

[0275] For example, a user running a campaign to launch a new sneaker product can simply set their target audience to "men in their 20s" and input the sneaker's features, and the AI ​​will automatically generate compelling ad copy. An example of a prompt might be, "Generate ad copy for this season's new sneakers that will appeal to men in their 20s."

[0276] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0277] Step 1:

[0278] Users log in to the system's administration screen via their device and input information about the goals and target audience of their campaign or marketing activity. This input data includes product features, price range, and timing of advertising. This information is then transmitted to the server via the device as basic data for content generation.

[0279] Step 2:

[0280] The server activates a generative AI model based on the user's input data. The server inputs this as a prompt to the generative AI, which then begins generating content suggestions tailored to the user's needs. For example, the prompt "Generate advertising copy for sneakers that appeals to men in their 20s" might be input to the generative AI. The generative AI then uses natural language processing techniques to create the advertising copy. In this step, the output is the generated content suggestion.

[0281] Step 3:

[0282] The generated content proposals are presented to the user by the server, and a preview for the user to evaluate the options is displayed. This allows the user to compare different content proposals and select the most suitable one. The selected content proposal is then made ready for posting.

[0283] Step 4:

[0284] The server collects and analyzes past user interaction data. This takes into account the historical performance data of the posted content and calculates the optimal posting time. In this process, factors such as the number of impressions, engagement rate, and the impact of the posting time zone are used in the calculation. The calculated optimal posting time is output as scheduling information.

[0285] Step 5:

[0286] Based on the determined schedule, the server automatically posts the selected content to the social communication network. The output here is the actual posting on the network. This step saves manual effort and realizes efficient information distribution.

[0287] Step 6:

[0288] After the posting is completed, the server automatically collects and analyzes the performance data of the posting. This evaluates the effectiveness and improvement points of the posting and generates a detailed report. This report includes the number of views, click-through rate, conversion rate, etc., and is provided to the user as reference information for future marketing strategies.

[0289] (Application Example 1)

[0290] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0291] In recent years, with the diversification of information dissemination strategies, there has been a growing demand for efficient and effective information dissemination techniques. However, traditional methods require considerable effort to optimize the quality and timing of generated information, and human resources tend to increase, especially when launching new products or campaigns. Furthermore, it has been difficult to design efficient schedules using past data, which has resulted in the inability to maximize the effectiveness of information dissemination.

[0292] 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.

[0293] In this invention, the server includes means for collecting and analyzing user response data to determine the optimal transmission time and frequency, means for regenerating or modifying the generated information based on the user's wishes, and means for calculating the transmission schedule using past time-series data. This reduces the effort required to optimize the quality and timing of information transmission, enabling effective and efficient information dissemination.

[0294] "Generative artificial intelligence" is a technology that automatically generates information based on the goals and target information set by the user.

[0295] "Information" refers to content and data generated by generative artificial intelligence and delivered to a dissemination platform.

[0296] A "social interaction platform" is a general term for online platforms that allow users to share information and interact with one another.

[0297] "Response data" refers to data about the recipient's response and interaction to information transmitted by a user.

[0298] A "dissemination schedule" is a plan that determines the most effective timing for disseminating information based on past time-series data.

[0299] "Outcome data" refers to data collected after information has been disseminated, concerning the effects and impacts achieved by that information.

[0300] The system that realizes this invention mainly consists of a server, a terminal, and a generative AI model. The server generates information using generative artificial intelligence based on goal and target information received from the user. The terminal is a device for the user to access the server and input information. The execution of this program uses commonly used artificial intelligence technologies as the generative AI model (e.g., GPT model).

[0301] The server collects and analyzes response data set by the user. This allows for the calculation of an optimal transmission schedule, making information dissemination more efficient. After transmission, the server collects performance data and reports it to the user. This provides data to optimize future information dissemination.

[0302] As a concrete example, when a store promotes a new product, this system can be used to automatically design an effective communication strategy. If the user sets the target customer as "men in their 30s living in urban areas" and the product's characteristics as "high-performance and well-designed," the AI ​​will generate optimal information content and suggest the timing of its release. An example of a prompt message would be, "Please generate advertising copy for a new product promotion. The target audience is men in their 30s living in urban areas, and the product's characteristics are 'high-performance and well-designed.' Please provide specific and compelling text."

[0303] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0304] Step 1:

[0305] Users access the management screen via their device and enter the advertising campaign goals, target audience, and product features. This input data is sent to the server as foundational data for the generating AI model to operate.

[0306] Step 2:

[0307] The server runs a generative AI model and generates multiple pieces of information based on the data received from the user. The generative AI model processes input data (e.g., target information, product features) and outputs attractive ad texts and visual content. The output information is evaluated by an algorithm, and the most suitable one is proposed to the user.

[0308] Step 3:

[0309] The user selects the most optimal one from the proposed multiple pieces of information and sends the selection content to the server. The selected information is saved on the server and proceeds to the next process.

[0310] Step 4:

[0311] Based on the past response data obtained so far, the server uses a machine learning algorithm to calculate the transmission schedule. The response data includes past interaction data (e.g., view count, click-through rate, user engagement information), and based on this, the optimal transmission time is calculated. The calculated schedule is reserved for automatic transmission.

[0312] Step 5:

[0313] The server automatically transmits the selected information to various social communication platforms according to the specified schedule. This process is carried out through the API of the platform and is fully automated.

[0314] Step 6:

[0315] After transmission, the server collects performance data. The collected data includes the view count of the information, engagement rate, conversion rate, etc. These data are analyzed to generate a detailed report.

[0316] Step 7:

[0317] The server provides the user with the generated report and feedback to optimize the next communication strategy. Users can use this report to adjust their next campaign plan.

[0318] 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.

[0319] This invention combines an emotion engine with a system for generating and optimizing content for posting to social networking sites, enabling the automatic generation of content tailored to the user's emotional state and preferences, thereby facilitating more personalized marketing activities.

[0320] Users can access a settings screen through their device to view the tone and style options for posts suggested by the sentiment engine. When a user enters goals and targeting information into the system, the server retrieves this information, activates the sentiment engine, and analyzes the user's emotional state.

[0321] The server uses acquired sentiment data to assist the generative AI in generating content with a tone and style appropriate to the user's current emotions. For example, if positive emotions are recognized, content containing bright and optimistic expressions will be generated. The generated content is stored in a database and used to create a schedule for optimal posting timing.

[0322] The server incorporates feedback from the emotion engine and analyzes past interaction data in detail. This analysis helps understand how content is received in relation to the user's emotional state and optimizes the strategy for future posts.

[0323] As a concrete example, when a company runs a campaign for a new product, if the emotion engine recognizes that the target audience is feeling excitement and anticipation, the server generates content incorporating stories and images that enhance that excitement and posts it at the optimal time. As a result, user engagement improves and product awareness expands effectively.

[0324] This system enables users to automate the optimization of the content they need, achieve a high level of personalization, and as a result, improve the effectiveness of their marketing activities on social networks.

[0325] The following describes the processing flow.

[0326] Step 1:

[0327] The device displays a settings screen for the posting campaign, including sentiment recognition options, where the user enters information such as goals, target audience, and desired sentiment state.

[0328] Step 2:

[0329] The terminal receives user input and sends the data to the server. The server analyzes the received data, activates the emotion engine, and determines the user's emotional state.

[0330] Step 3:

[0331] The server collects the user's emotional state, as recognized by the emotion engine, and uses it as input parameters for the generative AI. Based on this information, the generative AI generates content appropriate to the user's emotions.

[0332] Step 4:

[0333] The server temporarily stores the generated content in a database and sends feedback to the device to verify whether the content aligns with the user's intent.

[0334] Step 5:

[0335] Users can preview content through their devices and optionally request adjustments to emotional tone or regeneration. This feedback is sent to the server, and the content is regenerated as needed.

[0336] Step 6:

[0337] The server analyzes past interaction data and sentiment recognition results to determine the optimal posting schedule. It then sets a schedule to ensure posts are made at the optimal time and frequency.

[0338] Step 7:

[0339] The server automatically posts content via the social network's API at scheduled times. During this time, content that has been adjusted to match the user's emotions is effectively shared.

[0340] Step 8:

[0341] After posting, the server retrieves interaction data and performs another analysis using the sentiment engine. Based on this data, the effectiveness of the post and the emotional tone of the response are evaluated.

[0342] Step 9:

[0343] The server compiles the analysis results into a report and sends it to the user's terminal. The user can then refer to the report to inform their next posting strategy.

[0344] (Example 2)

[0345] 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".

[0346] The problem of decreased user engagement stems from a lack of personalized information generation tailored to users' emotional states and preferences in information dissemination on social networking platforms. Furthermore, conventional methods have made it difficult to determine the appropriate timing and frequency of information transmission, resulting in the inability to maximize the effectiveness of information dissemination.

[0347] 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.

[0348] In this invention, the server includes means for analyzing the user's emotional state and personalizing the information generated based on the results; means for generating information based on the user's set goals and target information using generative artificial intelligence; and means for acquiring and analyzing user interaction data and determining appropriate transmission time and frequency. This enables personalized and effective information delivery to users, maximizing engagement and the effectiveness of marketing activities.

[0349] "Generative artificial intelligence" is an artificial intelligence technology that generates information based on goals and target information set by the user.

[0350] "User's emotional state" refers to the emotional state information that users exhibit when sharing information on social networking platforms, and it is a factor used to personalize information based on this state.

[0351] "Methods for personalizing information" refer to the process of adjusting the tone and content of the information generated according to the user's emotional state and preferences.

[0352] "Interaction data" refers to data about the actions and reactions that users perform on social interaction networks, and is used to optimize the timing of information generation and transmission.

[0353] "Appropriate transmission time and frequency" refers to the optimal timing and frequency for information to be received by users in the most effective way.

[0354] "Performance data" refers to data that shows how effective transmitted information was on social networking.

[0355] This invention is a system for optimizing information dissemination in social networking, and its main components are a server, a terminal, and a generative AI model.

[0356] Users can access the system's settings screen using their devices and input their goals and target information. This clearly indicates the type of information the user is seeking and their target audience.

[0357] The server utilizes various software to process data received from users. Specifically, it employs natural language processing (NLP) techniques to analyze emotional states and uses machine learning frameworks such as TensorFlow and PyTorch. This allows for accurate evaluation of the user's emotional state and appropriate adjustment of the tone and style of the information generated.

[0358] Furthermore, the server uses a generative AI model, such as OpenAI's, as its generative artificial intelligence. The generative AI generates customized information by taking prompts based on the user's goals and emotional state. This information is stored in a database and transmitted to the social network at the appropriate time.

[0359] For example, the following prompt statements can be used for a generative AI model:

[0360] "Please create a positive and exciting story for our new product campaign post. Our target audience is working women in their 20s and 30s."

[0361] The server further analyzes user interaction data to determine the optimal transmission time and frequency. This process utilizes Python's Pandas and Scikit-learn as data analysis tools to learn from past data and optimize future information dissemination strategies.

[0362] In this way, this system can provide users with highly personalized information and enhance their presence within social networking networks.

[0363] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0364] Step 1:

[0365] The user accesses the system's settings screen using their device. Here, they enter their goals and target information. The input data includes an overview of the target campaign and the characteristics of the target audience. This information is sent to the server as input.

[0366] Step 2:

[0367] The server receives input data from the user and begins data analysis. Based on the received data, it analyzes the user's emotional state using natural language processing techniques. Specifically, it extracts emotional characteristics from the input text data. As output, numerical data representing the user's emotional state is generated.

[0368] Step 3:

[0369] The server generates information using a generative AI model based on the analysis results. It takes emotional characteristic data as input, provides prompts to the generative AI model, and generates personalized information. The generative AI model, for example, creates text adjusted to the tone and style desired by the user. The output of this step is the generated content.

[0370] Step 4:

[0371] The server saves the generated content to a database. The saved data is managed efficiently for use in subsequent processes. Specific operations include storage operations using a database management system (DBMS).

[0372] Step 5:

[0373] The server analyzes past interaction data to determine the optimal transmission time and frequency. It learns from historical data using Python's Pandas and Scikit-learn libraries and applies optimization algorithms. This process provides output for building future information dissemination strategies.

[0374] Step 6:

[0375] The server transmits the generated information to the social network according to the determined transmission schedule. Transmission takes place via network APIs. As a result of transmission, the information is delivered to the appropriate recipients. The output of this step is the transmission completion status.

[0376] (Application Example 2)

[0377] 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."

[0378] Advertising and marketing activities on information exchange networks require the provision of personalized content that takes into account the emotional state of users. However, conventional systems have difficulty generating content in real time that responds to users' emotions, making it challenging to achieve effective user engagement.

[0379] 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.

[0380] In this invention, the server includes means for sensing the user's emotional state and designing advertisements based on it, means for generating content based on the user's set goals and target information using generative artificial intelligence, and means for automatically posting the generated content to multiple information exchange networks. This makes it possible to provide advertisements that match the user's emotional state in real time and achieve effective marketing results.

[0381] "Means for sensing the user's emotional state" refers to a function that identifies and analyzes the user's emotions using information entered by the user and sensor data.

[0382] "A means of designing advertisements" refers to a function that generates and optimizes the tone and content of advertisements based on the user's emotional state.

[0383] "Generative artificial intelligence" is an advanced computing technology that uses natural language processing and image generation techniques to create information tailored to the user.

[0384] An "information exchange network" is a platform where multiple users share content and communicate with each other.

[0385] "Means for acquiring and analyzing interaction data" refers to a function that aggregates user operation history and responses and analyzes that data.

[0386] "Means for determining the optimal posting time and frequency" refers to a function that uses acquired data to determine the most effective time of day and frequency for posting content.

[0387] "Means for analyzing performance data and generating reports" refers to a function that evaluates the effectiveness of advertisements after posting and compiles the results into a report.

[0388] The system that realizes this invention includes a process for accurately sensing the user's emotional state and designing personalized advertisements based on that state. A smartphone is typically used as the hardware for this purpose. On the device, an emotion engine operates that analyzes emotions based on user input.

[0389] The server receives emotional data from users and generates advertising content using generative artificial intelligence (generative AI model). By applying natural language processing technology, it designs ads with a tone and visual style that matches the user's current emotional state. For example, if the server detects that the user is in a calm mood, ads related to relaxation products will be generated. Throughout this process, the emotional engine constantly receives feedback to improve the quality of the generated content.

[0390] Furthermore, the server analyzes the acquired performance data to optimize future content strategies. This data provides important indicators for, for example, improving user engagement and expanding product awareness. The generated advertisements are effectively distributed within the information exchange network.

[0391] For example, if a user is perceived as being in a "calm mood," the generative AI model will construct relevant advertisements based on a prompt such as, "Here are some great ways to spend your weekend for relaxation." Advertisements generated based on this prompt are more likely to interest the user, thus improving marketing effectiveness.

[0392] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0393] Step 1:

[0394] The user accesses the emotion input module using a terminal and inputs their current emotional state. The input data records the user's emotional status. As output, emotion data is generated and sent to the server.

[0395] Step 2:

[0396] The server analyzes the received emotional data using an emotion engine. In this step, the emotion engine uses natural language processing techniques to identify the user's mood and state. The output of the analysis is an analysis result indicating the user's emotional state.

[0397] Step 3:

[0398] The server uses generative artificial intelligence (generative AI model) to generate ad prompts based on the analysis results. This process designs ad content with appropriate tone and style based on sentiment data. The output is the generated prompt text.

[0399] Step 4:

[0400] The generative AI model receives a prompt and generates ad copy and related visuals based on it. The data calculation performed here is to create the optimal ad by utilizing the model's training data. The generated ad is obtained as the output.

[0401] Step 5:

[0402] The server uses the generated advertisement to post it to the user information exchange network. In this process, posting is executed through an appropriate application program interface, and the advertisement is published on the network. The output confirms the completion of the posting.

[0403] Step 6:

[0404] After posting, the server collects user reactions and interaction data and analyzes performance data. At this stage, it measures the effectiveness of the advertisement and generates information that can be used to improve future campaigns. The output is a report of the analysis results.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] [Third Embodiment]

[0409] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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).

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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".

[0421] The system of the present invention operates by integrating various elements in order to effectively carry out the automatic generation and management of content through social interaction networks. At the heart of the system is a content generation process that utilizes generative artificial intelligence, which automatically generates posts and images that are suitable for the goals and target information specified by the user.

[0422] Users first access the management screen via their device and enter campaign and marketing activity goals, target audience, and other relevant information. This input data is sent to the server and used as the basis for content generation by the generative AI.

[0423] The server runs a generative AI that generates multiple content suggestions based on user input. This allows users to choose the best option from several choices and post it to social networks. The generated content is filtered and adjusted to match the characteristics of the platform used and the interests of the target audience.

[0424] The server then analyzes past user interaction data to calculate the optimal timing for posting. This analysis includes content impressions, engagement rates, and the effectiveness of different posting times, which automatically determine the posting schedule.

[0425] The actual posting is done automatically by the server to various social networking networks according to a predetermined schedule. This process saves time and effort that would otherwise be spent manually, and also improves the accuracy of the posts.

[0426] After submission, the server automatically analyzes the acquired performance data and provides the user with a detailed report. This report includes the results and areas for improvement of the initiative and will be used to formulate future strategies.

[0427] As a concrete example, when a user launches a new product campaign, this system allows them to easily manage everything from content creation and posting to performance analysis in a single, streamlined process. The user simply specifies their target audience and inputs the product's features, and the AI ​​automatically creates compelling ad copy and delivers it at the optimal time. In this way, users can focus on other marketing activities while continuously conducting high-quality promotions.

[0428] The following describes the processing flow.

[0429] Step 1:

[0430] The device displays the posting campaign settings screen to the user, who then enters information such as goals, target audience, and post theme.

[0431] Step 2:

[0432] Information entered by the user through the terminal is sent to the server, which retrieves it and prepares it as input data for the generating AI.

[0433] Step 3:

[0434] The server runs a generation AI and generates content variations based on the input goal and target information. The generated content is temporarily stored in a database.

[0435] Step 4:

[0436] The server uses analytical tools to analyze past user interaction data and calculate the optimal posting time and frequency.

[0437] Step 5:

[0438] The server creates a series of posting schedules and sets up automated posting tasks based on those schedules.

[0439] Step 6:

[0440] When the scheduled posting time arrives, the server automatically calls the API of the selected social networking service and posts the generated content.

[0441] Step 7:

[0442] Once a post is submitted, the server retrieves interaction data from the social network to measure the effectiveness of the post.

[0443] Step 8:

[0444] The server analyzes the interaction data it acquires using an analysis tool and provides feedback to the user in the form of a report.

[0445] Step 9:

[0446] Users can request content regeneration or modification via their devices as needed, and the server will initiate the regeneration process based on this feedback.

[0447] (Example 1)

[0448] 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."

[0449] Traditional content creation and posting processes require users to manually create content tailored to their goals and target audience, and then post it to various social networks at the appropriate time, which is time-consuming and laborious. Furthermore, the cycle of analyzing post-post performance and using that analysis to improve future content tends to be lengthy.

[0450] 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.

[0451] In this invention, the server includes means for utilizing artificial intelligence to create content based on user-defined goals and target information, means for automatically posting the created content to a network of numerous social interaction groups, and means for collecting and analyzing user response data to determine the optimal posting timing and frequency. This enables users to efficiently create content tailored to their goals and post it to social interaction networks at the optimal time, while also allowing for rapid analysis of post-posting performance and reflection of the results in future work.

[0452] A "user" is someone who utilizes this system, inputting goal and target information and selecting the generated content.

[0453] "Goals" refer to the objectives or results that users hope to achieve when using this system.

[0454] "Target information" refers to data that indicates what audience the content to be generated is intended to appeal to.

[0455] "Content" refers to all material created and posted using generative AI, specifically informational media such as images and text.

[0456] "Generative AI" refers to an artificial intelligence model that automatically generates content based on user input.

[0457] A "social interaction network" refers to an online platform where information is shared and interactions take place among individual users.

[0458] "Posting" refers to the act of making generated content publicly available on a social network.

[0459] "Interaction data" refers to information about user reactions and engagement with posted content.

[0460] "Performance data" refers to information that numerically shows the results and effects of posted content.

[0461] A "report" is a document created based on collected and analyzed data, and includes the results of the campaign and proposals for future strategies.

[0462] The embodiments for carrying out the present invention will be described below.

[0463] This system allows users to easily and automatically generate content based on their self-defined goals and target information. Users first access the system's management screen via their device and input the information necessary for their campaigns and marketing activities. This information serves as the foundational data for content generation using the AI.

[0464] The terminal transmits user input data to the server in real time. The server uses partnered generative AI software to generate content based on the pre-entered information. This generative AI incorporates a large text database and can generate several optimal content options using natural language processing technology.

[0465] The server provides users with generated content proposals, allowing them to select the most suitable content based on their target audience and the characteristics of the social network they use. The server then analyzes past user interaction data to automatically calculate the best timing for posting. This data analysis includes content views, engagement rates, and posting dates.

[0466] Servers with automated posting capabilities post selected content to various social networking networks according to a predetermined schedule. This significantly reduces user effort and enables efficient content management.

[0467] After posting, the server automatically analyzes the acquired performance data and provides the user with a detailed report. This report allows the user to understand the results of their posts and use that information to inform their future marketing strategies.

[0468] For example, a user running a campaign to launch a new sneaker product can simply set their target audience to "men in their 20s" and input the sneaker's features, and the AI ​​will automatically generate compelling ad copy. An example of a prompt might be, "Generate ad copy for this season's new sneakers that will appeal to men in their 20s."

[0469] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0470] Step 1:

[0471] Users log in to the system's administration screen via their device and input information about the goals and target audience of their campaign or marketing activity. This input data includes product features, price range, and timing of advertising. This information is then transmitted to the server via the device as basic data for content generation.

[0472] Step 2:

[0473] The server activates a generative AI model based on the user's input data. The server inputs this as a prompt to the generative AI, which then begins generating content suggestions tailored to the user's needs. For example, the prompt "Generate advertising copy for sneakers that appeals to men in their 20s" might be input to the generative AI. The generative AI then uses natural language processing techniques to create the advertising copy. In this step, the output is the generated content suggestion.

[0474] Step 3:

[0475] The generated content proposals are presented to the user by the server, and a preview is displayed for the user to evaluate the options. This allows the user to compare different content proposals and select the one that best suits their needs. The selected content proposal is then considered ready for publication.

[0476] Step 4:

[0477] The server collects and analyzes historical user interaction data. This allows the server to consider the historical performance data of posted content and calculate the optimal posting time. Factors such as impression count, engagement rate, and the impact of posting time are used in the calculation. The calculated optimal posting time is output as scheduling information.

[0478] Step 5:

[0479] The server automatically posts selected content to the social network based on a predetermined schedule. The output here is the actual post on the network. This step eliminates manual effort and enables efficient information distribution.

[0480] Step 6:

[0481] After posting is complete, the server automatically collects and analyzes the post's performance data. This evaluates the post's effectiveness and areas for improvement, and generates a detailed report. This report includes data such as views, click-through rates, and conversion rates, and is provided to the user as reference information for future marketing strategies.

[0482] (Application Example 1)

[0483] 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."

[0484] In recent years, with the diversification of information dissemination strategies, there has been a growing demand for efficient and effective information dissemination techniques. However, traditional methods require considerable effort to optimize the quality and timing of generated information, and human resources tend to increase, especially when launching new products or campaigns. Furthermore, it has been difficult to design efficient schedules using past data, which has resulted in the inability to maximize the effectiveness of information dissemination.

[0485] 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.

[0486] In this invention, the server includes means for collecting and analyzing user response data to determine the optimal transmission time and frequency, means for regenerating or modifying the generated information based on the user's wishes, and means for calculating the transmission schedule using past time-series data. This reduces the effort required to optimize the quality and timing of information transmission, enabling effective and efficient information dissemination.

[0487] "Generative artificial intelligence" is a technology that automatically generates information based on the goals and target information set by the user.

[0488] "Information" refers to content and data generated by generative artificial intelligence and delivered to a dissemination platform.

[0489] A "social interaction platform" is a general term for online platforms that allow users to share information and interact with one another.

[0490] "Response data" refers to data about the recipient's response and interaction to information transmitted by a user.

[0491] A "dissemination schedule" is a plan that determines the most effective timing for disseminating information based on past time-series data.

[0492] "Outcome data" refers to data collected after information has been disseminated, concerning the effects and impacts achieved by that information.

[0493] The system that realizes this invention mainly consists of a server, a terminal, and a generative AI model. The server generates information using generative artificial intelligence based on goal and target information received from the user. The terminal is a device for the user to access the server and input information. The execution of this program uses commonly used artificial intelligence technologies as the generative AI model (e.g., GPT model).

[0494] The server collects and analyzes response data set by the user. This allows for the calculation of an optimal transmission schedule, making information dissemination more efficient. After transmission, the server collects performance data and reports it to the user. This provides data to optimize future information dissemination.

[0495] As a concrete example, when a store promotes a new product, this system can be used to automatically design an effective communication strategy. If the user sets the target customer as "men in their 30s living in urban areas" and the product's characteristics as "high-performance and well-designed," the AI ​​will generate optimal information content and suggest the timing of its release. An example of a prompt message would be, "Please generate advertising copy for a new product promotion. The target audience is men in their 30s living in urban areas, and the product's characteristics are 'high-performance and well-designed.' Please provide specific and compelling text."

[0496] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0497] Step 1:

[0498] Users access the management screen via their device and enter the advertising campaign goals, target audience, and product features. This input data is sent to the server as foundational data for the generating AI model to operate.

[0499] Step 2:

[0500] The server runs a generative AI model and generates multiple pieces of information based on data received from the user. The generative AI model processes the input data (e.g., target information, product features) and outputs compelling advertisements and visual content. The output information is evaluated by an algorithm, and the most suitable option is suggested to the user.

[0501] Step 3:

[0502] The user selects the most suitable option from several suggested pieces of information and sends their selection to the server. The selected information is stored on the server, and the process proceeds to the next stage.

[0503] Step 4:

[0504] Based on past response data acquired to date, the server uses a machine learning algorithm to calculate the sending schedule. The response data includes past interaction data (e.g., views, click-through rates, user engagement information), and the optimal sending time is calculated based on this data. The calculated schedule is then reserved for automated sending.

[0505] Step 5:

[0506] The server automatically transmits selected information to various social communication platforms according to a specified schedule. This process is carried out through the platform's API and is completely automated.

[0507] Step 6:

[0508] After the information is sent, the server collects performance data. This data includes the number of views, engagement rate, and conversion rate. This data is then analyzed to generate a detailed report.

[0509] Step 7:

[0510] The server provides the user with the generated report and feedback to optimize the next communication strategy. Users can use this report to adjust their next campaign plan.

[0511] 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.

[0512] This invention combines an emotion engine with a system for generating and optimizing content for posting to social networking sites, enabling the automatic generation of content tailored to the user's emotional state and preferences, thereby facilitating more personalized marketing activities.

[0513] Users can access a settings screen through their device to view the tone and style options for posts suggested by the sentiment engine. When a user enters goals and targeting information into the system, the server retrieves this information, activates the sentiment engine, and analyzes the user's emotional state.

[0514] The server uses acquired sentiment data to assist the generative AI in generating content with a tone and style appropriate to the user's current emotions. For example, if positive emotions are recognized, content containing bright and optimistic expressions will be generated. The generated content is stored in a database and used to create a schedule for optimal posting timing.

[0515] The server incorporates feedback from the emotion engine and analyzes past interaction data in detail. This analysis helps understand how content is received in relation to the user's emotional state and optimizes the strategy for future posts.

[0516] As a concrete example, when a company runs a campaign for a new product, if the emotion engine recognizes that the target audience is feeling excitement and anticipation, the server generates content incorporating stories and images that enhance that excitement and posts it at the optimal time. As a result, user engagement improves and product awareness expands effectively.

[0517] This system enables users to automate the optimization of the content they need, achieve a high level of personalization, and as a result, improve the effectiveness of their marketing activities on social networks.

[0518] The following describes the processing flow.

[0519] Step 1:

[0520] The device displays a settings screen for the posting campaign, including sentiment recognition options, where the user enters information such as goals, target audience, and desired sentiment state.

[0521] Step 2:

[0522] The terminal receives user input and sends the data to the server. The server analyzes the received data, activates the emotion engine, and determines the user's emotional state.

[0523] Step 3:

[0524] The server collects the user's emotional state, as recognized by the emotion engine, and uses it as input parameters for the generative AI. Based on this information, the generative AI generates content appropriate to the user's emotions.

[0525] Step 4:

[0526] The server temporarily stores the generated content in a database and sends feedback to the device to verify whether the content aligns with the user's intent.

[0527] Step 5:

[0528] Users can preview content through their devices and optionally request adjustments to emotional tone or regeneration. This feedback is sent to the server, and the content is regenerated as needed.

[0529] Step 6:

[0530] The server analyzes past interaction data and sentiment recognition results to determine the optimal posting schedule. It then sets a schedule to ensure posts are made at the optimal time and frequency.

[0531] Step 7:

[0532] The server automatically posts content via the social network's API at scheduled times. During this time, content that has been adjusted to match the user's emotions is effectively shared.

[0533] Step 8:

[0534] After posting, the server retrieves interaction data and performs another analysis using the sentiment engine. Based on this data, the effectiveness of the post and the emotional tone of the response are evaluated.

[0535] Step 9:

[0536] The server compiles the analysis results into a report and sends it to the user's terminal. The user can then refer to the report to inform their next posting strategy.

[0537] (Example 2)

[0538] 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."

[0539] The problem of decreased user engagement stems from a lack of personalized information generation tailored to users' emotional states and preferences in information dissemination on social networking platforms. Furthermore, conventional methods have made it difficult to determine the appropriate timing and frequency of information transmission, resulting in the inability to maximize the effectiveness of information dissemination.

[0540] 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.

[0541] In this invention, the server includes means for analyzing the user's emotional state and personalizing the information generated based on the results; means for generating information based on the user's set goals and target information using generative artificial intelligence; and means for acquiring and analyzing user interaction data and determining appropriate transmission time and frequency. This enables personalized and effective information delivery to users, maximizing engagement and the effectiveness of marketing activities.

[0542] "Generative artificial intelligence" is an artificial intelligence technology that generates information based on goals and target information set by the user.

[0543] "User's emotional state" refers to the emotional state information that users exhibit when sharing information on social networking platforms, and it is a factor used to personalize information based on this state.

[0544] "Methods for personalizing information" refer to the process of adjusting the tone and content of the information generated according to the user's emotional state and preferences.

[0545] "Interaction data" refers to data about the actions and reactions that users perform on social interaction networks, and is used to optimize the timing of information generation and transmission.

[0546] "Appropriate transmission time and frequency" refers to the optimal timing and frequency for information to be received by users in the most effective way.

[0547] "Performance data" refers to data that shows how effective transmitted information was on social networking.

[0548] This invention is a system for optimizing information dissemination in social networking, and its main components are a server, a terminal, and a generative AI model.

[0549] Users can access the system's settings screen using their devices and input their goals and target information. This clearly indicates the type of information the user is seeking and their target audience.

[0550] The server utilizes various software to process data received from users. Specifically, it employs natural language processing (NLP) techniques to analyze emotional states and uses machine learning frameworks such as TensorFlow and PyTorch. This allows for accurate evaluation of the user's emotional state and appropriate adjustment of the tone and style of the information generated.

[0551] Furthermore, the server uses a generative AI model, such as OpenAI's, as its generative artificial intelligence. The generative AI generates customized information by taking prompts based on the user's goals and emotional state. This information is stored in a database and transmitted to the social network at the appropriate time.

[0552] For example, the following prompt statements can be used for a generative AI model:

[0553] "Please create a positive and exciting story for our new product campaign post. Our target audience is working women in their 20s and 30s."

[0554] The server further analyzes user interaction data to determine the optimal transmission time and frequency. This process utilizes Python's Pandas and Scikit-learn as data analysis tools to learn from past data and optimize future information dissemination strategies.

[0555] In this way, this system can provide users with highly personalized information and enhance their presence within social networking networks.

[0556] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0557] Step 1:

[0558] The user accesses the system's settings screen using their device. Here, they enter their goals and target information. The input data includes an overview of the target campaign and the characteristics of the target audience. This information is sent to the server as input.

[0559] Step 2:

[0560] The server receives input data from the user and begins data analysis. Based on the received data, it analyzes the user's emotional state using natural language processing techniques. Specifically, it extracts emotional characteristics from the input text data. As output, numerical data representing the user's emotional state is generated.

[0561] Step 3:

[0562] The server generates information using a generative AI model based on the analysis results. It takes emotional characteristic data as input, provides prompts to the generative AI model, and generates personalized information. The generative AI model, for example, creates text adjusted to the tone and style desired by the user. The output of this step is the generated content.

[0563] Step 4:

[0564] The server saves the generated content to a database. The saved data is managed efficiently for use in subsequent processes. Specific operations include storage operations using a database management system (DBMS).

[0565] Step 5:

[0566] The server analyzes past interaction data to determine the optimal transmission time and frequency. It learns from historical data using Python's Pandas and Scikit-learn libraries and applies optimization algorithms. This process provides output for building future information dissemination strategies.

[0567] Step 6:

[0568] The server transmits the generated information to the social network according to the determined transmission schedule. Transmission takes place via network APIs. As a result of transmission, the information is delivered to the appropriate recipients. The output of this step is the transmission completion status.

[0569] (Application Example 2)

[0570] 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."

[0571] Advertising and marketing activities on information exchange networks require the provision of personalized content that takes into account the emotional state of users. However, conventional systems have difficulty generating content in real time that responds to users' emotions, making it challenging to achieve effective user engagement.

[0572] 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.

[0573] In this invention, the server includes means for sensing the user's emotional state and designing advertisements based on it, means for generating content based on the user's set goals and target information using generative artificial intelligence, and means for automatically posting the generated content to multiple information exchange networks. This makes it possible to provide advertisements that match the user's emotional state in real time and achieve effective marketing results.

[0574] "Means for sensing the user's emotional state" refers to a function that identifies and analyzes the user's emotions using information entered by the user and sensor data.

[0575] "A means of designing advertisements" refers to a function that generates and optimizes the tone and content of advertisements based on the user's emotional state.

[0576] "Generative artificial intelligence" is an advanced computing technology that uses natural language processing and image generation techniques to create information tailored to the user.

[0577] An "information exchange network" is a platform where multiple users share content and communicate with each other.

[0578] "Means for acquiring and analyzing interaction data" refers to a function that aggregates user operation history and responses and analyzes that data.

[0579] "Means for determining the optimal posting time and frequency" refers to a function that uses acquired data to determine the most effective time of day and frequency for posting content.

[0580] "Means for analyzing performance data and generating reports" refers to a function that evaluates the effectiveness of advertisements after posting and compiles the results into a report.

[0581] The system that realizes this invention includes a process for accurately sensing the user's emotional state and designing personalized advertisements based on that state. A smartphone is typically used as the hardware for this purpose. On the device, an emotion engine operates that analyzes emotions based on user input.

[0582] The server receives emotional data from users and generates advertising content using generative artificial intelligence (generative AI model). By applying natural language processing technology, it designs ads with a tone and visual style that matches the user's current emotional state. For example, if the server detects that the user is in a calm mood, ads related to relaxation products will be generated. Throughout this process, the emotional engine constantly receives feedback to improve the quality of the generated content.

[0583] Furthermore, the server analyzes the acquired performance data to optimize future content strategies. This data provides important indicators for, for example, improving user engagement and expanding product awareness. The generated advertisements are effectively distributed within the information exchange network.

[0584] For example, if a user is perceived as being in a "calm mood," the generative AI model will construct relevant advertisements based on a prompt such as, "Here are some great ways to spend your weekend for relaxation." Advertisements generated based on this prompt are more likely to interest the user, thus improving marketing effectiveness.

[0585] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0586] Step 1:

[0587] The user accesses the emotion input module using a terminal and inputs their current emotional state. The input data records the user's emotional status. As output, emotion data is generated and sent to the server.

[0588] Step 2:

[0589] The server analyzes the received emotional data using an emotion engine. In this step, the emotion engine uses natural language processing techniques to identify the user's mood and state. The output of the analysis is an analysis result indicating the user's emotional state.

[0590] Step 3:

[0591] The server uses generative artificial intelligence (generative AI model) to generate ad prompts based on the analysis results. This process designs ad content with appropriate tone and style based on sentiment data. The output is the generated prompt text.

[0592] Step 4:

[0593] The generative AI model receives a prompt and generates ad copy and related visuals based on it. The data calculation performed here is to create the optimal ad by utilizing the model's training data. The generated ad is obtained as the output.

[0594] Step 5:

[0595] The server uses the generated advertisement to post it to the user information exchange network. In this process, posting is executed through an appropriate application program interface, and the advertisement is published on the network. The output confirms the completion of the posting.

[0596] Step 6:

[0597] After posting, the server collects user reactions and interaction data and analyzes performance data. At this stage, it measures the effectiveness of the advertisement and generates information that can be used to improve future campaigns. The output is a report of the analysis results.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] [Fourth Embodiment]

[0602] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0603] 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.

[0604] 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).

[0605] 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.

[0606] 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.

[0607] 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).

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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.

[0614] 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".

[0615] The system of the present invention operates by integrating various elements in order to effectively carry out the automatic generation and management of content through social interaction networks. At the heart of the system is a content generation process that utilizes generative artificial intelligence, which automatically generates posts and images that are suitable for the goals and target information specified by the user.

[0616] Users first access the management screen via their device and enter campaign and marketing activity goals, target audience, and other relevant information. This input data is sent to the server and used as the basis for content generation by the generative AI.

[0617] The server runs a generative AI that generates multiple content suggestions based on user input. This allows users to choose the best option from several choices and post it to social networks. The generated content is filtered and adjusted to match the characteristics of the platform used and the interests of the target audience.

[0618] The server then analyzes past user interaction data to calculate the optimal timing for posting. This analysis includes content impressions, engagement rates, and the effectiveness of different posting times, which automatically determine the posting schedule.

[0619] The actual posting is done automatically by the server to various social networking networks according to a predetermined schedule. This process saves time and effort that would otherwise be spent manually, and also improves the accuracy of the posts.

[0620] After submission, the server automatically analyzes the acquired performance data and provides the user with a detailed report. This report includes the results and areas for improvement of the initiative and will be used to formulate future strategies.

[0621] As a concrete example, when a user launches a new product campaign, this system allows them to easily manage everything from content creation and posting to performance analysis in a single, streamlined process. The user simply specifies their target audience and inputs the product's features, and the AI ​​automatically creates compelling ad copy and delivers it at the optimal time. In this way, users can focus on other marketing activities while continuously conducting high-quality promotions.

[0622] The following describes the processing flow.

[0623] Step 1:

[0624] The device displays the posting campaign settings screen to the user, who then enters information such as goals, target audience, and post theme.

[0625] Step 2:

[0626] Information entered by the user through the terminal is sent to the server, which retrieves it and prepares it as input data for the generating AI.

[0627] Step 3:

[0628] The server runs a generation AI and generates content variations based on the input goal and target information. The generated content is temporarily stored in a database.

[0629] Step 4:

[0630] The server uses analytical tools to analyze past user interaction data and calculate the optimal posting time and frequency.

[0631] Step 5:

[0632] The server creates a series of posting schedules and sets up automated posting tasks based on those schedules.

[0633] Step 6:

[0634] When the scheduled posting time arrives, the server automatically calls the API of the selected social networking service and posts the generated content.

[0635] Step 7:

[0636] Once a post is submitted, the server retrieves interaction data from the social network to measure the effectiveness of the post.

[0637] Step 8:

[0638] The server analyzes the interaction data it acquires using an analysis tool and provides feedback to the user in the form of a report.

[0639] Step 9:

[0640] Users can request content regeneration or modification via their devices as needed, and the server will initiate the regeneration process based on this feedback.

[0641] (Example 1)

[0642] 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".

[0643] Traditional content creation and posting processes require users to manually create content tailored to their goals and target audience, and then post it to various social networks at the appropriate time, which is time-consuming and laborious. Furthermore, the cycle of analyzing post-post performance and using that analysis to improve future content tends to be lengthy.

[0644] 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.

[0645] In this invention, the server includes means for utilizing artificial intelligence to create content based on user-defined goals and target information, means for automatically posting the created content to a network of numerous social interaction groups, and means for collecting and analyzing user response data to determine the optimal posting timing and frequency. This enables users to efficiently create content tailored to their goals and post it to social interaction networks at the optimal time, while also allowing for rapid analysis of post-posting performance and reflection of the results in future work.

[0646] A "user" is someone who utilizes this system, inputting goal and target information and selecting the generated content.

[0647] "Goals" refer to the objectives or results that users hope to achieve when using this system.

[0648] "Target information" refers to data that indicates what audience the content to be generated is intended to appeal to.

[0649] "Content" refers to all material created and posted using generative AI, specifically informational media such as images and text.

[0650] "Generative AI" refers to an artificial intelligence model that automatically generates content based on user input.

[0651] A "social interaction network" refers to an online platform where information is shared and interactions take place among individual users.

[0652] "Posting" refers to the act of making generated content publicly available on a social network.

[0653] "Interaction data" refers to information about user reactions and engagement with posted content.

[0654] "Performance data" refers to information that numerically shows the results and effects of posted content.

[0655] A "report" is a document created based on collected and analyzed data, and includes the results of the campaign and proposals for future strategies.

[0656] The embodiments for carrying out the present invention will be described below.

[0657] This system allows users to easily and automatically generate content based on their self-defined goals and target information. Users first access the system's management screen via their device and input the information necessary for their campaigns and marketing activities. This information serves as the foundational data for content generation using the AI.

[0658] The terminal transmits user input data to the server in real time. The server uses partnered generative AI software to generate content based on the pre-entered information. This generative AI incorporates a large text database and can generate several optimal content options using natural language processing technology.

[0659] The server provides users with generated content proposals, allowing them to select the most suitable content based on their target audience and the characteristics of the social network they use. The server then analyzes past user interaction data to automatically calculate the best timing for posting. This data analysis includes content views, engagement rates, and posting dates.

[0660] Servers with automated posting capabilities post selected content to various social networking networks according to a predetermined schedule. This significantly reduces user effort and enables efficient content management.

[0661] After posting, the server automatically analyzes the acquired performance data and provides the user with a detailed report. This report allows the user to understand the results of their posts and use that information to inform their future marketing strategies.

[0662] For example, a user running a campaign to launch a new sneaker product can simply set their target audience to "men in their 20s" and input the sneaker's features, and the AI ​​will automatically generate compelling ad copy. An example of a prompt might be, "Generate ad copy for this season's new sneakers that will appeal to men in their 20s."

[0663] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0664] Step 1:

[0665] Users log in to the system's administration screen via their device and input information about the goals and target audience of their campaign or marketing activity. This input data includes product features, price range, and timing of advertising. This information is then transmitted to the server via the device as basic data for content generation.

[0666] Step 2:

[0667] The server activates a generative AI model based on the user's input data. The server inputs this as a prompt to the generative AI, which then begins generating content suggestions tailored to the user's needs. For example, the prompt "Generate advertising copy for sneakers that appeals to men in their 20s" might be input to the generative AI. The generative AI then uses natural language processing techniques to create the advertising copy. In this step, the output is the generated content suggestion.

[0668] Step 3:

[0669] The generated content proposals are presented to the user by the server, and a preview is displayed for the user to evaluate the options. This allows the user to compare different content proposals and select the one that best suits their needs. The selected content proposal is then considered ready for publication.

[0670] Step 4:

[0671] The server collects and analyzes historical user interaction data. This allows the server to consider the historical performance data of posted content and calculate the optimal posting time. Factors such as impression count, engagement rate, and the impact of posting time are used in the calculation. The calculated optimal posting time is output as scheduling information.

[0672] Step 5:

[0673] The server automatically posts selected content to the social network based on a predetermined schedule. The output here is the actual post on the network. This step eliminates manual effort and enables efficient information distribution.

[0674] Step 6:

[0675] After posting is complete, the server automatically collects and analyzes the post's performance data. This evaluates the post's effectiveness and areas for improvement, and generates a detailed report. This report includes data such as views, click-through rates, and conversion rates, and is provided to the user as reference information for future marketing strategies.

[0676] (Application Example 1)

[0677] 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".

[0678] In recent years, with the diversification of information dissemination strategies, there has been a growing demand for efficient and effective information dissemination techniques. However, traditional methods require considerable effort to optimize the quality and timing of generated information, and human resources tend to increase, especially when launching new products or campaigns. Furthermore, it has been difficult to design efficient schedules using past data, which has resulted in the inability to maximize the effectiveness of information dissemination.

[0679] 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.

[0680] In this invention, the server includes means for collecting and analyzing user response data to determine the optimal transmission time and frequency, means for regenerating or modifying the generated information based on the user's wishes, and means for calculating the transmission schedule using past time-series data. This reduces the effort required to optimize the quality and timing of information transmission, enabling effective and efficient information dissemination.

[0681] "Generative artificial intelligence" is a technology that automatically generates information based on the goals and target information set by the user.

[0682] "Information" refers to content and data generated by generative artificial intelligence and delivered to a dissemination platform.

[0683] A "social interaction platform" is a general term for online platforms that allow users to share information and interact with one another.

[0684] "Response data" refers to data about the recipient's response and interaction to information transmitted by a user.

[0685] A "dissemination schedule" is a plan that determines the most effective timing for disseminating information based on past time-series data.

[0686] "Outcome data" refers to data collected after information has been disseminated, concerning the effects and impacts achieved by that information.

[0687] The system that realizes this invention mainly consists of a server, a terminal, and a generative AI model. The server generates information using generative artificial intelligence based on goal and target information received from the user. The terminal is a device for the user to access the server and input information. The execution of this program uses commonly used artificial intelligence technologies as the generative AI model (e.g., GPT model).

[0688] The server collects and analyzes response data set by the user. This allows for the calculation of an optimal transmission schedule, making information dissemination more efficient. After transmission, the server collects performance data and reports it to the user. This provides data to optimize future information dissemination.

[0689] As a concrete example, when a store promotes a new product, this system can be used to automatically design an effective communication strategy. If the user sets the target customer as "men in their 30s living in urban areas" and the product's characteristics as "high-performance and well-designed," the AI ​​will generate optimal information content and suggest the timing of its release. An example of a prompt message would be, "Please generate advertising copy for a new product promotion. The target audience is men in their 30s living in urban areas, and the product's characteristics are 'high-performance and well-designed.' Please provide specific and compelling text."

[0690] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0691] Step 1:

[0692] Users access the management screen via their device and enter the advertising campaign goals, target audience, and product features. This input data is sent to the server as foundational data for the generating AI model to operate.

[0693] Step 2:

[0694] The server runs a generative AI model and generates multiple pieces of information based on data received from the user. The generative AI model processes the input data (e.g., target information, product features) and outputs compelling advertisements and visual content. The output information is evaluated by an algorithm, and the most suitable option is suggested to the user.

[0695] Step 3:

[0696] The user selects the most suitable option from several suggested pieces of information and sends their selection to the server. The selected information is stored on the server, and the process proceeds to the next stage.

[0697] Step 4:

[0698] Based on past response data acquired to date, the server uses a machine learning algorithm to calculate the sending schedule. The response data includes past interaction data (e.g., views, click-through rates, user engagement information), and the optimal sending time is calculated based on this data. The calculated schedule is then reserved for automated sending.

[0699] Step 5:

[0700] The server automatically transmits selected information to various social communication platforms according to a specified schedule. This process is carried out through the platform's API and is completely automated.

[0701] Step 6:

[0702] After the information is sent, the server collects performance data. This data includes the number of views, engagement rate, and conversion rate. This data is then analyzed to generate a detailed report.

[0703] Step 7:

[0704] The server provides the user with the generated report and feedback to optimize the next communication strategy. Users can use this report to adjust their next campaign plan.

[0705] 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.

[0706] This invention combines an emotion engine with a system for generating and optimizing content for posting to social networking sites, enabling the automatic generation of content tailored to the user's emotional state and preferences, thereby facilitating more personalized marketing activities.

[0707] Users can access a settings screen through their device to view the tone and style options for posts suggested by the sentiment engine. When a user enters goals and targeting information into the system, the server retrieves this information, activates the sentiment engine, and analyzes the user's emotional state.

[0708] The server uses acquired sentiment data to assist the generative AI in generating content with a tone and style appropriate to the user's current emotions. For example, if positive emotions are recognized, content containing bright and optimistic expressions will be generated. The generated content is stored in a database and used to create a schedule for optimal posting timing.

[0709] The server incorporates feedback from the emotion engine and analyzes past interaction data in detail. This analysis helps understand how content is received in relation to the user's emotional state and optimizes the strategy for future posts.

[0710] As a concrete example, when a company runs a campaign for a new product, if the emotion engine recognizes that the target audience is feeling excitement and anticipation, the server generates content incorporating stories and images that enhance that excitement and posts it at the optimal time. As a result, user engagement improves and product awareness expands effectively.

[0711] This system enables users to automate the optimization of the content they need, achieve a high level of personalization, and as a result, improve the effectiveness of their marketing activities on social networks.

[0712] The following describes the processing flow.

[0713] Step 1:

[0714] The device displays a settings screen for the posting campaign, including sentiment recognition options, where the user enters information such as goals, target audience, and desired sentiment state.

[0715] Step 2:

[0716] The terminal receives user input and sends the data to the server. The server analyzes the received data, activates the emotion engine, and determines the user's emotional state.

[0717] Step 3:

[0718] The server collects the user's emotional state, as recognized by the emotion engine, and uses it as input parameters for the generative AI. Based on this information, the generative AI generates content appropriate to the user's emotions.

[0719] Step 4:

[0720] The server temporarily stores the generated content in a database and sends feedback to the device to verify whether the content aligns with the user's intent.

[0721] Step 5:

[0722] Users can preview content through their devices and optionally request adjustments to emotional tone or regeneration. This feedback is sent to the server, and the content is regenerated as needed.

[0723] Step 6:

[0724] The server analyzes past interaction data and sentiment recognition results to determine the optimal posting schedule. It then sets a schedule to ensure posts are made at the optimal time and frequency.

[0725] Step 7:

[0726] The server automatically posts content via the social network's API at scheduled times. During this time, content that has been adjusted to match the user's emotions is effectively shared.

[0727] Step 8:

[0728] After posting, the server retrieves interaction data and performs another analysis using the sentiment engine. Based on this data, the effectiveness of the post and the emotional tone of the response are evaluated.

[0729] Step 9:

[0730] The server compiles the analysis results into a report and sends it to the user's terminal. The user can then refer to the report to inform their next posting strategy.

[0731] (Example 2)

[0732] 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".

[0733] The problem of decreased user engagement stems from a lack of personalized information generation tailored to users' emotional states and preferences in information dissemination on social networking platforms. Furthermore, conventional methods have made it difficult to determine the appropriate timing and frequency of information transmission, resulting in the inability to maximize the effectiveness of information dissemination.

[0734] 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.

[0735] In this invention, the server includes means for analyzing the user's emotional state and personalizing the information generated based on the results; means for generating information based on the user's set goals and target information using generative artificial intelligence; and means for acquiring and analyzing user interaction data and determining appropriate transmission time and frequency. This enables personalized and effective information delivery to users, maximizing engagement and the effectiveness of marketing activities.

[0736] "Generative artificial intelligence" is an artificial intelligence technology that generates information based on goals and target information set by the user.

[0737] "User's emotional state" refers to the emotional state information that users exhibit when sharing information on social networking platforms, and it is a factor used to personalize information based on this state.

[0738] "Methods for personalizing information" refer to the process of adjusting the tone and content of the information generated according to the user's emotional state and preferences.

[0739] "Interaction data" refers to data about the actions and reactions that users perform on social interaction networks, and is used to optimize the timing of information generation and transmission.

[0740] "Appropriate transmission time and frequency" refers to the optimal timing and frequency for information to be received by users in the most effective way.

[0741] "Performance data" refers to data that shows how effective transmitted information was on social networking.

[0742] This invention is a system for optimizing information dissemination in social networking, and its main components are a server, a terminal, and a generative AI model.

[0743] Users can access the system's settings screen using their devices and input their goals and target information. This clearly indicates the type of information the user is seeking and their target audience.

[0744] The server utilizes various software to process data received from users. Specifically, it employs natural language processing (NLP) techniques to analyze emotional states and uses machine learning frameworks such as TensorFlow and PyTorch. This allows for accurate evaluation of the user's emotional state and appropriate adjustment of the tone and style of the information generated.

[0745] Furthermore, the server uses a generative AI model, such as OpenAI's, as its generative artificial intelligence. The generative AI generates customized information by taking prompts based on the user's goals and emotional state. This information is stored in a database and transmitted to the social network at the appropriate time.

[0746] For example, the following prompt statements can be used for a generative AI model:

[0747] "Please create a positive and exciting story for our new product campaign post. Our target audience is working women in their 20s and 30s."

[0748] The server further analyzes user interaction data to determine the optimal transmission time and frequency. This process utilizes Python's Pandas and Scikit-learn as data analysis tools to learn from past data and optimize future information dissemination strategies.

[0749] In this way, this system can provide users with highly personalized information and enhance their presence within social networking networks.

[0750] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0751] Step 1:

[0752] The user accesses the system's settings screen using their device. Here, they enter their goals and target information. The input data includes an overview of the target campaign and the characteristics of the target audience. This information is sent to the server as input.

[0753] Step 2:

[0754] The server receives input data from the user and begins data analysis. Based on the received data, it analyzes the user's emotional state using natural language processing techniques. Specifically, it extracts emotional characteristics from the input text data. As output, numerical data representing the user's emotional state is generated.

[0755] Step 3:

[0756] The server generates information using a generative AI model based on the analysis results. It takes emotional characteristic data as input, provides prompts to the generative AI model, and generates personalized information. The generative AI model, for example, creates text adjusted to the tone and style desired by the user. The output of this step is the generated content.

[0757] Step 4:

[0758] The server saves the generated content to a database. The saved data is managed efficiently for use in subsequent processes. Specific operations include storage operations using a database management system (DBMS).

[0759] Step 5:

[0760] The server analyzes past interaction data to determine the optimal transmission time and frequency. It learns from historical data using Python's Pandas and Scikit-learn libraries and applies optimization algorithms. This process provides output for building future information dissemination strategies.

[0761] Step 6:

[0762] The server transmits the generated information to the social network according to the determined transmission schedule. Transmission takes place via network APIs. As a result of transmission, the information is delivered to the appropriate recipients. The output of this step is the transmission completion status.

[0763] (Application Example 2)

[0764] 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".

[0765] Advertising and marketing activities on information exchange networks require the provision of personalized content that takes into account the emotional state of users. However, conventional systems have difficulty generating content in real time that responds to users' emotions, making it challenging to achieve effective user engagement.

[0766] 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.

[0767] In this invention, the server includes means for sensing the user's emotional state and designing advertisements based on it, means for generating content based on the user's set goals and target information using generative artificial intelligence, and means for automatically posting the generated content to multiple information exchange networks. This makes it possible to provide advertisements that match the user's emotional state in real time and achieve effective marketing results.

[0768] "Means for sensing the user's emotional state" refers to a function that identifies and analyzes the user's emotions using information entered by the user and sensor data.

[0769] "A means of designing advertisements" refers to a function that generates and optimizes the tone and content of advertisements based on the user's emotional state.

[0770] "Generative artificial intelligence" is an advanced computing technology that uses natural language processing and image generation techniques to create information tailored to the user.

[0771] An "information exchange network" is a platform where multiple users share content and communicate with each other.

[0772] "Means for acquiring and analyzing interaction data" refers to a function that aggregates user operation history and responses and analyzes that data.

[0773] "Means for determining the optimal posting time and frequency" refers to a function that uses acquired data to determine the most effective time of day and frequency for posting content.

[0774] "Means for analyzing performance data and generating reports" refers to a function that evaluates the effectiveness of advertisements after posting and compiles the results into a report.

[0775] The system that realizes this invention includes a process for accurately sensing the user's emotional state and designing personalized advertisements based on that state. A smartphone is typically used as the hardware for this purpose. On the device, an emotion engine operates that analyzes emotions based on user input.

[0776] The server receives emotional data from users and generates advertising content using generative artificial intelligence (generative AI model). By applying natural language processing technology, it designs ads with a tone and visual style that matches the user's current emotional state. For example, if the server detects that the user is in a calm mood, ads related to relaxation products will be generated. Throughout this process, the emotional engine constantly receives feedback to improve the quality of the generated content.

[0777] Furthermore, the server analyzes the acquired performance data to optimize future content strategies. This data provides important indicators for, for example, improving user engagement and expanding product awareness. The generated advertisements are effectively distributed within the information exchange network.

[0778] For example, if a user is perceived as being in a "calm mood," the generative AI model will construct relevant advertisements based on a prompt such as, "Here are some great ways to spend your weekend for relaxation." Advertisements generated based on this prompt are more likely to interest the user, thus improving marketing effectiveness.

[0779] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0780] Step 1:

[0781] The user accesses the emotion input module using a terminal and inputs their current emotional state. The input data records the user's emotional status. As output, emotion data is generated and sent to the server.

[0782] Step 2:

[0783] The server analyzes the received emotional data using an emotion engine. In this step, the emotion engine uses natural language processing techniques to identify the user's mood and state. The output of the analysis is an analysis result indicating the user's emotional state.

[0784] Step 3:

[0785] The server uses generative artificial intelligence (generative AI model) to generate ad prompts based on the analysis results. This process designs ad content with appropriate tone and style based on sentiment data. The output is the generated prompt text.

[0786] Step 4:

[0787] The generative AI model receives a prompt and generates ad copy and related visuals based on it. The data calculation performed here is to create the optimal ad by utilizing the model's training data. The generated ad is obtained as the output.

[0788] Step 5:

[0789] The server uses the generated advertisement to post it to the user information exchange network. In this process, posting is executed through an appropriate application program interface, and the advertisement is published on the network. The output confirms the completion of the posting.

[0790] Step 6:

[0791] After posting, the server collects user reactions and interaction data and analyzes performance data. At this stage, it measures the effectiveness of the advertisement and generates information that can be used to improve future campaigns. The output is a report of the analysis results.

[0792] 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.

[0793] 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.

[0794] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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."

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] The following is further disclosed regarding the embodiments described above.

[0814] (Claim 1)

[0815] A means for generating content based on user-defined goals and target information using generative artificial intelligence,

[0816] A means of automatically posting generated content to multiple social networking networks,

[0817] A means for acquiring and analyzing user interaction data to determine the optimal posting time and frequency,

[0818] A means by which generated content is regenerated or modified based on the user's intentions,

[0819] A system that includes means for analyzing performance data after posting and generating reports.

[0820] (Claim 2)

[0821] The system according to claim 1, comprising means for connecting and authenticating via application program interfaces of various social interaction networks.

[0822] (Claim 3)

[0823] The system according to claim 1, comprising means for optimizing future posting content and schedule based on data obtained after posting.

[0824] "Example 1"

[0825] (Claim 1)

[0826] A means of utilizing artificial intelligence to create content based on user-defined goals and target information,

[0827] A method for automatically posting the created content to a large network of social interaction sites,

[0828] A means of collecting and analyzing user response data to determine the optimal posting timing and frequency,

[0829] A means by which the created content is regenerated or modified according to the user's wishes,

[0830] A system that includes a means of analyzing performance data after posting and generating reports.

[0831] (Claim 2)

[0832] The system according to claim 1, comprising means for connecting and authenticating through an application program interface of a network for various social interactions.

[0833] (Claim 3)

[0834] The system according to claim 1, comprising means for optimizing future posting content and schedule based on data obtained after posting.

[0835] "Application Example 1"

[0836] (Claim 1)

[0837] A means for generating information based on user-defined goals and target information using generative artificial intelligence,

[0838] A means of automatically disseminating generated information to multiple social communication platforms,

[0839] A means for collecting and analyzing user response data to determine the optimal transmission time and frequency,

[0840] A means by which the generated information is regenerated or modified based on the user's will,

[0841] A means of analyzing the results data after the information is sent and creating a report,

[0842] A system that includes means for calculating a transmission schedule using historical time-series data.

[0843] (Claim 2)

[0844] The system according to claim 1, comprising means for connecting and authenticating via application program interfaces of various social interaction platforms.

[0845] (Claim 3)

[0846] The system according to claim 1, comprising means for optimizing future transmission content and plans based on data acquired after transmission.

[0847] "Example 2 of combining an emotion engine"

[0848] (Claim 1)

[0849] A means for generating information based on user-defined goals and target information using generative artificial intelligence,

[0850] A means of analyzing the emotional state of users and personalizing the information generated based on the results,

[0851] A means for automatically transmitting generated information to multiple social networking networks,

[0852] A means for acquiring and analyzing user interaction data and determining appropriate transmission time and transmission frequency,

[0853] A means by which the generated information is regenerated or modified based on the user's wishes,

[0854] A system that includes means for analyzing performance data after transmission and generating a report.

[0855] (Claim 2)

[0856] The system according to claim 1, comprising means for connecting and authenticating via application program interfaces of various social interaction networks.

[0857] (Claim 3)

[0858] The system according to claim 1, further comprising means for optimizing future transmission content and plans based on data acquired after transmission.

[0859] "Application example 2 when combining with an emotional engine"

[0860] (Claim 1)

[0861] A means of sensing the emotional state of users and designing advertisements based on that,

[0862] A means for generating content based on user-defined goals and target information using generative artificial intelligence,

[0863] A means of automatically posting generated content to multiple information exchange networks,

[0864] A means for acquiring and analyzing user interaction data to determine the optimal posting time and frequency,

[0865] A means by which generated content is regenerated or modified based on the user's intentions,

[0866] A system that includes means for analyzing performance data after submission and generating reports.

[0867] (Claim 2)

[0868] The system according to claim 1, comprising means for connecting and authenticating via application program interfaces of various information exchange networks.

[0869] (Claim 3)

[0870] The system according to claim 1, comprising means for optimizing future posting content and schedule based on data obtained after posting. [Explanation of symbols]

[0871] 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 means for generating information based on user-defined goals and target information using generative artificial intelligence, A means of automatically disseminating generated information to multiple social communication platforms, A means for collecting and analyzing user response data to determine the optimal transmission time and frequency, A means by which the generated information is regenerated or modified based on the user's will, A means of analyzing the results data after the information is sent and creating a report, A system that includes means for calculating a transmission schedule using historical time-series data.

2. The system according to claim 1, comprising means for connecting and authenticating via application program interfaces of various social interaction platforms.

3. The system according to claim 1, further comprising means for optimizing future transmission content and plans based on data acquired after transmission.

Images