System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting viewing data; means for analyzing the collected viewing data and evaluating performance for each platform; means for generating an optimal content strategy for each platform based on an analysis result; means for notifying a user of the generated content strategy; and means for collecting feedback from the user and reflecting the feedback in future strategy generation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Currently, many video streamers are active on multiple platforms, but it is not easy to develop an effective content strategy that addresses the different viewer habits and preferences on each platform. Analyzing viewing data and formulating an appropriate strategy to maximize performance can be particularly challenging for novice video streamers. Furthermore, optimal content delivery while maintaining consistency across different platforms is a time-consuming and labor-intensive task. There is a need for a system that can solve these problems and help video streamers acquire viewers efficiently and effectively. [Means for solving the problem]

[0005] This invention solves the above-mentioned problems by providing a system that collects and analyzes viewing data to evaluate the performance of each platform and generate an optimal content strategy. Specifically, the system includes a means for collecting viewing data, a means for analyzing the collected viewing data and evaluating performance for each platform, and a means for generating an optimal content strategy for each platform based on the analysis results. The system also includes a means for notifying users of the generated content strategy and collecting user feedback to reflect this in the generation of future strategies. This makes it easier for video distributors to efficiently and effectively acquire viewers on each platform and enables consistent content distribution.

[0006] "Viewing data" refers to data that includes information such as the number of times video content is played on each digital platform, viewer attributes, viewing time, viewing completion rate, number of likes and comments, etc.

[0007] "Analysis" is the process of analyzing collected viewing data using statistical or machine learning methods to identify patterns and trends in viewer behavior.

[0008] "Performance evaluation" refers to evaluating the effectiveness of video content published on each platform using indicators such as number of views, engagement rate, and viewing time.

[0009] "Content strategy" refers to a specific action plan or plan for video streamers to effectively acquire viewers on each platform, including appropriate video themes, length, and posting frequency.

[0010] A "platform" refers to an online service or application where video streamers can publish content, including YouTube, TikTok, Instagram, and others.

[0011] "Notification" is the act of transmitting the generated content strategy to the video distributor's device and displaying it visually or audibly.

[0012] "Feedback" is the process of gathering information about the results and satisfaction of a video streamer's content strategy, data that can be used to improve future strategies. [Brief explanation of the drawings]

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

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

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

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

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

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

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

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

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

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

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0030] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

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

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0034] This invention provides a system that collects and analyzes viewing data, generates an optimal content strategy, and notifies users, thereby enabling users to effectively acquire viewers on each platform. Specific embodiments of this system are described below.

[0035] System configuration

[0036] server

[0037] 1. Collection of viewing data:

[0038] The server collects viewing data from each platform (e.g., YouTube, TikTok, Instagram) by sending API requests to obtain data including the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[0039] 2. Data Analysis:

[0040] The collected viewing data is converted into a unified format and analyzed to identify patterns and trends in viewer behavior, using statistical methods and machine learning models.

[0041] 3. Performance Evaluation:

[0042] Evaluate the performance of each piece of content (number of views and engagement rates) to identify which content is effective on which platforms.

[0043] 4. Generate a content strategy:

[0044] Based on the analysis results, the system generates the optimal content strategy for each platform, providing advice tailored to the characteristics of each platform, such as recommending long videos for YouTube and short videos for TikTok.

[0045] Terminal

[0046] 1. Receiving and displaying the strategy:

[0047] The user's device receives the strategy data generated by the server and visually displays it, providing specific advice for each platform in a user-friendly dashboard format.

[0048] 2. Gathering Feedback:

[0049] Provide an interface for collecting feedback from users, including performance data and satisfaction after implementing the strategy.

[0050] User

[0051] 1. Strategy Implementation:

[0052] Users post content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explainer video for YouTube, users create and post the video accordingly.

[0053] 2. Providing Feedback:

[0054] The results of the strategy execution are entered into the interface and sent to the server, which then obtains data to use in future strategy generation.

[0055] Specific examples

[0056] For example, User A distributes videos on YouTube and TikTok. The server analyzes data from YouTube that shows that long explanatory videos are popular, and determines that short, impactful skits are preferred on TikTok. Following the strategy generated by the server, User A posts long, specialized explanatory videos on YouTube and short, entertaining skits on TikTok. After posting, User A collects viewing data for each piece of content and provides feedback to the server via their device.

[0057] In this way, users can implement effective content strategies across each platform and optimize audience acquisition.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The server sends a request to the API endpoint of each platform (YouTube, TikTok, Instagram, etc.) to obtain viewing data, including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0061] Step 2:

[0062] The server converts the raw data it acquires into a unified format, which is done to streamline the subsequent analysis process.

[0063] Step 3:

[0064] The server uses statistical methods and machine learning algorithms to analyze the aggregated viewing data, with the goal of identifying patterns and trends in viewer behavior.

[0065] Step 4:

[0066] The server evaluates the performance of each platform based on the analysis results, including the number of views, engagement rate, and viewing time.

[0067] Step 5:

[0068] The server generates the optimal content strategy for each platform, making suggestions based on the characteristics of each platform, such as recommending long videos for YouTube and short videos for TikTok.

[0069] Step 6:

[0070] The server generates a content strategy that is delivered to the user's device, displayed in a user-friendly dashboard format and includes specific advice for each platform.

[0071] Step 7:

[0072] The device visually displays the content strategy notified by the server to the user, who then uses the displayed strategy to create a content plan and decide what to post on each platform.

[0073] Step 8:

[0074] Users post content to each platform through their devices according to the content strategy proposed by the server, for example, posting long-form expert instructional videos to YouTube and short, funny skits to TikTok.

[0075] Step 9:

[0076] The results of the strategies implemented by the user are collected and entered into the device, including viewing data after content is posted, engagement rates, and user satisfaction.

[0077] Step 10:

[0078] The device sends the feedback data collected from the user to the server, which can then use this feedback to improve future content strategies and provide more effective advice.

[0079] This specific process flow allows users to effectively acquire viewers across platforms and achieve consistent content delivery.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] Conventional content strategy generation systems require a lot of manual work to collect and analyze viewing data, making them inefficient. Furthermore, generating effective content strategies for different digital platforms requires advanced expertise, making them difficult for average users to use. Furthermore, there is a lack of a mechanism for continuously evaluating the effectiveness of the generated strategies and reflecting this in the next strategy generation, making it difficult to adapt to viewer needs.

[0083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0084] In this invention, the server includes means for collecting viewing data, means for converting the collected viewing data into a unified format and performing data cleansing, means for analyzing the viewing data after data cleansing and identifying viewer behavior patterns and trends, means for evaluating the performance of each platform based on the analysis results, means for generating an optimal content strategy for each platform using a generative AI model, means for notifying users of the generated content strategy in a user-friendly dashboard format, and means for collecting feedback from users and reflecting it in future strategy generation. This makes it possible to implement a series of automated processes from viewing data collection to analysis, strategy generation, and feedback collection, thereby enabling effective content strategies to be provided quickly and efficiently.

[0085] "Viewing data" refers to data that indicates the viewing status of videos and content on each digital platform, and includes the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc.

[0086] "Data cleansing" is the process of removing inaccurate information, duplicate information, and missing values ​​from collected viewing data and preparing it in an analyzable format.

[0087] "Behavioral patterns" refer to specific actions or tendencies that viewers exhibit on digital platforms, and are characteristics identified through analysis of factors such as length of viewing time and reactions to specific content.

[0088] A "trend" refers to an increasing audience interest or concern over a specific period of time, including a spike or decline in interest in a particular topic or genre.

[0089] "Performance" is an indicator of how well content is received by viewers and how much engagement it generates, and is an evaluation calculated based on the number of views and engagement rate (number of likes, number of comments, etc.).

[0090] "Generative AI model" is a general term for artificial intelligence models that generate natural language based on data and output analytical results, and are used to generate content strategies.

[0091] A "dashboard" is an interface that displays data and strategies in a visually easy-to-understand format for users, and includes strategies and analysis results for each platform.

[0092] "Feedback" refers to data that a user inputs, such as the results, impressions, and improvements of the content strategy they have implemented, and sends to the server, and is reflected in future strategy generation.

[0093] This invention provides a system that collects and analyzes viewing data, generates an optimal content strategy, and notifies users, thereby enabling users to effectively acquire viewers on each platform. Specific embodiments of this system are described below.

[0094] System configuration

[0095] server

[0096] The server uses a high-performance server computer and multiple pieces of software to collect viewing data, analyze it, evaluate performance, and generate content strategies. Specifically, it uses programming languages ​​such as Python and Node.js to send API requests to the YouTube Data API, TikTok API, and Instagram Graph API to obtain information such as the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[0097] The server that collects the viewing data first uses "pandas" to convert the data into a unified format. During the data cleansing process, missing values ​​are filled in and unnecessary data is removed. The cleansed data is then analyzed using statistical methods and machine learning models (e.g., scikit-learn, TensorFlow). This analysis identifies viewer behavior patterns and trends, and the results are visualized using Matplotlib.

[0098] Next, the performance of each piece of content is evaluated based on the number of views and engagement rate, and changes are compared with past data to create a report. This report is visually presented using a data visualization tool (e.g., Tableau).

[0099] Based on the analysis results, a generative AI model (e.g., GPT-3) is used to generate an optimal content strategy for each platform. The generated strategy is converted into JSON format and sent to the user's device.

[0100] Terminal

[0101] The user's device (PC or smartphone) receives the generated content from the server via an HTTP request. The received data is displayed in a user-friendly dashboard format. The software used here is a front-end framework such as React or Vue.js. This makes it easier to understand the strategy through a visual interface.

[0102] The terminal also provides an interface where users can enter feedback. After the user enters the feedback and presses the submit button, the data is sent to the server via the terminal. The terminal sends the form data as a POST request to a specific API endpoint on the server.

[0103] User

[0104] Users post new content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explanatory video on YouTube, the user creates a video along those lines and posts it. They check performance data on the management screen or app of each platform, enter that data into a dedicated form, and send feedback to the server. This allows the server to use the feedback information to generate future strategies.

[0105] Specific examples

[0106] For example, User A distributes videos on YouTube and TikTok. The server collects viewing data and uses the YouTube Data API and TikTok API to obtain data such as the number of views, viewing time, and viewer attributes from each platform. The server then cleanses the data using "pandas" and analyzes behavioral patterns using "scikit-learn." Based on the analysis results, GPT-3 determines that long-form explanatory videos are effective on YouTube and short skits on TikTok, and generates a new content strategy. This strategy is sent to User A's device in JSON format and displayed visually on a dashboard. User A creates and posts content according to the strategy and sends feedback to the server via their device, which will be used to generate the next strategy.

[0107] Prompt Sentence Examples

[0108] Generate an optimal content strategy for User A, who distributes videos on YouTube and TikTok. Please propose a specific strategy based on the analysis results of what types of videos are popular on YouTube and what types of content are preferred on TikTok. Furthermore, please tell us the expected results and performance indicators that should be measured after implementing the strategy.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1: The server collects viewing data from each digital platform. Specifically, the server uses the YouTube Data API, TikTok API, and Instagram Graph API to obtain data such as the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc. using the Python library "requests." This data is received in JSON format and stored in a database (e.g., MySQL or MongoDB). The input is the response data from the API request, and the output is the viewing data stored in the database.

[0111] Step 2: The server converts the collected viewing data into a unified format and performs data cleansing. Python's "pandas" is used to fill in missing values ​​and delete unnecessary data. The input is viewing data in JSON format, and the output is cleansed data in CSV or JSON format. Specific operations include filling in missing values, deleting duplicate data, and standardizing the format.

[0112] Step 3: The server analyzes the cleansed viewing data to identify viewer behavior patterns and trends. Using the Python machine learning libraries "scikit-learn" and "TensorFlow," it builds a model to identify viewer behavior patterns from the data. The input is the cleansed viewing data, and the output is the analysis results on viewer behavior patterns and trends. Specific operations include extracting features from the data, training the model, and making inferences.

[0113] Step 4: The server evaluates the performance of each platform. It scores the performance of each piece of content based on factors such as the number of views, engagement rate, and number of comments, and compiles the evaluation results into a report. This process uses data visualization tools (e.g., Matplotlib, Tableau). The input is the analysis results, and the output is a performance evaluation report. Specific operations include calculating evaluation indicators, comparing them with past data, and generating graphs.

[0114] Step 5: The server uses a generative AI model (e.g., GPT-3) to generate an optimal content strategy and converts it into JSON format. It inputs a prompt to the AI ​​model and receives a response from the API with the generated strategy. The input is the prompt and the analysis result, and the output is the generated content strategy. Specific operations include setting the prompt, making a request to the AI ​​model, and analyzing the response.

[0115] Step 6: The terminal receives the content strategy generated from the server and displays it in a user-friendly dashboard format. It uses a front-end framework (e.g., React, Vue.js) to visually organize the received data and provide it to the user. The input is the strategy data in JSON format from the server, and the output is a visual display on the dashboard. Specific operations include parsing the data and generating graphs and lists.

[0116] Step 7: The user posts content to each platform based on the generated content strategy. For example, if you want to upload a long-form explainer video to YouTube, you shoot the video, edit it, and then upload it to YouTube. The input is the content strategy, and the output is the posted content. The specific actions are creating, editing, and uploading the video.

[0117] Step 8: The user enters the results after the strategy is implemented into a dedicated form and sends feedback from the terminal to the server. The form data is sent to the server's API endpoint as a POST request. The input is the performance data after the strategy is implemented, and the output is the feedback sent to the server. Specific actions include entering data, clicking the submit button, and transferring the data to the server.

[0118] Step 9: The server collects feedback from users and reflects it in future strategy generation. The collected feedback is stored in a database and used for the next data analysis and strategy generation. The input is feedback data from users, and the output is data reflected in the next analysis and strategy generation. Specific operations include storing the feedback in the database and integrating it into the subsequent analysis process.

[0119] (Application example 1)

[0120] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0121] In recent years, a variety of digital platforms have emerged, and content creators need to effectively reach viewers with different characteristics on each platform. However, doing so requires time and expertise to collect and analyze vast amounts of viewing data and generate optimal content strategies. Furthermore, a system that efficiently reflects user feedback and continuously optimizes content is also important. It is desirable to provide a system that can solve these challenges and enable users to effectively acquire viewers on each platform.

[0122] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0123] In this invention, the server includes means for collecting viewing data, means for analyzing the collected viewing data and evaluating performance for each platform, means for generating an optimal content strategy for each platform based on the analysis results, means for notifying users of the generated content strategy, means for collecting feedback from users and reflecting it in generating future strategies, means for providing a user interface optimized for smartphones and displaying visual advice, and means for updating and continuously optimizing a machine learning model based on the feedback data. This enables users to efficiently analyze viewing data, implement an optimal content strategy for each platform, and effectively acquire viewers.

[0124] "Viewing data" refers to information about when a user views content on a digital platform, including the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc.

[0125] A "platform" is a digital service that distributes content and allows viewers to access it, such as YouTube, TikTok, or Instagram.

[0126] "Performance" is the result of evaluating viewer response and engagement with content, taking into account indicators such as number of views, viewing time, number of likes and comments.

[0127] A "content strategy" is a policy for determining the format and content of content to effectively attract viewers on each platform, and includes recommendations such as long-form videos and short skits.

[0128] "User" refers to an individual or entity that utilizes the system provided in accordance with this invention to distribute content or execute strategies.

[0129] "Feedback" refers to information provided by users about the results and satisfaction after strategy implementation, which is used to improve future strategy generation.

[0130] A "machine learning model" is a collection of algorithms for analysis and prediction using viewing data and feedback data, and improves accuracy by continuously learning from the data.

[0131] The "user interface" refers to the interface that allows users to operate the system and visually check the generated content strategy, and is optimized for smartphones.

[0132] This invention is a system that collects and analyzes viewing data and provides users with optimal content strategies. This system is composed of a server, a terminal, and a user.

[0133] server

[0134] The server has the following features:

[0135] 1. Collecting viewing data

[0136] It collects viewing data from each digital platform, specifically using the platform's API to obtain data such as the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0137] 2. Data Analysis

[0138] The collected viewing data is converted into a unified format and analyzed using statistical methods and machine learning models to process the data and identify patterns and trends in viewer behavior.

[0139] 3. Performance Evaluation

[0140] Evaluate the performance of each piece of content (number of views and engagement rates) to identify which content is effective on which platforms.

[0141] 4. Generate a content strategy

[0142] Based on the analysis, it generates the optimal content strategy for each platform, for example recommending long-form videos for YouTube and short-form videos for TikTok based on viewing patterns.

[0143] 5. Gathering feedback and updating the machine learning model

[0144] It collects user feedback data and uses it to update the machine learning model, thereby continuously optimizing the system.

[0145] Terminal

[0146] The terminal has the following features:

[0147] 1. Receiving and displaying the strategy

[0148] The server receives the generated content strategy and visually displays it to the user in a user-friendly dashboard format that is optimized for smartphones.

[0149] 2. Gathering feedback

[0150] Provide an interface for collecting feedback from users, including performance data and satisfaction after implementing the strategy.

[0151] User

[0152] The user has the following capabilities:

[0153] 1. Strategy Implementation

[0154] Users post content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explainer video for YouTube, the user creates and posts the video accordingly.

[0155] 2. Providing Feedback

[0156] The results of the strategy execution are entered into the terminal interface and sent to the server, which collects the data necessary for future strategy generation.

[0157] Specific examples

[0158] For example, consider the case where User A distributes videos on YouTube and TikTok. The server analyzes YouTube viewing data and determines that long explanatory videos are popular, while short, impactful skits are preferred on TikTok. Following the strategy generated by the server, User A posts long, specialized explanatory videos on YouTube and short, entertaining skits on TikTok. After posting, User A collects viewing data for each piece of content and provides feedback to the server via their device. This allows the system to reflect this in future strategies.

[0159] Prompt Sentence Examples

[0160] Create a Python script that allows users to collect viewing data from YouTube, TikTok, and Instagram, and generate optimal content strategies based on data analysis.

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] The server collects viewing data.

[0164] Input: Viewing data requests from the API of each platform (e.g. YouTube, TikTok, Instagram).

[0165] Specific operation: The server uses the API of each digital platform to collect viewing data such as the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc. It sends requests using the API authentication key and receives data from each platform.

[0166] Output: JSON format response of the retrieved viewing data.

[0167] Step 2:

[0168] The server analyzes the collected viewing data.

[0169] Input: Viewing data obtained in step 1.

[0170] What it does: The server converts the viewing data into a unified format and analyzes it using machine learning models to identify patterns and trends in viewer behavior. It converts the data into TF-IDF vectors and classifies the viewing data using KMeans clustering.

[0171] Output: Viewing data patterns and trend information for each cluster.

[0172] Step 3:

[0173] The server evaluates the performance.

[0174] Input: Analysis results from step 2.

[0175] Specific operation: The server evaluates the performance of viewing data (number of views, engagement rate, etc.) for each platform and identifies which content is effective. Specifically, it analyzes the distribution of viewing numbers and engagement rates for each cluster and determines the optimal content format for each platform.

[0176] Output: Performance evaluation results for each platform.

[0177] Step 4:

[0178] The server generates the content strategy.

[0179] Input: Performance evaluation results from step 3.

[0180] What it does: Based on the analysis results, it generates the optimal content strategy for each platform, for example, recommending long videos for YouTube and short videos for TikTok based on viewing patterns.

[0181] Output: Optimal content strategies for each generated platform.

[0182] Step 5:

[0183] The terminal receives the strategy and notifies the user.

[0184] Input: The content strategy generated in step 4.

[0185] Specific operation: The device receives content strategy data from the server and visually displays it to the user. The strategy content is provided in dashboard format through a smartphone-oriented user interface.

[0186] Output: A visual content strategy interface for the user.

[0187] Step 6:

[0188] Users post content based on a strategy.

[0189] Input: Content strategy provided in step 5.

[0190] Specific behavior: Users follow the provided strategy to create and post content in a format appropriate for each platform, for example, posting a long-form explainer video on YouTube and a short skit on TikTok.

[0191] Output: Content posted to each platform.

[0192] Step 7:

[0193] The device collects the feedback and sends it to the server.

[0194] Input: Outcome data and satisfaction level provided by users after strategy implementation.

[0195] Specific operations: The results after the strategy is executed (number of views, engagement rate, etc.) are entered into the user interface and sent to the server.

[0196] Output: Feedback data.

[0197] Step 8:

[0198] The server updates the machine learning model based on the feedback data.

[0199] Input: Feedback data collected in step 7.

[0200] What it does: The server analyzes the feedback data and updates the machine learning model, allowing the system to generate more accurate content strategies in future.

[0201] Output: An updated machine learning model.

[0202] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0203] This invention is a system that combines a system that collects and analyzes viewing data and generates optimal content strategies for each platform with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0204] System configuration

[0205] server

[0206] 1. Collection of viewing data:

[0207] The server retrieves viewing data from the API endpoints of each digital platform (e.g., YouTube, TikTok, etc.), including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0208] 2. Data Analysis:

[0209] The raw data is then converted into a unified format and analyzed to identify patterns and trends in viewer behavior using statistical methods and machine learning algorithms.

[0210] 3. Emotion Recognition with Emotion Engine:

[0211] The server uses an emotion engine to analyze facial and voice data from the user's device to identify the user's emotions, for example, using data from a webcam or microphone.

[0212] 4. Performance evaluation and strategy generation:

[0213] We evaluate the performance of each platform based on the results of viewing data analysis and user sentiment data, and then generate the optimal content strategy for each platform based on the evaluation results.

[0214] 5. Strategic Notification:

[0215] The server generates strategy data and sends it to the user's device, where specific advice for each platform is displayed in a user-friendly dashboard format.

[0216] 6. Feedback Collection:

[0217] Feedback data from users is collected and reflected in future strategy generation. Since the feedback includes emotional data, the data collected by the emotion engine is also taken into account.

[0218] Terminal

[0219] 1. Receiving and displaying the strategy:

[0220] The terminal receives strategic data from the server and visually displays it, providing specific advice to the user in the form of a dashboard.

[0221] 2. Collecting Emotional Data:

[0222] The user's facial expressions and voice data are collected through a webcam and microphone and sent to a server, which then identifies the user's emotions in real time.

[0223] User

[0224] 1. Strategy Implementation:

[0225] Users post content to each platform according to the content strategy from the server. Based on data, for example, users can post long videos to YouTube and short videos to TikTok to increase viewer engagement.

[0226] 2. Emotion-based regulation:

[0227] It adjusts content direction based on real-time feedback from the server. For example, if the emotion engine detects that the user is dissatisfied, it automatically adjusts its strategy.

[0228] 3. Providing Feedback:

[0229] The results after posting content are collected and feedback, including emotional data, is sent to the server, which then obtains the data necessary for future strategy generation.

[0230] Specific examples

[0231] For example, User B distributes videos on YouTube and TikTok. The server analyzes the viewing data obtained from User B and User B's emotional data during the distribution (e.g., emotion recognition data from facial expressions and voice). Based on this data, the server generates a content strategy that recommends "long explanatory videos" on YouTube and "short, fun skits" on TikTok. User B then posts a long video on YouTube and a short video on TikTok. The viewing data and emotional data after posting are then sent to the server as feedback, which the server uses to generate the next strategy.

[0232] In this way, the system can provide more accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement across platforms.

[0233] The processing flow will be explained below.

[0234] Step 1:

[0235] The server sends requests to the API endpoints of each digital platform (YouTube, TikTok, Instagram, etc.) to obtain viewing data, including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0236] Step 2:

[0237] The server converts the raw data it acquires into a unified format to eliminate differences between platforms and facilitate subsequent analysis.

[0238] Step 3:

[0239] The server analyzes the aggregated viewing data, using statistical methods and machine learning algorithms to identify patterns and trends in viewer behavior.

[0240] Step 4:

[0241] The server evaluates the performance of each platform based on the analysis results, including the number of views, engagement rate, and viewing time, and analyzes how each indicator contributes.

[0242] Step 5:

[0243] The server uses an emotion engine to analyze facial expressions and voice data collected from the user's device, and identifies the user's emotional state through the analysis.

[0244] Step 6:

[0245] The server combines the results of the viewing data analysis with user sentiment data to generate the optimal content strategy for each platform. For example, YouTube recommends long videos, while TikTok recommends short videos.

[0246] Step 7:

[0247] The server sends the generated content strategy to the user's device, where a notification is displayed, allowing the user to confirm specific actions based on the strategy.

[0248] Step 8:

[0249] The device receives notifications from the server and visually displays strategies to the user, providing specific advice for each platform in the form of a dashboard.

[0250] Step 9:

[0251] Users post content to each platform based on a content strategy suggested by the server, for example, posting a long-form explainer video to YouTube and a short, fun skit to TikTok.

[0252] Step 10:

[0253] The device collects the user's facial expressions and voice data in real time, analyzes it through an emotion engine, and sends it to a server, allowing changes in the user's emotions to be grasped in real time.

[0254] Step 11:

[0255] The user evaluates the results of the content strategy and their emotional state, and then inputs the feedback into the terminal. The feedback includes viewing data and emotional data.

[0256] Step 12:

[0257] The device collects feedback data from users and sends it to the server, which uses this feedback to improve the strategy generation process and provide more accurate advice in the future.

[0258] Through this specific process, the system can provide content strategies that take into account the user's emotional state and effectively acquire audiences on each platform.

[0259] Example 2

[0260] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0261] Conventional content strategy generation systems were able to generate strategies based on the analysis of viewing data, but were unable to generate strategies that took into account viewer emotions. As a result, strategies that did not reflect viewer reactions or emotions resulted in the provision of less than optimal content. Furthermore, strategies that took into account the characteristics of each platform across multiple digital platforms were not sufficiently generated.

[0262] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting viewing data, a means for converting the collected viewing data into a unified format and analyzing it, a means for collecting user facial expression and voice data and recognizing emotions, a means for generating an optimal content strategy for each platform based on the analysis results and emotion data, a means for notifying the user of the generated content strategy on the user's terminal and visually displaying it, and a means for collecting feedback data from the user and reflecting it in future strategy generation. This makes it possible to generate a more accurate content strategy that takes into account not only viewing data but also viewer emotions. It is also possible to provide a strategy that takes into account the characteristics of each platform.

[0263] "Viewing data" refers to data including the number of views on digital platforms, viewing time, viewing completion rate, viewer attributes, number of likes and comments, etc.

[0264] The "unified format" is a data format that converts viewing data collected from multiple digital platforms into a format that is easy to analyze.

[0265] "Facial expression data" refers to data relating to the facial expressions of a user captured through a webcam.

[0266] "Voice data" refers to data relating to the user's speech or voice acquired through a microphone.

[0267] "Emotion recognition" means analyzing facial expression data and voice data to identify the user's emotional state (for example, joy, sadness, surprise, etc.).

[0268] The "analysis results" are analysis results based on viewing data and emotional data, and indicate the behavioral patterns and emotional tendencies of viewers.

[0269] "Content strategy" refers to the type, content, timing, etc. of content posted on digital platforms.

[0270] A "user terminal" is a device (e.g., a PC, a smartphone, a tablet, etc.) that visually displays strategic data and collects feedback from users.

[0271] "Feedback data" refers to data provided by users that includes opinions, results, and sentiment data regarding content strategies.

[0272] This invention is a system that collects and analyzes viewing data to generate optimal content strategies for each platform. Furthermore, by combining it with an emotion engine that recognizes user emotions, it provides a more accurate content strategy.

[0273] server

[0274] 1. Collection of viewing data:

[0275] The server obtains viewing data from digital platforms such as YouTube and TikTok through APIs, using OAuth for authentication, and collects data such as the number of views, viewer attributes, viewing time, completion rate, likes, and comments.

[0276] 2. Data Analysis:

[0277] The server uses Python's pandas library to convert the collected viewing data into a unified format, then analyzes the data using machine learning algorithms such as scikit-learn to identify patterns in viewer behavior.

[0278] 3. Emotion Recognition with Emotion Engine:

[0279] The server collects facial and voice data from the user's device in real time and recognizes emotions. It uses the OpenCV library to analyze facial data and the Google Cloud Speech-to-Text API to analyze voice data.

[0280] 4. Performance evaluation and strategy generation:

[0281] The server evaluates the performance of each platform based on viewing data analysis and sentiment data, and then uses a generative AI model to generate the optimal content strategy for each platform.

[0282] 5. Strategic Notification:

[0283] The server sends the generated strategy to the user's device, where it is visually displayed in a dashboard format using a front-end framework such as React.js.

[0284] 6. Feedback Collection:

[0285] The server collects feedback from users, including viewing data and emotional data, and reflects this feedback in future strategy generation.

[0286] Terminal

[0287] 1. Receiving and displaying the strategy:

[0288] The terminal receives strategy data from the server and displays it to the user in a dashboard format, allowing the user to visually grasp specific advice for each platform.

[0289] 2. Collecting Emotional Data:

[0290] The device collects the user's facial expressions and voice data through a webcam and microphone and transmits it to a server in real time.

[0291] User

[0292] 1. Strategy Implementation:

[0293] Users follow the content strategy provided by the server to post content appropriate for each platform, for example, posting long videos to YouTube and short videos to TikTok.

[0294] 2. Emotion-based regulation:

[0295] Based on real-time feedback from the server, users can adjust the direction of their content. When the emotion engine recognizes the user's satisfaction, it automatically adjusts the strategy.

[0296] 3. Providing Feedback:

[0297] After posting content, users send feedback including performance data and emotional data to the server, which then acquires the data necessary for generating the next strategy.

[0298] Specific examples

[0299] For example, User B distributes videos on YouTube and TikTok. The server analyzes the viewing data obtained from User B and User B's emotional data during distribution (e.g., emotion recognition data from facial expressions and voice). Based on the analysis results, the server generates a content strategy that recommends long explanatory videos on YouTube and short, entertaining skits on TikTok. User B follows this strategy and posts long videos on YouTube and short videos on TikTok. The viewing data and emotional data after posting are then sent to the server as feedback, which the server uses to generate the next strategy.

[0300] For example, here is an example of a prompt to input to a generative AI model:

[0301] "If the average watch time of viewers on YouTube is increasing, what type of video should I post next?"

[0302] As a result, this system can provide highly accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement on each platform.

[0303] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0304] Step 1:

[0305] The server connects to the API of each digital platform (e.g., YouTube, TikTok) to collect viewing data. The server performs OAuth authentication using the API key and secret key, and sends an HTTP request to obtain viewing data (number of views, viewer attributes, viewing time, viewing completion rate, number of likes, number of comments, etc.) from the data endpoint. The input data is the API endpoint URL and authentication information, and the output is viewing data in JSON format.

[0306] Step 2:

[0307] The server converts the acquired viewing data into a unified format. Specifically, it uses the Python pandas library to convert raw data into data frame format. The input of this step is viewing data in JSON format, and the output is viewing data in a unified format (data frame format).

[0308] Step 3:

[0309] The server analyzes the converted viewing data to identify patterns and trends in viewer behavior. Specifically, it uses a scikit-learn clustering algorithm to identify viewer behavior patterns. The input to this step is viewing data in a data frame format, and the output is clustered viewer behavior patterns.

[0310] Step 4:

[0311] The device uses a webcam and microphone to collect the user's facial and voice data and transmits it to the server in real time. The input is the user's real-time facial and voice data, and the output is raw emotion data sent to the server.

[0312] Step 5:

[0313] The server analyzes the facial and voice data sent from the device to identify the user's emotions. Specifically, it uses the OpenCV library to analyze the facial data and the Google Cloud Speech-to-Text API to analyze the voice data. The input of this step is the raw emotion data sent from the device, and the output is the analyzed emotion data.

[0314] Step 6:

[0315] The server combines the analysis results of the viewing data with the emotion data to evaluate the performance of each platform. The analysis results and emotion data are integrated to calculate a performance index for each platform. The input is the clustered viewing data and the analyzed emotion data, and the output is a performance index for each platform.

[0316] Step 7:

[0317] The server uses a generative AI model to generate the optimal content strategy for each platform, for example suggesting long-form explainer videos for YouTube and short, fun skits for TikTok. The input for this step is performance metrics, and the output is the optimal content strategy for each platform.

[0318] Step 8:

[0319] The server sends the generated strategy data to the user's device, which then visually displays it. The device uses React.js to display the strategy in a dashboard format and provide specific advice to the user. The input of this step is the generated content strategy, and the output is the visual advice on the dashboard.

[0320] Step 9:

[0321] The user posts content appropriate for each platform according to the content strategy provided by the server. Specifically, the user posts long videos to YouTube and short videos to TikTok. The input of this step is the content strategy, and the output is the content posted to each platform.

[0322] Step 10:

[0323] After posting content, users collect performance and emotion data and send it to the server. The feedback data includes viewing data and user emotion data. The input of this step is performance data and emotion data, and the output is feedback data sent to the server.

[0324] Step 11:

[0325] The server analyzes the feedback data collected from users and reflects it in the next strategy generation. The feedback data is stored in a database and used for future strategy generation. The input of this step is the feedback data, and the output is the analyzed feedback information.

[0326] (Application example 2)

[0327] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0328] Content distribution on modern digital platforms requires analyzing user viewing data and generating optimal content strategies for each platform. However, current systems rely on analyzing viewing data and lack the ability to generate strategies that take into account the user's emotional state. This makes it difficult to provide individually optimized strategies that reflect user feedback and emotional changes in real time.

[0329] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting viewing data, means for analyzing the collected viewing data and evaluating performance for each platform, means including an emotion engine for collecting and analyzing user emotion data, means for generating an optimal content strategy for each platform based on the analysis results and the emotion data, means for notifying users of the generated content strategy, and means for collecting feedback from users and reflecting it in future strategy generation. As a result, by combining and analyzing viewing data and user emotion data, it is possible to generate an individually optimal content strategy in real time and maximize user engagement.

[0330] "Viewing data" refers to information such as the number of viewers of content on digital platforms, viewing time, completion rate, number of likes and comments, etc.

[0331] An "emotion engine" refers to a system that analyzes a user's facial expressions and voice data to identify the user's emotional state in real time.

[0332] "Server" refers to the core processing system that collects and analyzes viewing and sentiment data to generate and inform optimal content strategies for each platform.

[0333] "Platform performance" is a metric that shows how successful content is on each digital platform and encompasses multiple factors such as number of views, viewing time, and engagement rate.

[0334] "Content strategy" refers to a plan that uses viewing and sentiment data to suggest the most appropriate type of content and posting timing for each platform.

[0335] "Feedback" refers to information provided by users, including their reactions and impressions after viewing content, viewing data, and emotional data.

[0336] The present invention provides a system that combines an emotion engine that collects and analyzes viewing data and recognizes the user's emotions. Specific embodiments of this system will be described below.

[0337] System configuration

[0338] server

[0339] The server includes the following means:

[0340] 1. Collection of viewing data:

[0341] The server retrieves viewing data from the API endpoints of each digital platform (e.g., video platform), including the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[0342] 2. Data Analysis:

[0343] The raw data is then converted into a unified format and analyzed to identify patterns and trends in viewer behavior using statistical methods and machine learning algorithms.

[0344] 3. Emotion Recognition with Emotion Engine:

[0345] The server uses an emotion engine to analyze facial and voice data from the user's device to identify the user's emotions, for example, using emotion recognition models built with TensorFlow and Keras.

[0346] 4. Performance evaluation and strategy generation:

[0347] We evaluate the performance of each platform based on the results of viewing data analysis and user sentiment data, and then generate the optimal content strategy for each platform based on the evaluation results.

[0348] 5. Strategic Notification:

[0349] The server sends the generated strategies to the user's terminal via the Internet, where they are visually displayed in a user-friendly dashboard format.

[0350] 6. Feedback Collection:

[0351] Feedback data from users is collected and reflected in future strategy generation. Since the feedback includes emotional data, the data collected by the emotion engine is also taken into account.

[0352] Terminal

[0353] The terminal includes the following means:

[0354] 1. Receiving and displaying the strategy:

[0355] The device receives the content strategy sent from the server and provides specific advice in the form of a dashboard.

[0356] 2. Collecting Emotional Data:

[0357] The smartphone's camera and microphone are used to collect the user's facial expressions and voice data, which are then sent to a server, allowing the user's emotions to be identified in real time.

[0358] User

[0359] The user includes the following means:

[0360] 1. Strategy Implementation:

[0361] Users post content to each platform based on the content strategy provided by the server. For example, users can post long videos to YouTube and short videos to TikTok to increase viewer engagement.

[0362] 2. Emotion-based regulation:

[0363] It adjusts content direction based on real-time feedback from the server. For example, if the emotion engine detects that the user is dissatisfied, it automatically adjusts its strategy.

[0364] 3. Providing Feedback:

[0365] The results after posting content are collected and feedback, including emotional data, is sent to the server, which then obtains the data necessary for future strategy generation.

[0366] Specific examples

[0367] The following is a specific example:

[0368] Example of viewing data obtained from the platform: "Average viewing time 320 seconds, 15,000 views, 120 comments"

[0369] Example of user sentiment analysis result: "Emotion 'happy', probability 0.85"

[0370] Example prompt for a generative AI model: "Generate the optimal content strategy based on viewing data and sentiment data. Viewing data: average viewing time 320 seconds, 15,000 views, 120 comments. Sentiment data: sentiment 'happy', probability 0.85."

[0371] In this way, the system can provide more accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement across platforms.

[0372] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0373] Step 1:

[0374] Collecting viewing data

[0375] The server collects viewing data from each digital platform. Specifically, it accesses API endpoints such as YouTube and TikTok to obtain data such as the number of views, viewer attributes, viewing time, viewing completion rate, number of likes and comments, etc. The server receives raw data from the platforms as viewing data as input and outputs it as a data list.

[0376] Step 2:

[0377] Data analysis

[0378] The server converts the collected viewing data into a unified format and analyzes it. It uses statistical methods and machine learning algorithms to identify viewer behavior patterns and trends. Specifically, it calculates indicators such as viewing time distribution and engagement rate, and generates the analysis results as output.

[0379] Step 3:

[0380] Collecting Emotional Data

[0381] The device uses the smartphone's camera and microphone to collect the user's facial and voice data and transmits that data to a server. Specifically, when the user uses the app, the camera and microphone are activated, capturing facial and voice data in real time and transmitting it to the server. In this process, raw data obtained from the camera and microphone is input and output as emotion data.

[0382] Step 4:

[0383] Emotion Analysis

[0384] The server analyzes the received facial and voice data to identify the user's emotions. This analysis uses an emotion recognition model built with TensorFlow or Keras, for example. Specifically, image processing technology is used to extract facial features and classify emotions based on those features. This outputs emotion labels and their probabilities as analysis results.

[0385] Step 5:

[0386] Performance Evaluation and Strategy Generation

[0387] The server evaluates the performance of each platform based on the analysis of viewing data and emotional data, and generates an optimal content strategy. Specifically, it evaluates the viewing data and user emotional state for each platform, and generates the most efficient content strategy from the evaluation results using an AI model. The generated content strategy is then output.

[0388] Step 6:

[0389] Strategic Notification

[0390] The server notifies the user of the generated content strategy. Specifically, the strategy data is sent via the Internet and visualized in a dashboard format on the user's device. This notification allows the user to easily understand the strategy.

[0391] Step 7:

[0392] Implementing strategies and gathering feedback

[0393] Users post content to each platform based on the content strategy provided by the server. After posting, users provide feedback to the server, including viewing data and emotional data. Specifically, the number of views and comments on the posted video, as well as the user's own emotional state, are sent as input to the server, which then reflects this in future strategy generation.

[0394] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0395] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0396] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0397] [Second embodiment]

[0398] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0399] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0400] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0401] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0402] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0403] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0404] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0405] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0406] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0407] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0408] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0409] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0410] This invention provides a system that collects and analyzes viewing data, generates an optimal content strategy, and notifies users, thereby enabling users to effectively acquire viewers on each platform. Specific embodiments of this system are described below.

[0411] System configuration

[0412] server

[0413] 1. Collection of viewing data:

[0414] The server collects viewing data from each platform (e.g., YouTube, TikTok, Instagram) by sending API requests to obtain data including the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[0415] 2. Data Analysis:

[0416] The collected viewing data is converted into a unified format and analyzed to identify patterns and trends in viewer behavior, using statistical methods and machine learning models.

[0417] 3. Performance Evaluation:

[0418] Evaluate the performance of each piece of content (number of views and engagement rates) to identify which content is effective on which platforms.

[0419] 4. Generate a content strategy:

[0420] Based on the analysis results, the system generates the optimal content strategy for each platform, providing advice tailored to the characteristics of each platform, such as recommending long videos for YouTube and short videos for TikTok.

[0421] Terminal

[0422] 1. Receiving and displaying the strategy:

[0423] The user's device receives the strategy data generated by the server and visually displays it, providing specific advice for each platform in a user-friendly dashboard format.

[0424] 2. Gathering Feedback:

[0425] Provide an interface for collecting feedback from users, including performance data and satisfaction after implementing the strategy.

[0426] User

[0427] 1. Strategy Implementation:

[0428] Users post content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explainer video for YouTube, users create and post the video accordingly.

[0429] 2. Providing Feedback:

[0430] The results of the strategy execution are entered into the interface and sent to the server, which then obtains data to use in future strategy generation.

[0431] Specific examples

[0432] For example, User A distributes videos on YouTube and TikTok. The server analyzes data from YouTube that shows that long explanatory videos are popular, and determines that short, impactful skits are preferred on TikTok. Following the strategy generated by the server, User A posts long, specialized explanatory videos on YouTube and short, entertaining skits on TikTok. After posting, User A collects viewing data for each piece of content and provides feedback to the server via their device.

[0433] In this way, users can implement effective content strategies across each platform and optimize audience acquisition.

[0434] The processing flow will be explained below.

[0435] Step 1:

[0436] The server sends a request to the API endpoint of each platform (YouTube, TikTok, Instagram, etc.) to obtain viewing data, including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0437] Step 2:

[0438] The server converts the raw data it acquires into a unified format, which is done to streamline the subsequent analysis process.

[0439] Step 3:

[0440] The server uses statistical methods and machine learning algorithms to analyze the aggregated viewing data, with the goal of identifying patterns and trends in viewer behavior.

[0441] Step 4:

[0442] The server evaluates the performance of each platform based on the analysis results, including the number of views, engagement rate, and viewing time.

[0443] Step 5:

[0444] The server generates the optimal content strategy for each platform, making suggestions based on the characteristics of each platform, such as recommending long videos for YouTube and short videos for TikTok.

[0445] Step 6:

[0446] The server generates a content strategy that is delivered to the user's device, displayed in a user-friendly dashboard format and includes specific advice for each platform.

[0447] Step 7:

[0448] The device visually displays the content strategy notified by the server to the user, who then uses the displayed strategy to create a content plan and decide what to post on each platform.

[0449] Step 8:

[0450] Users post content to each platform through their devices according to the content strategy proposed by the server, for example, posting long-form expert instructional videos to YouTube and short, funny skits to TikTok.

[0451] Step 9:

[0452] The results of the strategies implemented by the user are collected and entered into the device, including viewing data after content is posted, engagement rates, and user satisfaction.

[0453] Step 10:

[0454] The device sends the feedback data collected from the user to the server, which can then use this feedback to improve future content strategies and provide more effective advice.

[0455] This specific process flow allows users to effectively acquire viewers across platforms and achieve consistent content delivery.

[0456] Example 1

[0457] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0458] Conventional content strategy generation systems require a lot of manual work to collect and analyze viewing data, making them inefficient. Furthermore, generating effective content strategies for different digital platforms requires advanced expertise, making them difficult for average users to use. Furthermore, there is a lack of a mechanism for continuously evaluating the effectiveness of the generated strategies and reflecting this in the next strategy generation, making it difficult to adapt to viewer needs.

[0459] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0460] In this invention, the server includes means for collecting viewing data, means for converting the collected viewing data into a unified format and performing data cleansing, means for analyzing the viewing data after data cleansing and identifying viewer behavior patterns and trends, means for evaluating the performance of each platform based on the analysis results, means for generating an optimal content strategy for each platform using a generative AI model, means for notifying users of the generated content strategy in a user-friendly dashboard format, and means for collecting feedback from users and reflecting it in future strategy generation. This makes it possible to implement a series of automated processes from viewing data collection to analysis, strategy generation, and feedback collection, thereby enabling effective content strategies to be provided quickly and efficiently.

[0461] "Viewing data" refers to data that indicates the viewing status of videos and content on each digital platform, and includes the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc.

[0462] "Data cleansing" is the process of removing inaccurate information, duplicate information, and missing values ​​from collected viewing data and preparing it in an analyzable format.

[0463] "Behavioral patterns" refer to specific actions or tendencies that viewers exhibit on digital platforms, and are characteristics identified through analysis of factors such as length of viewing time and reactions to specific content.

[0464] A "trend" refers to an increasing audience interest or concern over a specific period of time, including a spike or decline in interest in a particular topic or genre.

[0465] "Performance" is an indicator of how well content is received by viewers and how much engagement it generates, and is an evaluation calculated based on the number of views and engagement rate (number of likes, number of comments, etc.).

[0466] "Generative AI model" is a general term for artificial intelligence models that generate natural language based on data and output analytical results, and are used to generate content strategies.

[0467] A "dashboard" is an interface that displays data and strategies in a visually easy-to-understand format for users, and includes strategies and analysis results for each platform.

[0468] "Feedback" refers to data that a user inputs, such as the results, impressions, and improvements of the content strategy they have implemented, and sends to the server, and is reflected in future strategy generation.

[0469] This invention provides a system that collects and analyzes viewing data, generates an optimal content strategy, and notifies users, thereby enabling users to effectively acquire viewers on each platform. Specific embodiments of this system are described below.

[0470] System configuration

[0471] server

[0472] The server uses a high-performance server computer and multiple pieces of software to collect viewing data, analyze it, evaluate performance, and generate content strategies. Specifically, it uses programming languages ​​such as Python and Node.js to send API requests to the YouTube Data API, TikTok API, and Instagram Graph API to obtain information such as the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[0473] The server that collects the viewing data first uses "pandas" to convert the data into a unified format. During the data cleansing process, missing values ​​are filled in and unnecessary data is removed. The cleansed data is then analyzed using statistical methods and machine learning models (e.g., scikit-learn, TensorFlow). This analysis identifies viewer behavior patterns and trends, and the results are visualized using Matplotlib.

[0474] Next, the performance of each piece of content is evaluated based on the number of views and engagement rate, and changes are compared with past data to create a report. This report is visually presented using a data visualization tool (e.g., Tableau).

[0475] Based on the analysis results, a generative AI model (e.g., GPT-3) is used to generate an optimal content strategy for each platform. The generated strategy is converted into JSON format and sent to the user's device.

[0476] Terminal

[0477] The user's device (PC or smartphone) receives the generated content from the server via an HTTP request. The received data is displayed in a user-friendly dashboard format. The software used here is a front-end framework such as React or Vue.js. This makes it easier to understand the strategy through a visual interface.

[0478] The terminal also provides an interface where users can enter feedback. After the user enters the feedback and presses the submit button, the data is sent to the server via the terminal. The terminal sends the form data as a POST request to a specific API endpoint on the server.

[0479] User

[0480] Users post new content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explanatory video on YouTube, the user creates a video along those lines and posts it. They check performance data on the management screen or app of each platform, enter that data into a dedicated form, and send feedback to the server. This allows the server to use the feedback information to generate future strategies.

[0481] Specific examples

[0482] For example, User A distributes videos on YouTube and TikTok. The server collects viewing data and uses the YouTube Data API and TikTok API to obtain data such as the number of views, viewing time, and viewer attributes from each platform. The server then cleanses the data using "pandas" and analyzes behavioral patterns using "scikit-learn." Based on the analysis results, GPT-3 determines that long-form explanatory videos are effective on YouTube and short skits on TikTok, and generates a new content strategy. This strategy is sent to User A's device in JSON format and displayed visually on a dashboard. User A creates and posts content according to the strategy and sends feedback to the server via their device, which will be used to generate the next strategy.

[0483] Prompt Sentence Examples

[0484] Generate an optimal content strategy for User A, who distributes videos on YouTube and TikTok. Please propose a specific strategy based on the analysis results of what types of videos are popular on YouTube and what types of content are preferred on TikTok. Furthermore, please tell us the expected results and performance indicators that should be measured after implementing the strategy.

[0485] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0486] Step 1: The server collects viewing data from each digital platform. Specifically, the server uses the YouTube Data API, TikTok API, and Instagram Graph API to obtain data such as the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc. using the Python library "requests." This data is received in JSON format and stored in a database (e.g., MySQL or MongoDB). The input is the response data from the API request, and the output is the viewing data stored in the database.

[0487] Step 2: The server converts the collected viewing data into a unified format and performs data cleansing. Python's "pandas" is used to fill in missing values ​​and delete unnecessary data. The input is viewing data in JSON format, and the output is cleansed data in CSV or JSON format. Specific operations include filling in missing values, deleting duplicate data, and standardizing the format.

[0488] Step 3: The server analyzes the cleansed viewing data to identify viewer behavior patterns and trends. Using the Python machine learning libraries "scikit-learn" and "TensorFlow," it builds a model to identify viewer behavior patterns from the data. The input is the cleansed viewing data, and the output is the analysis results on viewer behavior patterns and trends. Specific operations include extracting features from the data, training the model, and making inferences.

[0489] Step 4: The server evaluates the performance of each platform. It scores the performance of each piece of content based on factors such as the number of views, engagement rate, and number of comments, and compiles the evaluation results into a report. This process uses data visualization tools (e.g., Matplotlib, Tableau). The input is the analysis results, and the output is a performance evaluation report. Specific operations include calculating evaluation indicators, comparing them with past data, and generating graphs.

[0490] Step 5: The server uses a generative AI model (e.g., GPT-3) to generate an optimal content strategy and converts it into JSON format. It inputs a prompt to the AI ​​model and receives a response from the API with the generated strategy. The input is the prompt and the analysis result, and the output is the generated content strategy. Specific operations include setting the prompt, making a request to the AI ​​model, and analyzing the response.

[0491] Step 6: The terminal receives the content strategy generated from the server and displays it in a user-friendly dashboard format. It uses a front-end framework (e.g., React, Vue.js) to visually organize the received data and provide it to the user. The input is the strategy data in JSON format from the server, and the output is a visual display on the dashboard. Specific operations include parsing the data and generating graphs and lists.

[0492] Step 7: The user posts content to each platform based on the generated content strategy. For example, if you want to upload a long-form explainer video to YouTube, you shoot the video, edit it, and then upload it to YouTube. The input is the content strategy, and the output is the posted content. The specific actions are creating, editing, and uploading the video.

[0493] Step 8: The user enters the results after the strategy is implemented into a dedicated form and sends feedback from the terminal to the server. The form data is sent to the server's API endpoint as a POST request. The input is the performance data after the strategy is implemented, and the output is the feedback sent to the server. Specific actions include entering data, clicking the submit button, and transferring the data to the server.

[0494] Step 9: The server collects feedback from users and reflects it in future strategy generation. The collected feedback is stored in a database and used for the next data analysis and strategy generation. The input is feedback data from users, and the output is data reflected in the next analysis and strategy generation. Specific operations include storing the feedback in the database and integrating it into the subsequent analysis process.

[0495] (Application example 1)

[0496] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0497] In recent years, a variety of digital platforms have emerged, and content creators need to effectively reach viewers with different characteristics on each platform. However, doing so requires time and expertise to collect and analyze vast amounts of viewing data and generate optimal content strategies. Furthermore, a system that efficiently reflects user feedback and continuously optimizes content is also important. It is desirable to provide a system that can solve these challenges and enable users to effectively acquire viewers on each platform.

[0498] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0499] In this invention, the server includes means for collecting viewing data, means for analyzing the collected viewing data and evaluating performance for each platform, means for generating an optimal content strategy for each platform based on the analysis results, means for notifying users of the generated content strategy, means for collecting feedback from users and reflecting it in generating future strategies, means for providing a user interface optimized for smartphones and displaying visual advice, and means for updating and continuously optimizing a machine learning model based on the feedback data. This enables users to efficiently analyze viewing data, implement an optimal content strategy for each platform, and effectively acquire viewers.

[0500] "Viewing data" refers to information about when a user views content on a digital platform, including the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc.

[0501] A "platform" is a digital service that distributes content and allows viewers to access it, such as YouTube, TikTok, or Instagram.

[0502] "Performance" is the result of evaluating viewer response and engagement with content, taking into account indicators such as number of views, viewing time, number of likes and comments.

[0503] A "content strategy" is a policy for determining the format and content of content to effectively attract viewers on each platform, and includes recommendations such as long-form videos and short skits.

[0504] "User" refers to an individual or entity that utilizes the system provided in accordance with this invention to distribute content or execute strategies.

[0505] "Feedback" refers to information provided by users about the results and satisfaction after strategy implementation, which is used to improve future strategy generation.

[0506] A "machine learning model" is a collection of algorithms for analysis and prediction using viewing data and feedback data, and improves accuracy by continuously learning from the data.

[0507] The "user interface" refers to the interface that allows users to operate the system and visually check the generated content strategy, and is optimized for smartphones.

[0508] This invention is a system that collects and analyzes viewing data and provides users with optimal content strategies. This system is composed of a server, a terminal, and a user.

[0509] server

[0510] The server has the following features:

[0511] 1. Collecting viewing data

[0512] It collects viewing data from each digital platform, specifically using the platform's API to obtain data such as the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0513] 2. Data Analysis

[0514] The collected viewing data is converted into a unified format and analyzed using statistical methods and machine learning models to process the data and identify patterns and trends in viewer behavior.

[0515] 3. Performance Evaluation

[0516] Evaluate the performance of each piece of content (number of views and engagement rates) to identify which content is effective on which platforms.

[0517] 4. Generate a content strategy

[0518] Based on the analysis, it generates the optimal content strategy for each platform, for example recommending long-form videos for YouTube and short-form videos for TikTok based on viewing patterns.

[0519] 5. Gathering feedback and updating the machine learning model

[0520] It collects user feedback data and uses it to update the machine learning model, thereby continuously optimizing the system.

[0521] Terminal

[0522] The terminal has the following features:

[0523] 1. Receiving and displaying the strategy

[0524] The server receives the generated content strategy and visually displays it to the user in a user-friendly dashboard format that is optimized for smartphones.

[0525] 2. Gathering feedback

[0526] Provide an interface for collecting feedback from users, including performance data and satisfaction after implementing the strategy.

[0527] User

[0528] The user has the following capabilities:

[0529] 1. Strategy Implementation

[0530] Users post content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explainer video for YouTube, the user creates and posts the video accordingly.

[0531] 2. Providing Feedback

[0532] The results of the strategy execution are entered into the terminal interface and sent to the server, which collects the data necessary for future strategy generation.

[0533] Specific examples

[0534] For example, consider the case where User A distributes videos on YouTube and TikTok. The server analyzes YouTube viewing data and determines that long explanatory videos are popular, while short, impactful skits are preferred on TikTok. Following the strategy generated by the server, User A posts long, specialized explanatory videos on YouTube and short, entertaining skits on TikTok. After posting, User A collects viewing data for each piece of content and provides feedback to the server via their device. This allows the system to reflect this in future strategies.

[0535] Prompt Sentence Examples

[0536] Create a Python script that allows users to collect viewing data from YouTube, TikTok, and Instagram, and generate optimal content strategies based on data analysis.

[0537] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0538] Step 1:

[0539] The server collects viewing data.

[0540] Input: Viewing data requests from the API of each platform (e.g. YouTube, TikTok, Instagram).

[0541] Specific operation: The server uses the API of each digital platform to collect viewing data such as the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc. It sends requests using the API authentication key and receives data from each platform.

[0542] Output: JSON format response of the retrieved viewing data.

[0543] Step 2:

[0544] The server analyzes the collected viewing data.

[0545] Input: Viewing data obtained in step 1.

[0546] What it does: The server converts the viewing data into a unified format and analyzes it using machine learning models to identify patterns and trends in viewer behavior. It converts the data into TF-IDF vectors and classifies the viewing data using KMeans clustering.

[0547] Output: Viewing data patterns and trend information for each cluster.

[0548] Step 3:

[0549] The server evaluates the performance.

[0550] Input: Analysis results from step 2.

[0551] Specific operation: The server evaluates the performance of viewing data (number of views, engagement rate, etc.) for each platform and identifies which content is effective. Specifically, it analyzes the distribution of viewing numbers and engagement rates for each cluster and determines the optimal content format for each platform.

[0552] Output: Performance evaluation results for each platform.

[0553] Step 4:

[0554] The server generates the content strategy.

[0555] Input: Performance evaluation results from step 3.

[0556] What it does: Based on the analysis results, it generates the optimal content strategy for each platform, for example, recommending long videos for YouTube and short videos for TikTok based on viewing patterns.

[0557] Output: Optimal content strategies for each generated platform.

[0558] Step 5:

[0559] The terminal receives the strategy and notifies the user.

[0560] Input: The content strategy generated in step 4.

[0561] Specific operation: The device receives content strategy data from the server and visually displays it to the user. The strategy content is provided in dashboard format through a smartphone-oriented user interface.

[0562] Output: A visual content strategy interface for the user.

[0563] Step 6:

[0564] Users post content based on a strategy.

[0565] Input: Content strategy provided in step 5.

[0566] Specific behavior: Users follow the provided strategy to create and post content in a format appropriate for each platform, for example, posting a long-form explainer video on YouTube and a short skit on TikTok.

[0567] Output: Content posted to each platform.

[0568] Step 7:

[0569] The device collects the feedback and sends it to the server.

[0570] Input: Outcome data and satisfaction level provided by users after strategy implementation.

[0571] Specific operations: The results after the strategy is executed (number of views, engagement rate, etc.) are entered into the user interface and sent to the server.

[0572] Output: Feedback data.

[0573] Step 8:

[0574] The server updates the machine learning model based on the feedback data.

[0575] Input: Feedback data collected in step 7.

[0576] What it does: The server analyzes the feedback data and updates the machine learning model, allowing the system to generate more accurate content strategies in future.

[0577] Output: An updated machine learning model.

[0578] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0579] This invention is a system that combines a system that collects and analyzes viewing data and generates optimal content strategies for each platform with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0580] System configuration

[0581] server

[0582] 1. Collection of viewing data:

[0583] The server retrieves viewing data from the API endpoints of each digital platform (e.g., YouTube, TikTok, etc.), including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0584] 2. Data Analysis:

[0585] The raw data is then converted into a unified format and analyzed to identify patterns and trends in viewer behavior using statistical methods and machine learning algorithms.

[0586] 3. Emotion Recognition with Emotion Engine:

[0587] The server uses an emotion engine to analyze facial and voice data from the user's device to identify the user's emotions, for example, using data from a webcam or microphone.

[0588] 4. Performance evaluation and strategy generation:

[0589] We evaluate the performance of each platform based on the results of viewing data analysis and user sentiment data, and then generate the optimal content strategy for each platform based on the evaluation results.

[0590] 5. Strategic Notification:

[0591] The server generates strategy data and sends it to the user's device, where specific advice for each platform is displayed in a user-friendly dashboard format.

[0592] 6. Feedback Collection:

[0593] Feedback data from users is collected and reflected in future strategy generation. Since the feedback includes emotional data, the data collected by the emotion engine is also taken into account.

[0594] Terminal

[0595] 1. Receiving and displaying the strategy:

[0596] The terminal receives strategic data from the server and visually displays it, providing specific advice to the user in the form of a dashboard.

[0597] 2. Collecting Emotional Data:

[0598] The user's facial expressions and voice data are collected through a webcam and microphone and sent to a server, which then identifies the user's emotions in real time.

[0599] User

[0600] 1. Strategy Implementation:

[0601] Users post content to each platform according to the content strategy from the server. Based on data, for example, users can post long videos to YouTube and short videos to TikTok to increase viewer engagement.

[0602] 2. Emotion-based regulation:

[0603] It adjusts content direction based on real-time feedback from the server. For example, if the emotion engine detects that the user is dissatisfied, it automatically adjusts its strategy.

[0604] 3. Providing Feedback:

[0605] The results after posting content are collected and feedback, including emotional data, is sent to the server, which then obtains the data necessary for future strategy generation.

[0606] Specific examples

[0607] For example, User B distributes videos on YouTube and TikTok. The server analyzes the viewing data obtained from User B and User B's emotional data during the distribution (e.g., emotion recognition data from facial expressions and voice). Based on this data, the server generates a content strategy that recommends "long explanatory videos" on YouTube and "short, fun skits" on TikTok. User B then posts a long video on YouTube and a short video on TikTok. The viewing data and emotional data after posting are then sent to the server as feedback, which the server uses to generate the next strategy.

[0608] In this way, the system can provide more accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement across platforms.

[0609] The processing flow will be explained below.

[0610] Step 1:

[0611] The server sends requests to the API endpoints of each digital platform (YouTube, TikTok, Instagram, etc.) to obtain viewing data, including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0612] Step 2:

[0613] The server converts the raw data it acquires into a unified format to eliminate differences between platforms and facilitate subsequent analysis.

[0614] Step 3:

[0615] The server analyzes the aggregated viewing data, using statistical methods and machine learning algorithms to identify patterns and trends in viewer behavior.

[0616] Step 4:

[0617] The server evaluates the performance of each platform based on the analysis results, including the number of views, engagement rate, and viewing time, and analyzes how each indicator contributes.

[0618] Step 5:

[0619] The server uses an emotion engine to analyze facial expressions and voice data collected from the user's device, and identifies the user's emotional state through the analysis.

[0620] Step 6:

[0621] The server combines the results of the viewing data analysis with user sentiment data to generate the optimal content strategy for each platform. For example, YouTube recommends long videos, while TikTok recommends short videos.

[0622] Step 7:

[0623] The server sends the generated content strategy to the user's device, where a notification is displayed, allowing the user to confirm specific actions based on the strategy.

[0624] Step 8:

[0625] The device receives notifications from the server and visually displays strategies to the user, providing specific advice for each platform in the form of a dashboard.

[0626] Step 9:

[0627] Users post content to each platform based on a content strategy suggested by the server, for example, posting a long-form explainer video to YouTube and a short, fun skit to TikTok.

[0628] Step 10:

[0629] The device collects the user's facial expressions and voice data in real time, analyzes it through an emotion engine, and sends it to a server, allowing changes in the user's emotions to be grasped in real time.

[0630] Step 11:

[0631] The user evaluates the results of the content strategy and their emotional state, and then inputs the feedback into the terminal. The feedback includes viewing data and emotional data.

[0632] Step 12:

[0633] The device collects feedback data from users and sends it to the server, which uses this feedback to improve the strategy generation process and provide more accurate advice in the future.

[0634] Through this specific process, the system can provide content strategies that take into account the user's emotional state and effectively acquire audiences on each platform.

[0635] Example 2

[0636] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0637] Conventional content strategy generation systems were able to generate strategies based on the analysis of viewing data, but were unable to generate strategies that took into account viewer emotions. As a result, strategies that did not reflect viewer reactions or emotions resulted in the provision of less than optimal content. Furthermore, strategies that took into account the characteristics of each platform across multiple digital platforms were not sufficiently generated.

[0638] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting viewing data, a means for converting the collected viewing data into a unified format and analyzing it, a means for collecting user facial expression and voice data and recognizing emotions, a means for generating an optimal content strategy for each platform based on the analysis results and emotion data, a means for notifying the user of the generated content strategy on the user's terminal and visually displaying it, and a means for collecting feedback data from the user and reflecting it in future strategy generation. This makes it possible to generate a more accurate content strategy that takes into account not only viewing data but also viewer emotions. It is also possible to provide a strategy that takes into account the characteristics of each platform.

[0639] "Viewing data" refers to data including the number of views on digital platforms, viewing time, viewing completion rate, viewer attributes, number of likes and comments, etc.

[0640] The "unified format" is a data format that converts viewing data collected from multiple digital platforms into a format that is easy to analyze.

[0641] "Facial expression data" refers to data relating to the facial expressions of a user captured through a webcam.

[0642] "Voice data" refers to data relating to the user's speech or voice acquired through a microphone.

[0643] "Emotion recognition" means analyzing facial expression data and voice data to identify the user's emotional state (for example, joy, sadness, surprise, etc.).

[0644] The "analysis results" are analysis results based on viewing data and emotional data, and indicate the behavioral patterns and emotional tendencies of viewers.

[0645] "Content strategy" refers to the type, content, timing, etc. of content posted on digital platforms.

[0646] A "user terminal" is a device (e.g., a PC, a smartphone, a tablet, etc.) that visually displays strategic data and collects feedback from users.

[0647] "Feedback data" refers to data provided by users that includes opinions, results, and sentiment data regarding content strategies.

[0648] This invention is a system that collects and analyzes viewing data to generate optimal content strategies for each platform. Furthermore, by combining it with an emotion engine that recognizes user emotions, it provides a more accurate content strategy.

[0649] server

[0650] 1. Collection of viewing data:

[0651] The server obtains viewing data from digital platforms such as YouTube and TikTok through APIs, using OAuth for authentication, and collects data such as the number of views, viewer attributes, viewing time, completion rate, likes, and comments.

[0652] 2. Data Analysis:

[0653] The server uses Python's pandas library to convert the collected viewing data into a unified format, then analyzes the data using machine learning algorithms such as scikit-learn to identify patterns in viewer behavior.

[0654] 3. Emotion Recognition with Emotion Engine:

[0655] The server collects facial and voice data from the user's device in real time and recognizes emotions. It uses the OpenCV library to analyze facial data and the Google Cloud Speech-to-Text API to analyze voice data.

[0656] 4. Performance evaluation and strategy generation:

[0657] The server evaluates the performance of each platform based on viewing data analysis and sentiment data, and then uses a generative AI model to generate the optimal content strategy for each platform.

[0658] 5. Strategic Notification:

[0659] The server sends the generated strategy to the user's device, where it is visually displayed in a dashboard format using a front-end framework such as React.js.

[0660] 6. Feedback Collection:

[0661] The server collects feedback from users, including viewing data and emotional data, and reflects this feedback in future strategy generation.

[0662] Terminal

[0663] 1. Receiving and displaying the strategy:

[0664] The terminal receives strategy data from the server and displays it to the user in a dashboard format, allowing the user to visually grasp specific advice for each platform.

[0665] 2. Collecting Emotional Data:

[0666] The device collects the user's facial expressions and voice data through a webcam and microphone and transmits it to a server in real time.

[0667] User

[0668] 1. Strategy Implementation:

[0669] Users follow the content strategy provided by the server to post content appropriate for each platform, for example, posting long videos to YouTube and short videos to TikTok.

[0670] 2. Emotion-based regulation:

[0671] Based on real-time feedback from the server, users can adjust the direction of their content. When the emotion engine recognizes the user's satisfaction, it automatically adjusts the strategy.

[0672] 3. Providing Feedback:

[0673] After posting content, users send feedback including performance data and emotional data to the server, which then acquires the data necessary for generating the next strategy.

[0674] Specific examples

[0675] For example, User B distributes videos on YouTube and TikTok. The server analyzes the viewing data obtained from User B and User B's emotional data during distribution (e.g., emotion recognition data from facial expressions and voice). Based on the analysis results, the server generates a content strategy that recommends long explanatory videos on YouTube and short, entertaining skits on TikTok. User B follows this strategy and posts long videos on YouTube and short videos on TikTok. The viewing data and emotional data after posting are then sent to the server as feedback, which the server uses to generate the next strategy.

[0676] For example, here is an example of a prompt to input to a generative AI model:

[0677] "If the average watch time of viewers on YouTube is increasing, what type of video should I post next?"

[0678] As a result, this system can provide highly accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement on each platform.

[0679] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0680] Step 1:

[0681] The server connects to the API of each digital platform (e.g., YouTube, TikTok) to collect viewing data. The server performs OAuth authentication using the API key and secret key, and sends an HTTP request to obtain viewing data (number of views, viewer attributes, viewing time, viewing completion rate, number of likes, number of comments, etc.) from the data endpoint. The input data is the API endpoint URL and authentication information, and the output is viewing data in JSON format.

[0682] Step 2:

[0683] The server converts the acquired viewing data into a unified format. Specifically, it uses the Python pandas library to convert raw data into data frame format. The input of this step is viewing data in JSON format, and the output is viewing data in a unified format (data frame format).

[0684] Step 3:

[0685] The server analyzes the converted viewing data to identify patterns and trends in viewer behavior. Specifically, it uses a scikit-learn clustering algorithm to identify viewer behavior patterns. The input to this step is viewing data in a data frame format, and the output is clustered viewer behavior patterns.

[0686] Step 4:

[0687] The device uses a webcam and microphone to collect the user's facial and voice data and transmits it to the server in real time. The input is the user's real-time facial and voice data, and the output is raw emotion data sent to the server.

[0688] Step 5:

[0689] The server analyzes the facial and voice data sent from the device to identify the user's emotions. Specifically, it uses the OpenCV library to analyze the facial data and the Google Cloud Speech-to-Text API to analyze the voice data. The input of this step is the raw emotion data sent from the device, and the output is the analyzed emotion data.

[0690] Step 6:

[0691] The server combines the analysis results of the viewing data with the emotion data to evaluate the performance of each platform. The analysis results and emotion data are integrated to calculate a performance index for each platform. The input is the clustered viewing data and the analyzed emotion data, and the output is a performance index for each platform.

[0692] Step 7:

[0693] The server uses a generative AI model to generate the optimal content strategy for each platform, for example suggesting long-form explainer videos for YouTube and short, fun skits for TikTok. The input for this step is performance metrics, and the output is the optimal content strategy for each platform.

[0694] Step 8:

[0695] The server sends the generated strategy data to the user's device, which then visually displays it. The device uses React.js to display the strategy in a dashboard format and provide specific advice to the user. The input of this step is the generated content strategy, and the output is the visual advice on the dashboard.

[0696] Step 9:

[0697] The user posts content appropriate for each platform according to the content strategy provided by the server. Specifically, the user posts long videos to YouTube and short videos to TikTok. The input of this step is the content strategy, and the output is the content posted to each platform.

[0698] Step 10:

[0699] After posting content, users collect performance and emotion data and send it to the server. The feedback data includes viewing data and user emotion data. The input of this step is performance data and emotion data, and the output is feedback data sent to the server.

[0700] Step 11:

[0701] The server analyzes the feedback data collected from users and reflects it in the next strategy generation. The feedback data is stored in a database and used for future strategy generation. The input of this step is the feedback data, and the output is the analyzed feedback information.

[0702] (Application example 2)

[0703] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0704] Content distribution on modern digital platforms requires analyzing user viewing data and generating optimal content strategies for each platform. However, current systems rely on analyzing viewing data and lack the ability to generate strategies that take into account the user's emotional state. This makes it difficult to provide individually optimized strategies that reflect user feedback and emotional changes in real time.

[0705] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting viewing data, means for analyzing the collected viewing data and evaluating performance for each platform, means including an emotion engine for collecting and analyzing user emotion data, means for generating an optimal content strategy for each platform based on the analysis results and the emotion data, means for notifying users of the generated content strategy, and means for collecting feedback from users and reflecting it in future strategy generation. As a result, by combining and analyzing viewing data and user emotion data, it is possible to generate an individually optimal content strategy in real time and maximize user engagement.

[0706] "Viewing data" refers to information such as the number of viewers of content on digital platforms, viewing time, completion rate, number of likes and comments, etc.

[0707] An "emotion engine" refers to a system that analyzes a user's facial expressions and voice data to identify the user's emotional state in real time.

[0708] "Server" refers to the core processing system that collects and analyzes viewing and sentiment data to generate and inform optimal content strategies for each platform.

[0709] "Platform performance" is a metric that shows how successful content is on each digital platform and encompasses multiple factors such as number of views, viewing time, and engagement rate.

[0710] "Content strategy" refers to a plan that uses viewing and sentiment data to suggest the most appropriate type of content and posting timing for each platform.

[0711] "Feedback" refers to information provided by users, including their reactions and impressions after viewing content, viewing data, and emotional data.

[0712] The present invention provides a system that combines an emotion engine that collects and analyzes viewing data and recognizes the user's emotions. Specific embodiments of this system will be described below.

[0713] System configuration

[0714] server

[0715] The server includes the following means:

[0716] 1. Collection of viewing data:

[0717] The server retrieves viewing data from the API endpoints of each digital platform (e.g., video platform), including the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[0718] 2. Data Analysis:

[0719] The raw data is then converted into a unified format and analyzed to identify patterns and trends in viewer behavior using statistical methods and machine learning algorithms.

[0720] 3. Emotion Recognition with Emotion Engine:

[0721] The server uses an emotion engine to analyze facial and voice data from the user's device to identify the user's emotions, for example, using emotion recognition models built with TensorFlow and Keras.

[0722] 4. Performance evaluation and strategy generation:

[0723] We evaluate the performance of each platform based on the results of viewing data analysis and user sentiment data, and then generate the optimal content strategy for each platform based on the evaluation results.

[0724] 5. Strategic Notification:

[0725] The server sends the generated strategies to the user's terminal via the Internet, where they are visually displayed in a user-friendly dashboard format.

[0726] 6. Feedback Collection:

[0727] Feedback data from users is collected and reflected in future strategy generation. Since the feedback includes emotional data, the data collected by the emotion engine is also taken into account.

[0728] Terminal

[0729] The terminal includes the following means:

[0730] 1. Receiving and displaying the strategy:

[0731] The device receives the content strategy sent from the server and provides specific advice in the form of a dashboard.

[0732] 2. Collecting Emotional Data:

[0733] The smartphone's camera and microphone are used to collect the user's facial expressions and voice data, which are then sent to a server, allowing the user's emotions to be identified in real time.

[0734] User

[0735] The user includes the following means:

[0736] 1. Strategy Implementation:

[0737] Users post content to each platform based on the content strategy provided by the server. For example, users can post long videos to YouTube and short videos to TikTok to increase viewer engagement.

[0738] 2. Emotion-based regulation:

[0739] It adjusts content direction based on real-time feedback from the server. For example, if the emotion engine detects that the user is dissatisfied, it automatically adjusts its strategy.

[0740] 3. Providing Feedback:

[0741] The results after posting content are collected and feedback, including emotional data, is sent to the server, which then obtains the data necessary for future strategy generation.

[0742] Specific examples

[0743] The following is a specific example:

[0744] Example of viewing data obtained from the platform: "Average viewing time 320 seconds, 15,000 views, 120 comments"

[0745] Example of user sentiment analysis result: "Emotion 'happy', probability 0.85"

[0746] Example prompt for a generative AI model: "Generate the optimal content strategy based on viewing data and sentiment data. Viewing data: average viewing time 320 seconds, 15,000 views, 120 comments. Sentiment data: sentiment 'happy', probability 0.85."

[0747] In this way, the system can provide more accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement across platforms.

[0748] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0749] Step 1:

[0750] Collecting viewing data

[0751] The server collects viewing data from each digital platform. Specifically, it accesses API endpoints such as YouTube and TikTok to obtain data such as the number of views, viewer attributes, viewing time, viewing completion rate, number of likes and comments, etc. The server receives raw data from the platforms as viewing data as input and outputs it as a data list.

[0752] Step 2:

[0753] Data analysis

[0754] The server converts the collected viewing data into a unified format and analyzes it. It uses statistical methods and machine learning algorithms to identify viewer behavior patterns and trends. Specifically, it calculates indicators such as viewing time distribution and engagement rate, and generates the analysis results as output.

[0755] Step 3:

[0756] Collecting Emotional Data

[0757] The device uses the smartphone's camera and microphone to collect the user's facial and voice data and transmits that data to a server. Specifically, when the user uses the app, the camera and microphone are activated, capturing facial and voice data in real time and transmitting it to the server. In this process, raw data obtained from the camera and microphone is input and output as emotion data.

[0758] Step 4:

[0759] Emotion Analysis

[0760] The server analyzes the received facial and voice data to identify the user's emotions. This analysis uses an emotion recognition model built with TensorFlow or Keras, for example. Specifically, image processing technology is used to extract facial features and classify emotions based on those features. This outputs emotion labels and their probabilities as analysis results.

[0761] Step 5:

[0762] Performance Evaluation and Strategy Generation

[0763] The server evaluates the performance of each platform based on the analysis of viewing data and emotional data, and generates an optimal content strategy. Specifically, it evaluates the viewing data and user emotional state for each platform, and generates the most efficient content strategy from the evaluation results using an AI model. The generated content strategy is then output.

[0764] Step 6:

[0765] Strategic Notification

[0766] The server notifies the user of the generated content strategy. Specifically, the strategy data is sent via the Internet and visualized in a dashboard format on the user's device. This notification allows the user to easily understand the strategy.

[0767] Step 7:

[0768] Implementing strategies and gathering feedback

[0769] Users post content to each platform based on the content strategy provided by the server. After posting, users provide feedback to the server, including viewing data and emotional data. Specifically, the number of views and comments on the posted video, as well as the user's own emotional state, are sent as input to the server, which then reflects this in future strategy generation.

[0770] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0771] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0772] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0773] [Third embodiment]

[0774] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0775] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0776] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0777] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0778] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0779] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0780] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0781] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0782] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0783] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0784] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0785] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0786] This invention provides a system that collects and analyzes viewing data, generates an optimal content strategy, and notifies users, thereby enabling users to effectively acquire viewers on each platform. Specific embodiments of this system are described below.

[0787] System configuration

[0788] server

[0789] 1. Collection of viewing data:

[0790] The server collects viewing data from each platform (e.g., YouTube, TikTok, Instagram) by sending API requests to obtain data including the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[0791] 2. Data Analysis:

[0792] The collected viewing data is converted into a unified format and analyzed to identify patterns and trends in viewer behavior, using statistical methods and machine learning models.

[0793] 3. Performance Evaluation:

[0794] Evaluate the performance of each piece of content (number of views and engagement rates) to identify which content is effective on which platforms.

[0795] 4. Generate a content strategy:

[0796] Based on the analysis results, the system generates the optimal content strategy for each platform, providing advice tailored to the characteristics of each platform, such as recommending long videos for YouTube and short videos for TikTok.

[0797] Terminal

[0798] 1. Receiving and displaying the strategy:

[0799] The user's device receives the strategy data generated by the server and visually displays it, providing specific advice for each platform in a user-friendly dashboard format.

[0800] 2. Gathering Feedback:

[0801] Provide an interface for collecting feedback from users, including performance data and satisfaction after implementing the strategy.

[0802] User

[0803] 1. Strategy Implementation:

[0804] Users post content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explainer video for YouTube, users create and post the video accordingly.

[0805] 2. Providing Feedback:

[0806] The results of the strategy execution are entered into the interface and sent to the server, which then obtains data to use in future strategy generation.

[0807] Specific examples

[0808] For example, User A distributes videos on YouTube and TikTok. The server analyzes data from YouTube that shows that long explanatory videos are popular, and determines that short, impactful skits are preferred on TikTok. Following the strategy generated by the server, User A posts long, specialized explanatory videos on YouTube and short, entertaining skits on TikTok. After posting, User A collects viewing data for each piece of content and provides feedback to the server via their device.

[0809] In this way, users can implement effective content strategies across each platform and optimize audience acquisition.

[0810] The processing flow will be explained below.

[0811] Step 1:

[0812] The server sends a request to the API endpoint of each platform (YouTube, TikTok, Instagram, etc.) to obtain viewing data, including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0813] Step 2:

[0814] The server converts the raw data it acquires into a unified format, which is done to streamline the subsequent analysis process.

[0815] Step 3:

[0816] The server uses statistical methods and machine learning algorithms to analyze the aggregated viewing data, with the goal of identifying patterns and trends in viewer behavior.

[0817] Step 4:

[0818] The server evaluates the performance of each platform based on the analysis results, including the number of views, engagement rate, and viewing time.

[0819] Step 5:

[0820] The server generates the optimal content strategy for each platform, making suggestions based on the characteristics of each platform, such as recommending long videos for YouTube and short videos for TikTok.

[0821] Step 6:

[0822] The server generates a content strategy that is delivered to the user's device, displayed in a user-friendly dashboard format and includes specific advice for each platform.

[0823] Step 7:

[0824] The device visually displays the content strategy notified by the server to the user, who then uses the displayed strategy to create a content plan and decide what to post on each platform.

[0825] Step 8:

[0826] Users post content to each platform through their devices according to the content strategy proposed by the server, for example, posting long-form expert instructional videos to YouTube and short, funny skits to TikTok.

[0827] Step 9:

[0828] The results of the strategies implemented by the user are collected and entered into the device, including viewing data after content is posted, engagement rates, and user satisfaction.

[0829] Step 10:

[0830] The device sends the feedback data collected from the user to the server, which can then use this feedback to improve future content strategies and provide more effective advice.

[0831] This specific process flow allows users to effectively acquire viewers across platforms and achieve consistent content delivery.

[0832] Example 1

[0833] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0834] Conventional content strategy generation systems require a lot of manual work to collect and analyze viewing data, making them inefficient. Furthermore, generating effective content strategies for different digital platforms requires advanced expertise, making them difficult for average users to use. Furthermore, there is a lack of a mechanism for continuously evaluating the effectiveness of the generated strategies and reflecting this in the next strategy generation, making it difficult to adapt to viewer needs.

[0835] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0836] In this invention, the server includes means for collecting viewing data, means for converting the collected viewing data into a unified format and performing data cleansing, means for analyzing the viewing data after data cleansing and identifying viewer behavior patterns and trends, means for evaluating the performance of each platform based on the analysis results, means for generating an optimal content strategy for each platform using a generative AI model, means for notifying users of the generated content strategy in a user-friendly dashboard format, and means for collecting feedback from users and reflecting it in future strategy generation. This makes it possible to implement a series of automated processes from viewing data collection to analysis, strategy generation, and feedback collection, thereby enabling effective content strategies to be provided quickly and efficiently.

[0837] "Viewing data" refers to data that indicates the viewing status of videos and content on each digital platform, and includes the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc.

[0838] "Data cleansing" is the process of removing inaccurate information, duplicate information, and missing values ​​from collected viewing data and preparing it in an analyzable format.

[0839] "Behavioral patterns" refer to specific actions or tendencies that viewers exhibit on digital platforms, and are characteristics identified through analysis of factors such as length of viewing time and reactions to specific content.

[0840] A "trend" refers to an increasing audience interest or concern over a specific period of time, including a spike or decline in interest in a particular topic or genre.

[0841] "Performance" is an indicator of how well content is received by viewers and how much engagement it generates, and is an evaluation calculated based on the number of views and engagement rate (number of likes, number of comments, etc.).

[0842] "Generative AI model" is a general term for artificial intelligence models that generate natural language based on data and output analytical results, and are used to generate content strategies.

[0843] A "dashboard" is an interface that displays data and strategies in a visually easy-to-understand format for users, and includes strategies and analysis results for each platform.

[0844] "Feedback" refers to data that a user inputs, such as the results, impressions, and improvements of the content strategy they have implemented, and sends to the server, and is reflected in future strategy generation.

[0845] This invention provides a system that collects and analyzes viewing data, generates an optimal content strategy, and notifies users, thereby enabling users to effectively acquire viewers on each platform. Specific embodiments of this system are described below.

[0846] System configuration

[0847] server

[0848] The server uses a high-performance server computer and multiple pieces of software to collect viewing data, analyze it, evaluate performance, and generate content strategies. Specifically, it uses programming languages ​​such as Python and Node.js to send API requests to the YouTube Data API, TikTok API, and Instagram Graph API to obtain information such as the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[0849] The server that collects the viewing data first uses "pandas" to convert the data into a unified format. During the data cleansing process, missing values ​​are filled in and unnecessary data is removed. The cleansed data is then analyzed using statistical methods and machine learning models (e.g., scikit-learn, TensorFlow). This analysis identifies viewer behavior patterns and trends, and the results are visualized using Matplotlib.

[0850] Next, the performance of each piece of content is evaluated based on the number of views and engagement rate, and changes are compared with past data to create a report. This report is visually presented using a data visualization tool (e.g., Tableau).

[0851] Based on the analysis results, a generative AI model (e.g., GPT-3) is used to generate an optimal content strategy for each platform. The generated strategy is converted into JSON format and sent to the user's device.

[0852] Terminal

[0853] The user's device (PC or smartphone) receives the generated content from the server via an HTTP request. The received data is displayed in a user-friendly dashboard format. The software used here is a front-end framework such as React or Vue.js. This makes it easier to understand the strategy through a visual interface.

[0854] The terminal also provides an interface where users can enter feedback. After the user enters the feedback and presses the submit button, the data is sent to the server via the terminal. The terminal sends the form data as a POST request to a specific API endpoint on the server.

[0855] User

[0856] Users post new content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explanatory video on YouTube, the user creates a video along those lines and posts it. They check performance data on the management screen or app of each platform, enter that data into a dedicated form, and send feedback to the server. This allows the server to use the feedback information to generate future strategies.

[0857] Specific examples

[0858] For example, User A distributes videos on YouTube and TikTok. The server collects viewing data and uses the YouTube Data API and TikTok API to obtain data such as the number of views, viewing time, and viewer attributes from each platform. The server then cleanses the data using "pandas" and analyzes behavioral patterns using "scikit-learn." Based on the analysis results, GPT-3 determines that long-form explanatory videos are effective on YouTube and short skits on TikTok, and generates a new content strategy. This strategy is sent to User A's device in JSON format and displayed visually on a dashboard. User A creates and posts content according to the strategy and sends feedback to the server via their device, which will be used to generate the next strategy.

[0859] Prompt Sentence Examples

[0860] Generate an optimal content strategy for User A, who distributes videos on YouTube and TikTok. Please propose a specific strategy based on the analysis results of what types of videos are popular on YouTube and what types of content are preferred on TikTok. Furthermore, please tell us the expected results and performance indicators that should be measured after implementing the strategy.

[0861] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0862] Step 1: The server collects viewing data from each digital platform. Specifically, the server uses the YouTube Data API, TikTok API, and Instagram Graph API to obtain data such as the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc. using the Python library "requests." This data is received in JSON format and stored in a database (e.g., MySQL or MongoDB). The input is the response data from the API request, and the output is the viewing data stored in the database.

[0863] Step 2: The server converts the collected viewing data into a unified format and performs data cleansing. Python's "pandas" is used to fill in missing values ​​and delete unnecessary data. The input is viewing data in JSON format, and the output is cleansed data in CSV or JSON format. Specific operations include filling in missing values, deleting duplicate data, and standardizing the format.

[0864] Step 3: The server analyzes the cleansed viewing data to identify viewer behavior patterns and trends. Using the Python machine learning libraries "scikit-learn" and "TensorFlow," it builds a model to identify viewer behavior patterns from the data. The input is the cleansed viewing data, and the output is the analysis results on viewer behavior patterns and trends. Specific operations include extracting features from the data, training the model, and making inferences.

[0865] Step 4: The server evaluates the performance of each platform. It scores the performance of each piece of content based on factors such as the number of views, engagement rate, and number of comments, and compiles the evaluation results into a report. This process uses data visualization tools (e.g., Matplotlib, Tableau). The input is the analysis results, and the output is a performance evaluation report. Specific operations include calculating evaluation indicators, comparing them with past data, and generating graphs.

[0866] Step 5: The server uses a generative AI model (e.g., GPT-3) to generate an optimal content strategy and converts it into JSON format. It inputs a prompt to the AI ​​model and receives a response from the API with the generated strategy. The input is the prompt and the analysis result, and the output is the generated content strategy. Specific operations include setting the prompt, making a request to the AI ​​model, and analyzing the response.

[0867] Step 6: The terminal receives the content strategy generated from the server and displays it in a user-friendly dashboard format. It uses a front-end framework (e.g., React, Vue.js) to visually organize the received data and provide it to the user. The input is the strategy data in JSON format from the server, and the output is a visual display on the dashboard. Specific operations include parsing the data and generating graphs and lists.

[0868] Step 7: The user posts content to each platform based on the generated content strategy. For example, if you want to upload a long-form explainer video to YouTube, you shoot the video, edit it, and then upload it to YouTube. The input is the content strategy, and the output is the posted content. The specific actions are creating, editing, and uploading the video.

[0869] Step 8: The user enters the results after the strategy is implemented into a dedicated form and sends feedback from the terminal to the server. The form data is sent to the server's API endpoint as a POST request. The input is the performance data after the strategy is implemented, and the output is the feedback sent to the server. Specific actions include entering data, clicking the submit button, and transferring the data to the server.

[0870] Step 9: The server collects feedback from users and reflects it in future strategy generation. The collected feedback is stored in a database and used for the next data analysis and strategy generation. The input is feedback data from users, and the output is data reflected in the next analysis and strategy generation. Specific operations include storing the feedback in the database and integrating it into the subsequent analysis process.

[0871] (Application example 1)

[0872] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0873] In recent years, a variety of digital platforms have emerged, and content creators need to effectively reach viewers with different characteristics on each platform. However, doing so requires time and expertise to collect and analyze vast amounts of viewing data and generate optimal content strategies. Furthermore, a system that efficiently reflects user feedback and continuously optimizes content is also important. It is desirable to provide a system that can solve these challenges and enable users to effectively acquire viewers on each platform.

[0874] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0875] In this invention, the server includes means for collecting viewing data, means for analyzing the collected viewing data and evaluating performance for each platform, means for generating an optimal content strategy for each platform based on the analysis results, means for notifying users of the generated content strategy, means for collecting feedback from users and reflecting it in generating future strategies, means for providing a user interface optimized for smartphones and displaying visual advice, and means for updating and continuously optimizing a machine learning model based on the feedback data. This enables users to efficiently analyze viewing data, implement an optimal content strategy for each platform, and effectively acquire viewers.

[0876] "Viewing data" refers to information about when a user views content on a digital platform, including the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc.

[0877] A "platform" is a digital service that distributes content and allows viewers to access it, such as YouTube, TikTok, or Instagram.

[0878] "Performance" is the result of evaluating viewer response and engagement with content, taking into account indicators such as number of views, viewing time, number of likes and comments.

[0879] A "content strategy" is a policy for determining the format and content of content to effectively attract viewers on each platform, and includes recommendations such as long-form videos and short skits.

[0880] "User" refers to an individual or entity that utilizes the system provided in accordance with this invention to distribute content or execute strategies.

[0881] "Feedback" refers to information provided by users about the results and satisfaction after strategy implementation, which is used to improve future strategy generation.

[0882] A "machine learning model" is a collection of algorithms for analysis and prediction using viewing data and feedback data, and improves accuracy by continuously learning from the data.

[0883] The "user interface" refers to the interface that allows users to operate the system and visually check the generated content strategy, and is optimized for smartphones.

[0884] This invention is a system that collects and analyzes viewing data and provides users with optimal content strategies. This system is composed of a server, a terminal, and a user.

[0885] server

[0886] The server has the following features:

[0887] 1. Collecting viewing data

[0888] It collects viewing data from each digital platform, specifically using the platform's API to obtain data such as the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0889] 2. Data Analysis

[0890] The collected viewing data is converted into a unified format and analyzed using statistical methods and machine learning models to process the data and identify patterns and trends in viewer behavior.

[0891] 3. Performance Evaluation

[0892] Evaluate the performance of each piece of content (number of views and engagement rates) to identify which content is effective on which platforms.

[0893] 4. Generate a content strategy

[0894] Based on the analysis, it generates the optimal content strategy for each platform, for example recommending long-form videos for YouTube and short-form videos for TikTok based on viewing patterns.

[0895] 5. Gathering feedback and updating the machine learning model

[0896] It collects user feedback data and uses it to update the machine learning model, thereby continuously optimizing the system.

[0897] Terminal

[0898] The terminal has the following features:

[0899] 1. Receiving and displaying the strategy

[0900] The server receives the generated content strategy and visually displays it to the user in a user-friendly dashboard format that is optimized for smartphones.

[0901] 2. Gathering feedback

[0902] Provide an interface for collecting feedback from users, including performance data and satisfaction after implementing the strategy.

[0903] User

[0904] The user has the following capabilities:

[0905] 1. Strategy Implementation

[0906] Users post content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explainer video for YouTube, the user creates and posts the video accordingly.

[0907] 2. Providing Feedback

[0908] The results of the strategy execution are entered into the terminal interface and sent to the server, which collects the data necessary for future strategy generation.

[0909] Specific examples

[0910] For example, consider the case where User A distributes videos on YouTube and TikTok. The server analyzes YouTube viewing data and determines that long explanatory videos are popular, while short, impactful skits are preferred on TikTok. Following the strategy generated by the server, User A posts long, specialized explanatory videos on YouTube and short, entertaining skits on TikTok. After posting, User A collects viewing data for each piece of content and provides feedback to the server via their device. This allows the system to reflect this in future strategies.

[0911] Prompt Sentence Examples

[0912] Create a Python script that allows users to collect viewing data from YouTube, TikTok, and Instagram, and generate optimal content strategies based on data analysis.

[0913] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0914] Step 1:

[0915] The server collects viewing data.

[0916] Input: Viewing data requests from the API of each platform (e.g. YouTube, TikTok, Instagram).

[0917] Specific operation: The server uses the API of each digital platform to collect viewing data such as the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc. It sends requests using the API authentication key and receives data from each platform.

[0918] Output: JSON format response of the retrieved viewing data.

[0919] Step 2:

[0920] The server analyzes the collected viewing data.

[0921] Input: Viewing data obtained in step 1.

[0922] What it does: The server converts the viewing data into a unified format and analyzes it using machine learning models to identify patterns and trends in viewer behavior. It converts the data into TF-IDF vectors and classifies the viewing data using KMeans clustering.

[0923] Output: Viewing data patterns and trend information for each cluster.

[0924] Step 3:

[0925] The server evaluates the performance.

[0926] Input: Analysis results from step 2.

[0927] Specific operation: The server evaluates the performance of viewing data (number of views, engagement rate, etc.) for each platform and identifies which content is effective. Specifically, it analyzes the distribution of viewing numbers and engagement rates for each cluster and determines the optimal content format for each platform.

[0928] Output: Performance evaluation results for each platform.

[0929] Step 4:

[0930] The server generates the content strategy.

[0931] Input: Performance evaluation results from step 3.

[0932] What it does: Based on the analysis results, it generates the optimal content strategy for each platform, for example, recommending long videos for YouTube and short videos for TikTok based on viewing patterns.

[0933] Output: Optimal content strategies for each generated platform.

[0934] Step 5:

[0935] The terminal receives the strategy and notifies the user.

[0936] Input: The content strategy generated in step 4.

[0937] Specific operation: The device receives content strategy data from the server and visually displays it to the user. The strategy content is provided in dashboard format through a smartphone-oriented user interface.

[0938] Output: A visual content strategy interface for the user.

[0939] Step 6:

[0940] Users post content based on a strategy.

[0941] Input: Content strategy provided in step 5.

[0942] Specific behavior: Users follow the provided strategy to create and post content in a format appropriate for each platform, for example, posting a long-form explainer video on YouTube and a short skit on TikTok.

[0943] Output: Content posted to each platform.

[0944] Step 7:

[0945] The device collects the feedback and sends it to the server.

[0946] Input: Outcome data and satisfaction level provided by users after strategy implementation.

[0947] Specific operations: The results after the strategy is executed (number of views, engagement rate, etc.) are entered into the user interface and sent to the server.

[0948] Output: Feedback data.

[0949] Step 8:

[0950] The server updates the machine learning model based on the feedback data.

[0951] Input: Feedback data collected in step 7.

[0952] What it does: The server analyzes the feedback data and updates the machine learning model, allowing the system to generate more accurate content strategies in future.

[0953] Output: An updated machine learning model.

[0954] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0955] This invention is a system that combines a system that collects and analyzes viewing data and generates an optimal content strategy for each platform with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0956] System configuration

[0957] server

[0958] 1. Collection of viewing data:

[0959] The server retrieves viewing data from the API endpoints of each digital platform (e.g., YouTube, TikTok, etc.), including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0960] 2. Data Analysis:

[0961] The raw data is then converted into a unified format and analyzed to identify patterns and trends in viewer behavior using statistical methods and machine learning algorithms.

[0962] 3. Emotion Recognition with Emotion Engine:

[0963] The server uses an emotion engine to analyze facial and voice data from the user's device to identify the user's emotions, for example, using data from a webcam or microphone.

[0964] 4. Performance evaluation and strategy generation:

[0965] We evaluate the performance of each platform based on the results of viewing data analysis and user sentiment data, and then generate the optimal content strategy for each platform based on the evaluation results.

[0966] 5. Strategic Notification:

[0967] The server generates strategy data and sends it to the user's device, where specific advice for each platform is displayed in a user-friendly dashboard format.

[0968] 6. Feedback Collection:

[0969] Feedback data from users is collected and reflected in future strategy generation. Since the feedback includes emotional data, the data collected by the emotion engine is also taken into account.

[0970] Terminal

[0971] 1. Receiving and displaying the strategy:

[0972] The terminal receives strategic data from the server and visually displays it, providing specific advice to the user in the form of a dashboard.

[0973] 2. Collecting Emotional Data:

[0974] The user's facial expressions and voice data are collected through a webcam and microphone and sent to a server, which then identifies the user's emotions in real time.

[0975] User

[0976] 1. Strategy Implementation:

[0977] Users post content to each platform according to the content strategy from the server. Based on data, for example, users can post long videos to YouTube and short videos to TikTok to increase viewer engagement.

[0978] 2. Emotion-based regulation:

[0979] It adjusts content direction based on real-time feedback from the server. For example, if the emotion engine detects that the user is dissatisfied, it automatically adjusts its strategy.

[0980] 3. Providing Feedback:

[0981] The results after posting content are collected and feedback, including emotional data, is sent to the server, which then obtains the data necessary for future strategy generation.

[0982] Specific examples

[0983] For example, User B distributes videos on YouTube and TikTok. The server analyzes the viewing data obtained from User B and User B's emotional data during the distribution (e.g., emotion recognition data from facial expressions and voice). Based on this data, the server generates a content strategy that recommends "long explanatory videos" on YouTube and "short, fun skits" on TikTok. User B then posts a long video on YouTube and a short video on TikTok. The viewing data and emotional data after posting are then sent to the server as feedback, which the server uses to generate the next strategy.

[0984] In this way, the system can provide more accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement across platforms.

[0985] The processing flow will be explained below.

[0986] Step 1:

[0987] The server sends requests to the API endpoints of each digital platform (YouTube, TikTok, Instagram, etc.) to obtain viewing data, including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[0988] Step 2:

[0989] The server converts the raw data it acquires into a unified format to eliminate differences between platforms and facilitate subsequent analysis.

[0990] Step 3:

[0991] The server analyzes the aggregated viewing data, using statistical methods and machine learning algorithms to identify patterns and trends in viewer behavior.

[0992] Step 4:

[0993] The server evaluates the performance of each platform based on the analysis results, including the number of views, engagement rate, and viewing time, and analyzes how each indicator contributes.

[0994] Step 5:

[0995] The server uses an emotion engine to analyze facial expressions and voice data collected from the user's device, and identifies the user's emotional state through the analysis.

[0996] Step 6:

[0997] The server combines the results of the viewing data analysis with user sentiment data to generate the optimal content strategy for each platform. For example, YouTube recommends long videos, while TikTok recommends short videos.

[0998] Step 7:

[0999] The server sends the generated content strategy to the user's device, where a notification is displayed, allowing the user to confirm specific actions based on the strategy.

[1000] Step 8:

[1001] The device receives notifications from the server and visually displays strategies to the user, providing specific advice for each platform in the form of a dashboard.

[1002] Step 9:

[1003] Users post content to each platform based on a content strategy suggested by the server, for example, posting a long-form explainer video to YouTube and a short, fun skit to TikTok.

[1004] Step 10:

[1005] The device collects the user's facial expressions and voice data in real time, analyzes it through an emotion engine, and sends it to a server, allowing changes in the user's emotions to be grasped in real time.

[1006] Step 11:

[1007] The user evaluates the results of the content strategy and their emotional state, and then inputs the feedback into the terminal. The feedback includes viewing data and emotional data.

[1008] Step 12:

[1009] The device collects feedback data from users and sends it to the server, which uses this feedback to improve the strategy generation process and provide more accurate advice in the future.

[1010] Through this specific process, the system can provide content strategies that take into account the user's emotional state and effectively acquire audiences on each platform.

[1011] Example 2

[1012] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1013] Conventional content strategy generation systems were able to generate strategies based on the analysis of viewing data, but were unable to generate strategies that took into account viewer emotions. As a result, strategies that did not reflect viewer reactions or emotions resulted in the provision of less than optimal content. Furthermore, strategies that took into account the characteristics of each platform across multiple digital platforms were not sufficiently generated.

[1014] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting viewing data, a means for converting the collected viewing data into a unified format and analyzing it, a means for collecting user facial expression and voice data and recognizing emotions, a means for generating an optimal content strategy for each platform based on the analysis results and emotion data, a means for notifying the user of the generated content strategy on the user's terminal and visually displaying it, and a means for collecting feedback data from the user and reflecting it in future strategy generation. This makes it possible to generate a more accurate content strategy that takes into account not only viewing data but also viewer emotions. It is also possible to provide a strategy that takes into account the characteristics of each platform.

[1015] "Viewing data" refers to data including the number of views on digital platforms, viewing time, viewing completion rate, viewer attributes, number of likes and comments, etc.

[1016] The "unified format" is a data format that converts viewing data collected from multiple digital platforms into a format that is easy to analyze.

[1017] "Facial expression data" refers to data relating to the facial expressions of a user captured through a webcam.

[1018] "Voice data" refers to data relating to the user's speech or voice acquired through a microphone.

[1019] "Emotion recognition" means analyzing facial expression data and voice data to identify the user's emotional state (for example, joy, sadness, surprise, etc.).

[1020] The "analysis results" are analysis results based on viewing data and emotional data, and indicate the behavioral patterns and emotional tendencies of viewers.

[1021] "Content strategy" refers to the type, content, timing, etc. of content posted on digital platforms.

[1022] A "user terminal" is a device (e.g., a PC, a smartphone, a tablet, etc.) that visually displays strategic data and collects feedback from users.

[1023] "Feedback data" refers to data provided by users that includes opinions, results, and sentiment data regarding content strategies.

[1024] This invention is a system that collects and analyzes viewing data to generate optimal content strategies for each platform. Furthermore, by combining it with an emotion engine that recognizes user emotions, it provides a more accurate content strategy.

[1025] server

[1026] 1. Collection of viewing data:

[1027] The server obtains viewing data from digital platforms such as YouTube and TikTok through APIs, using OAuth for authentication, and collects data such as the number of views, viewer attributes, viewing time, completion rate, likes, and comments.

[1028] 2. Data Analysis:

[1029] The server uses Python's pandas library to convert the collected viewing data into a unified format, then analyzes the data using machine learning algorithms such as scikit-learn to identify patterns in viewer behavior.

[1030] 3. Emotion Recognition with Emotion Engine:

[1031] The server collects facial and voice data from the user's device in real time and recognizes emotions. It uses the OpenCV library to analyze facial data and the Google Cloud Speech-to-Text API to analyze voice data.

[1032] 4. Performance evaluation and strategy generation:

[1033] The server evaluates the performance of each platform based on viewing data analysis and sentiment data, and then uses a generative AI model to generate the optimal content strategy for each platform.

[1034] 5. Strategic Notification:

[1035] The server sends the generated strategy to the user's device, where it is visually displayed in a dashboard format using a front-end framework such as React.js.

[1036] 6. Feedback Collection:

[1037] The server collects feedback from users, including viewing data and emotional data, and reflects this feedback in future strategy generation.

[1038] Terminal

[1039] 1. Receiving and displaying the strategy:

[1040] The terminal receives strategy data from the server and displays it to the user in a dashboard format, allowing the user to visually grasp specific advice for each platform.

[1041] 2. Collecting Emotional Data:

[1042] The device collects the user's facial expressions and voice data through a webcam and microphone and transmits it to a server in real time.

[1043] User

[1044] 1. Strategy Implementation:

[1045] Users follow the content strategy provided by the server to post content appropriate for each platform, for example, posting long videos to YouTube and short videos to TikTok.

[1046] 2. Emotion-based regulation:

[1047] Based on real-time feedback from the server, users can adjust the direction of their content. When the emotion engine recognizes the user's satisfaction, it automatically adjusts the strategy.

[1048] 3. Providing Feedback:

[1049] After posting content, users send feedback including performance data and emotional data to the server, which then acquires the data necessary for generating the next strategy.

[1050] Specific examples

[1051] For example, User B distributes videos on YouTube and TikTok. The server analyzes the viewing data obtained from User B and User B's emotional data during distribution (e.g., emotion recognition data from facial expressions and voice). Based on the analysis results, the server generates a content strategy that recommends long explanatory videos on YouTube and short, entertaining skits on TikTok. User B follows this strategy and posts long videos on YouTube and short videos on TikTok. The viewing data and emotional data after posting are then sent to the server as feedback, which the server uses to generate the next strategy.

[1052] For example, here is an example of a prompt to input to a generative AI model:

[1053] "If the average watch time of viewers on YouTube is increasing, what type of video should I post next?"

[1054] As a result, this system can provide highly accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement on each platform.

[1055] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1056] Step 1:

[1057] The server connects to the API of each digital platform (e.g., YouTube, TikTok) to collect viewing data. The server performs OAuth authentication using the API key and secret key, and sends an HTTP request to obtain viewing data (number of views, viewer attributes, viewing time, viewing completion rate, number of likes, number of comments, etc.) from the data endpoint. The input data is the API endpoint URL and authentication information, and the output is viewing data in JSON format.

[1058] Step 2:

[1059] The server converts the acquired viewing data into a unified format. Specifically, it uses the Python pandas library to convert raw data into data frame format. The input of this step is viewing data in JSON format, and the output is viewing data in a unified format (data frame format).

[1060] Step 3:

[1061] The server analyzes the converted viewing data to identify patterns and trends in viewer behavior. Specifically, it uses a scikit-learn clustering algorithm to identify viewer behavior patterns. The input to this step is viewing data in a data frame format, and the output is clustered viewer behavior patterns.

[1062] Step 4:

[1063] The device uses a webcam and microphone to collect the user's facial and voice data and transmits it to the server in real time. The input is the user's real-time facial and voice data, and the output is raw emotion data sent to the server.

[1064] Step 5:

[1065] The server analyzes the facial and voice data sent from the device to identify the user's emotions. Specifically, it uses the OpenCV library to analyze the facial data and the Google Cloud Speech-to-Text API to analyze the voice data. The input of this step is the raw emotion data sent from the device, and the output is the analyzed emotion data.

[1066] Step 6:

[1067] The server combines the analysis results of the viewing data with the emotion data to evaluate the performance of each platform. The analysis results and emotion data are integrated to calculate a performance index for each platform. The input is the clustered viewing data and the analyzed emotion data, and the output is a performance index for each platform.

[1068] Step 7:

[1069] The server uses a generative AI model to generate the optimal content strategy for each platform, for example suggesting long-form explainer videos for YouTube and short, fun skits for TikTok. The input for this step is performance metrics, and the output is the optimal content strategy for each platform.

[1070] Step 8:

[1071] The server sends the generated strategy data to the user's device, which then visually displays it. The device uses React.js to display the strategy in a dashboard format and provide specific advice to the user. The input of this step is the generated content strategy, and the output is the visual advice on the dashboard.

[1072] Step 9:

[1073] The user posts content appropriate for each platform according to the content strategy provided by the server. Specifically, the user posts long videos to YouTube and short videos to TikTok. The input of this step is the content strategy, and the output is the content posted to each platform.

[1074] Step 10:

[1075] After posting content, users collect performance and emotion data and send it to the server. The feedback data includes viewing data and user emotion data. The input of this step is performance data and emotion data, and the output is feedback data sent to the server.

[1076] Step 11:

[1077] The server analyzes the feedback data collected from users and reflects it in the next strategy generation. The feedback data is stored in a database and used for future strategy generation. The input of this step is the feedback data, and the output is the analyzed feedback information.

[1078] (Application example 2)

[1079] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1080] Content distribution on modern digital platforms requires analyzing user viewing data and generating optimal content strategies for each platform. However, current systems rely on analyzing viewing data and lack the ability to generate strategies that take into account the user's emotional state. This makes it difficult to provide individually optimized strategies that reflect user feedback and emotional changes in real time.

[1081] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting viewing data, means for analyzing the collected viewing data and evaluating performance for each platform, means including an emotion engine for collecting and analyzing user emotion data, means for generating an optimal content strategy for each platform based on the analysis results and the emotion data, means for notifying users of the generated content strategy, and means for collecting feedback from users and reflecting it in future strategy generation. As a result, by combining and analyzing viewing data and user emotion data, it is possible to generate an individually optimal content strategy in real time and maximize user engagement.

[1082] "Viewing data" refers to information such as the number of viewers of content on digital platforms, viewing time, completion rate, number of likes and comments, etc.

[1083] An "emotion engine" refers to a system that analyzes a user's facial expressions and voice data to identify the user's emotional state in real time.

[1084] "Server" refers to the core processing system that collects and analyzes viewing and sentiment data to generate and inform optimal content strategies for each platform.

[1085] "Platform performance" is a metric that shows how successful content is on each digital platform and encompasses multiple factors such as number of views, viewing time, and engagement rate.

[1086] "Content strategy" refers to a plan that uses viewing and sentiment data to suggest the most appropriate type of content and posting timing for each platform.

[1087] "Feedback" refers to information provided by users, including their reactions and impressions after viewing content, viewing data, and emotional data.

[1088] The present invention provides a system that combines an emotion engine that collects and analyzes viewing data and recognizes the user's emotions. Specific embodiments of this system will be described below.

[1089] System configuration

[1090] server

[1091] The server includes the following means:

[1092] 1. Collection of viewing data:

[1093] The server retrieves viewing data from the API endpoints of each digital platform (e.g., video platform), including the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[1094] 2. Data Analysis:

[1095] The raw data is then converted into a unified format and analyzed to identify patterns and trends in viewer behavior using statistical methods and machine learning algorithms.

[1096] 3. Emotion Recognition with Emotion Engine:

[1097] The server uses an emotion engine to analyze facial and voice data from the user's device to identify the user's emotions, for example, using emotion recognition models built with TensorFlow and Keras.

[1098] 4. Performance evaluation and strategy generation:

[1099] We evaluate the performance of each platform based on the results of viewing data analysis and user sentiment data, and then generate the optimal content strategy for each platform based on the evaluation results.

[1100] 5. Strategic Notification:

[1101] The server sends the generated strategies to the user's terminal via the Internet, where they are visually displayed in a user-friendly dashboard format.

[1102] 6. Feedback Collection:

[1103] Feedback data from users is collected and reflected in future strategy generation. Since the feedback includes emotional data, the data collected by the emotion engine is also taken into account.

[1104] Terminal

[1105] The terminal includes the following means:

[1106] 1. Receiving and displaying the strategy:

[1107] The device receives the content strategy sent from the server and provides specific advice in the form of a dashboard.

[1108] 2. Collecting Emotional Data:

[1109] The smartphone's camera and microphone are used to collect the user's facial expressions and voice data, which are then sent to a server, allowing the user's emotions to be identified in real time.

[1110] User

[1111] The user includes the following means:

[1112] 1. Strategy Implementation:

[1113] Users post content to each platform based on the content strategy provided by the server. For example, users can post long videos to YouTube and short videos to TikTok to increase viewer engagement.

[1114] 2. Emotion-based regulation:

[1115] It adjusts content direction based on real-time feedback from the server. For example, if the emotion engine detects that the user is dissatisfied, it automatically adjusts its strategy.

[1116] 3. Providing Feedback:

[1117] The results after posting content are collected and feedback, including emotional data, is sent to the server, which then obtains the data necessary for future strategy generation.

[1118] Specific examples

[1119] The following is a specific example:

[1120] Example of viewing data obtained from the platform: "Average viewing time 320 seconds, 15,000 views, 120 comments"

[1121] Example of user sentiment analysis result: "Emotion 'happy', probability 0.85"

[1122] Example prompt for a generative AI model: "Generate the optimal content strategy based on viewing data and sentiment data. Viewing data: average viewing time 320 seconds, 15,000 views, 120 comments. Sentiment data: sentiment 'happy', probability 0.85."

[1123] In this way, the system can provide more accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement across platforms.

[1124] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1125] Step 1:

[1126] Collecting viewing data

[1127] The server collects viewing data from each digital platform. Specifically, it accesses API endpoints such as YouTube and TikTok to obtain data such as the number of views, viewer attributes, viewing time, viewing completion rate, number of likes and comments, etc. The server receives raw data from the platforms as viewing data as input and outputs it as a data list.

[1128] Step 2:

[1129] Data analysis

[1130] The server converts the collected viewing data into a unified format and analyzes it. It uses statistical methods and machine learning algorithms to identify viewer behavior patterns and trends. Specifically, it calculates indicators such as viewing time distribution and engagement rate, and generates the analysis results as output.

[1131] Step 3:

[1132] Collecting Emotional Data

[1133] The device uses the smartphone's camera and microphone to collect the user's facial and voice data and transmits that data to a server. Specifically, when the user uses the app, the camera and microphone are activated, capturing facial and voice data in real time and transmitting it to the server. In this process, raw data obtained from the camera and microphone is input and output as emotion data.

[1134] Step 4:

[1135] Emotion Analysis

[1136] The server analyzes the received facial and voice data to identify the user's emotions. This analysis uses an emotion recognition model built with TensorFlow or Keras, for example. Specifically, image processing technology is used to extract facial features and classify emotions based on those features. This outputs emotion labels and their probabilities as analysis results.

[1137] Step 5:

[1138] Performance Evaluation and Strategy Generation

[1139] The server evaluates the performance of each platform based on the analysis of viewing data and emotional data, and generates an optimal content strategy. Specifically, it evaluates the viewing data and user emotional state for each platform, and generates the most efficient content strategy from the evaluation results using an AI model. The generated content strategy is then output.

[1140] Step 6:

[1141] Strategic Notification

[1142] The server notifies the user of the generated content strategy. Specifically, the strategy data is sent via the Internet and visualized in a dashboard format on the user's device. This notification allows the user to easily understand the strategy.

[1143] Step 7:

[1144] Implementing strategies and gathering feedback

[1145] Users post content to each platform based on the content strategy provided by the server. After posting, users provide feedback to the server, including viewing data and emotional data. Specifically, the number of views and comments on the posted video, as well as the user's own emotional state, are sent as input to the server, which then reflects this in future strategy generation.

[1146] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1147] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1148] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1149] [Fourth embodiment]

[1150] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1151] 7, a 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.

[1152] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1153] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1154] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1155] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1156] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1157] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1158] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1159] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1160] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1161] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1162] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1163] This invention provides a system that collects and analyzes viewing data, generates an optimal content strategy, and notifies users, thereby enabling users to effectively acquire viewers on each platform. Specific embodiments of this system are described below.

[1164] System configuration

[1165] server

[1166] 1. Collection of viewing data:

[1167] The server collects viewing data from each platform (e.g., YouTube, TikTok, Instagram) by sending API requests to obtain data including the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[1168] 2. Data Analysis:

[1169] The collected viewing data is converted into a unified format and analyzed to identify patterns and trends in viewer behavior, using statistical methods and machine learning models.

[1170] 3. Performance Evaluation:

[1171] Evaluate the performance of each piece of content (number of views and engagement rates) to identify which content is effective on which platforms.

[1172] 4. Generate a content strategy:

[1173] Based on the analysis results, the system generates the optimal content strategy for each platform, providing advice tailored to the characteristics of each platform, such as recommending long videos for YouTube and short videos for TikTok.

[1174] Terminal

[1175] 1. Receiving and displaying the strategy:

[1176] The user's device receives the strategy data generated by the server and visually displays it, providing specific advice for each platform in a user-friendly dashboard format.

[1177] 2. Gathering Feedback:

[1178] Provide an interface for collecting feedback from users, including performance data and satisfaction after implementing the strategy.

[1179] User

[1180] 1. Strategy Implementation:

[1181] Users post content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explainer video for YouTube, users create and post the video accordingly.

[1182] 2. Providing Feedback:

[1183] The results of the strategy execution are entered into the interface and sent to the server, which then obtains data to use in future strategy generation.

[1184] Specific examples

[1185] For example, User A distributes videos on YouTube and TikTok. The server analyzes data from YouTube that shows that long explanatory videos are popular, and determines that short, impactful skits are preferred on TikTok. Following the strategy generated by the server, User A posts long, specialized explanatory videos on YouTube and short, entertaining skits on TikTok. After posting, User A collects viewing data for each piece of content and provides feedback to the server via their device.

[1186] In this way, users can implement effective content strategies across each platform and optimize audience acquisition.

[1187] The processing flow will be explained below.

[1188] Step 1:

[1189] The server sends a request to the API endpoint of each platform (YouTube, TikTok, Instagram, etc.) to obtain viewing data, including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[1190] Step 2:

[1191] The server converts the raw data it acquires into a unified format, which is done to streamline the subsequent analysis process.

[1192] Step 3:

[1193] The server uses statistical methods and machine learning algorithms to analyze the aggregated viewing data, with the goal of identifying patterns and trends in viewer behavior.

[1194] Step 4:

[1195] The server evaluates the performance of each platform based on the analysis results, including the number of views, engagement rate, and viewing time.

[1196] Step 5:

[1197] The server generates the optimal content strategy for each platform, making suggestions based on the characteristics of each platform, such as recommending long videos for YouTube and short videos for TikTok.

[1198] Step 6:

[1199] The server generates a content strategy that is delivered to the user's device, displayed in a user-friendly dashboard format and includes specific advice for each platform.

[1200] Step 7:

[1201] The device visually displays the content strategy notified by the server to the user, who then uses the displayed strategy to create a content plan and decide what to post on each platform.

[1202] Step 8:

[1203] Users post content to each platform through their devices according to the content strategy proposed by the server, for example, posting long-form expert instructional videos to YouTube and short, funny skits to TikTok.

[1204] Step 9:

[1205] The results of the strategies implemented by the user are collected and entered into the device, including viewing data after content is posted, engagement rates, and user satisfaction.

[1206] Step 10:

[1207] The device sends the feedback data collected from the user to the server, which can then use this feedback to improve future content strategies and provide more effective advice.

[1208] This specific process flow allows users to effectively acquire viewers across platforms and achieve consistent content delivery.

[1209] Example 1

[1210] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1211] Conventional content strategy generation systems require a lot of manual work to collect and analyze viewing data, making them inefficient. Furthermore, generating effective content strategies for different digital platforms requires advanced expertise, making them difficult for average users to use. Furthermore, there is a lack of a mechanism for continuously evaluating the effectiveness of the generated strategies and reflecting this in the next strategy generation, making it difficult to adapt to viewer needs.

[1212] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1213] In this invention, the server includes means for collecting viewing data, means for converting the collected viewing data into a unified format and performing data cleansing, means for analyzing the viewing data after data cleansing and identifying viewer behavior patterns and trends, means for evaluating the performance of each platform based on the analysis results, means for generating an optimal content strategy for each platform using a generative AI model, means for notifying users of the generated content strategy in a user-friendly dashboard format, and means for collecting feedback from users and reflecting it in future strategy generation. This makes it possible to implement a series of automated processes from viewing data collection to analysis, strategy generation, and feedback collection, thereby enabling effective content strategies to be provided quickly and efficiently.

[1214] "Viewing data" refers to data that indicates the viewing status of videos and content on each digital platform, and includes the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc.

[1215] "Data cleansing" is the process of removing inaccurate information, duplicate information, and missing values ​​from collected viewing data and preparing it in an analyzable format.

[1216] "Behavioral patterns" refer to specific actions or tendencies that viewers exhibit on digital platforms, and are characteristics identified through analysis of factors such as length of viewing time and reactions to specific content.

[1217] A "trend" refers to an increasing audience interest or concern over a specific period of time, including a spike or decline in interest in a particular topic or genre.

[1218] "Performance" is an indicator of how well content is received by viewers and how much engagement it generates, and is an evaluation calculated based on the number of views and engagement rate (number of likes, number of comments, etc.).

[1219] "Generative AI model" is a general term for artificial intelligence models that generate natural language based on data and output analytical results, and are used to generate content strategies.

[1220] A "dashboard" is an interface that displays data and strategies in a visually easy-to-understand format for users, and includes strategies and analysis results for each platform.

[1221] "Feedback" refers to data that a user inputs, such as the results, impressions, and improvements of the content strategy they have implemented, and sends to the server, and is reflected in future strategy generation.

[1222] This invention provides a system that collects and analyzes viewing data, generates an optimal content strategy, and notifies users, thereby enabling users to effectively acquire viewers on each platform. Specific embodiments of this system are described below.

[1223] System configuration

[1224] server

[1225] The server uses a high-performance server computer and multiple pieces of software to collect viewing data, analyze it, evaluate performance, and generate content strategies. Specifically, it uses programming languages ​​such as Python and Node.js to send API requests to the YouTube Data API, TikTok API, and Instagram Graph API to obtain information such as the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[1226] The server that collects the viewing data first uses "pandas" to convert the data into a unified format. During the data cleansing process, missing values ​​are filled in and unnecessary data is removed. The cleansed data is then analyzed using statistical methods and machine learning models (e.g., scikit-learn, TensorFlow). This analysis identifies viewer behavior patterns and trends, and the results are visualized using Matplotlib.

[1227] Next, the performance of each piece of content is evaluated based on the number of views and engagement rate, and changes are compared with past data to create a report. This report is visually presented using a data visualization tool (e.g., Tableau).

[1228] Based on the analysis results, a generative AI model (e.g., GPT-3) is used to generate an optimal content strategy for each platform. The generated strategy is converted into JSON format and sent to the user's device.

[1229] Terminal

[1230] The user's device (PC or smartphone) receives the generated content from the server via an HTTP request. The received data is displayed in a user-friendly dashboard format. The software used here is a front-end framework such as React or Vue.js. This makes it easier to understand the strategy through a visual interface.

[1231] The terminal also provides an interface where users can enter feedback. After the user enters the feedback and presses the submit button, the data is sent to the server via the terminal. The terminal sends the form data as a POST request to a specific API endpoint on the server.

[1232] User

[1233] Users post new content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explanatory video on YouTube, the user creates a video along those lines and posts it. They check performance data on the management screen or app of each platform, enter that data into a dedicated form, and send feedback to the server. This allows the server to use the feedback information to generate future strategies.

[1234] Specific examples

[1235] For example, User A distributes videos on YouTube and TikTok. The server collects viewing data and uses the YouTube Data API and TikTok API to obtain data such as the number of views, viewing time, and viewer attributes from each platform. The server then cleanses the data using "pandas" and analyzes behavioral patterns using "scikit-learn." Based on the analysis results, GPT-3 determines that long-form explanatory videos are effective on YouTube and short skits on TikTok, and generates a new content strategy. This strategy is sent to User A's device in JSON format and displayed visually on a dashboard. User A creates and posts content according to the strategy and sends feedback to the server via their device, which will be used to generate the next strategy.

[1236] Prompt Sentence Examples

[1237] Generate an optimal content strategy for User A, who distributes videos on YouTube and TikTok. Please propose a specific strategy based on the analysis results of what types of videos are popular on YouTube and what types of content are preferred on TikTok. Furthermore, please tell us the expected results and performance indicators that should be measured after implementing the strategy.

[1238] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1239] Step 1: The server collects viewing data from each digital platform. Specifically, the server uses the YouTube Data API, TikTok API, and Instagram Graph API to obtain data such as the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc. using the Python library "requests." This data is received in JSON format and stored in a database (e.g., MySQL or MongoDB). The input is the response data from the API request, and the output is the viewing data stored in the database.

[1240] Step 2: The server converts the collected viewing data into a unified format and performs data cleansing. Python's "pandas" is used to fill in missing values ​​and delete unnecessary data. The input is viewing data in JSON format, and the output is cleansed data in CSV or JSON format. Specific operations include filling in missing values, deleting duplicate data, and standardizing the format.

[1241] Step 3: The server analyzes the cleansed viewing data to identify viewer behavior patterns and trends. Using the Python machine learning libraries "scikit-learn" and "TensorFlow," it builds a model to identify viewer behavior patterns from the data. The input is the cleansed viewing data, and the output is the analysis results on viewer behavior patterns and trends. Specific operations include extracting features from the data, training the model, and making inferences.

[1242] Step 4: The server evaluates the performance of each platform. It scores the performance of each piece of content based on factors such as the number of views, engagement rate, and number of comments, and compiles the evaluation results into a report. This process uses data visualization tools (e.g., Matplotlib, Tableau). The input is the analysis results, and the output is a performance evaluation report. Specific operations include calculating evaluation indicators, comparing them with past data, and generating graphs.

[1243] Step 5: The server uses a generative AI model (e.g., GPT-3) to generate an optimal content strategy and converts it into JSON format. It inputs a prompt to the AI ​​model and receives a response from the API with the generated strategy. The input is the prompt and the analysis result, and the output is the generated content strategy. Specific operations include setting the prompt, making a request to the AI ​​model, and analyzing the response.

[1244] Step 6: The terminal receives the content strategy generated from the server and displays it in a user-friendly dashboard format. It uses a front-end framework (e.g., React, Vue.js) to visually organize the received data and provide it to the user. The input is the strategy data in JSON format from the server, and the output is a visual display on the dashboard. Specific operations include parsing the data and generating graphs and lists.

[1245] Step 7: The user posts content to each platform based on the generated content strategy. For example, if you want to upload a long-form explainer video to YouTube, you shoot the video, edit it, and then upload it to YouTube. The input is the content strategy, and the output is the posted content. The specific actions are creating, editing, and uploading the video.

[1246] Step 8: The user enters the results after the strategy is implemented into a dedicated form and sends feedback from the terminal to the server. The form data is sent to the server's API endpoint as a POST request. The input is the performance data after the strategy is implemented, and the output is the feedback sent to the server. Specific actions include entering data, clicking the submit button, and transferring the data to the server.

[1247] Step 9: The server collects feedback from users and reflects it in future strategy generation. The collected feedback is stored in a database and used for the next data analysis and strategy generation. The input is feedback data from users, and the output is data reflected in the next analysis and strategy generation. Specific operations include storing the feedback in the database and integrating it into the subsequent analysis process.

[1248] (Application example 1)

[1249] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1250] In recent years, a variety of digital platforms have emerged, and content creators need to effectively reach viewers with different characteristics on each platform. However, doing so requires time and expertise to collect and analyze vast amounts of viewing data and generate optimal content strategies. Furthermore, a system that efficiently reflects user feedback and continuously optimizes content is also important. It is desirable to provide a system that can solve these challenges and enable users to effectively acquire viewers on each platform.

[1251] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1252] In this invention, the server includes means for collecting viewing data, means for analyzing the collected viewing data and evaluating performance for each platform, means for generating an optimal content strategy for each platform based on the analysis results, means for notifying users of the generated content strategy, means for collecting feedback from users and reflecting it in generating future strategies, means for providing a user interface optimized for smartphones and displaying visual advice, and means for updating and continuously optimizing a machine learning model based on the feedback data. This enables users to efficiently analyze viewing data, implement an optimal content strategy for each platform, and effectively acquire viewers.

[1253] "Viewing data" refers to information about when a user views content on a digital platform, including the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc.

[1254] A "platform" is a digital service that distributes content and allows viewers to access it, such as YouTube, TikTok, or Instagram.

[1255] "Performance" is the result of evaluating viewer response and engagement with content, taking into account indicators such as number of views, viewing time, number of likes and comments.

[1256] A "content strategy" is a policy for determining the format and content of content to effectively attract viewers on each platform, and includes recommendations such as long-form videos and short skits.

[1257] "User" refers to an individual or entity that utilizes the system provided in accordance with this invention to distribute content or execute strategies.

[1258] "Feedback" refers to information provided by users about the results and satisfaction after strategy implementation, which is used to improve future strategy generation.

[1259] A "machine learning model" is a collection of algorithms for analysis and prediction using viewing data and feedback data, and improves accuracy by continuously learning from the data.

[1260] The "user interface" refers to the interface that allows users to operate the system and visually check the generated content strategy, and is optimized for smartphones.

[1261] This invention is a system that collects and analyzes viewing data and provides users with optimal content strategies. This system is composed of a server, a terminal, and a user.

[1262] server

[1263] The server has the following features:

[1264] 1. Collecting viewing data

[1265] It collects viewing data from each digital platform, specifically using the platform's API to obtain data such as the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[1266] 2. Data Analysis

[1267] The collected viewing data is converted into a unified format and analyzed using statistical methods and machine learning models to process the data and identify patterns and trends in viewer behavior.

[1268] 3. Performance Evaluation

[1269] Evaluate the performance of each piece of content (number of views and engagement rates) to identify which content is effective on which platforms.

[1270] 4. Generate a content strategy

[1271] Based on the analysis, it generates the optimal content strategy for each platform, for example recommending long-form videos for YouTube and short-form videos for TikTok based on viewing patterns.

[1272] 5. Gathering feedback and updating the machine learning model

[1273] It collects user feedback data and uses it to update the machine learning model, thereby continuously optimizing the system.

[1274] Terminal

[1275] The terminal has the following features:

[1276] 1. Receiving and displaying the strategy

[1277] The server receives the generated content strategy and visually displays it to the user in a user-friendly dashboard format that is optimized for smartphones.

[1278] 2. Gathering feedback

[1279] Provide an interface for collecting feedback from users, including performance data and satisfaction after implementing the strategy.

[1280] User

[1281] The user has the following capabilities:

[1282] 1. Strategy Implementation

[1283] Users post content to each platform based on the content strategy received from the server. For example, if the server recommends a long-form explainer video for YouTube, the user creates and posts the video accordingly.

[1284] 2. Providing Feedback

[1285] The results of the strategy execution are entered into the terminal interface and sent to the server, which collects the data necessary for future strategy generation.

[1286] Specific examples

[1287] For example, consider the case where User A distributes videos on YouTube and TikTok. The server analyzes YouTube viewing data and determines that long explanatory videos are popular, while short, impactful skits are preferred on TikTok. Following the strategy generated by the server, User A posts long, specialized explanatory videos on YouTube and short, entertaining skits on TikTok. After posting, User A collects viewing data for each piece of content and provides feedback to the server via their device. This allows the system to reflect this in future strategies.

[1288] Prompt Sentence Examples

[1289] Create a Python script that allows users to collect viewing data from YouTube, TikTok, and Instagram, and generate optimal content strategies based on data analysis.

[1290] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1291] Step 1:

[1292] The server collects viewing data.

[1293] Input: Viewing data requests from the API of each platform (e.g. YouTube, TikTok, Instagram).

[1294] Specific operation: The server uses the API of each digital platform to collect viewing data such as the number of views, viewing time, viewer attributes, viewing completion rate, number of likes and comments, etc. It sends requests using the API authentication key and receives data from each platform.

[1295] Output: JSON format response of the retrieved viewing data.

[1296] Step 2:

[1297] The server analyzes the collected viewing data.

[1298] Input: Viewing data obtained in step 1.

[1299] What it does: The server converts the viewing data into a unified format and analyzes it using machine learning models to identify patterns and trends in viewer behavior. It converts the data into TF-IDF vectors and classifies the viewing data using KMeans clustering.

[1300] Output: Viewing data patterns and trend information for each cluster.

[1301] Step 3:

[1302] The server evaluates the performance.

[1303] Input: Analysis results from step 2.

[1304] Specific operation: The server evaluates the performance of viewing data (number of views, engagement rate, etc.) for each platform and identifies which content is effective. Specifically, it analyzes the distribution of viewing numbers and engagement rates for each cluster and determines the optimal content format for each platform.

[1305] Output: Performance evaluation results for each platform.

[1306] Step 4:

[1307] The server generates the content strategy.

[1308] Input: Performance evaluation results from step 3.

[1309] What it does: Based on the analysis results, it generates the optimal content strategy for each platform, for example, recommending long videos for YouTube and short videos for TikTok based on viewing patterns.

[1310] Output: Optimal content strategies for each generated platform.

[1311] Step 5:

[1312] The terminal receives the strategy and notifies the user.

[1313] Input: The content strategy generated in step 4.

[1314] Specific operation: The device receives content strategy data from the server and visually displays it to the user. The strategy content is provided in dashboard format through a smartphone-oriented user interface.

[1315] Output: A visual content strategy interface for the user.

[1316] Step 6:

[1317] Users post content based on a strategy.

[1318] Input: Content strategy provided in step 5.

[1319] Specific behavior: Users follow the provided strategy to create and post content in a format appropriate for each platform, for example, posting a long-form explainer video on YouTube and a short skit on TikTok.

[1320] Output: Content posted to each platform.

[1321] Step 7:

[1322] The device collects the feedback and sends it to the server.

[1323] Input: Outcome data and satisfaction level provided by users after strategy implementation.

[1324] Specific operations: The results after the strategy is executed (number of views, engagement rate, etc.) are entered into the user interface and sent to the server.

[1325] Output: Feedback data.

[1326] Step 8:

[1327] The server updates the machine learning model based on the feedback data.

[1328] Input: Feedback data collected in step 7.

[1329] What it does: The server analyzes the feedback data and updates the machine learning model, allowing the system to generate more accurate content strategies in future.

[1330] Output: An updated machine learning model.

[1331] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1332] This invention is a system that combines a system that collects and analyzes viewing data and generates optimal content strategies for each platform with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1333] System configuration

[1334] server

[1335] 1. Collection of viewing data:

[1336] The server retrieves viewing data from the API endpoints of each digital platform (e.g., YouTube, TikTok, etc.), including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[1337] 2. Data Analysis:

[1338] The raw data is then converted into a unified format and analyzed to identify patterns and trends in viewer behavior using statistical methods and machine learning algorithms.

[1339] 3. Emotion Recognition with Emotion Engine:

[1340] The server uses an emotion engine to analyze facial and voice data from the user's device to identify the user's emotions, for example, using data from a webcam or microphone.

[1341] 4. Performance evaluation and strategy generation:

[1342] We evaluate the performance of each platform based on the results of viewing data analysis and user sentiment data, and then generate the optimal content strategy for each platform based on the evaluation results.

[1343] 5. Strategic Notification:

[1344] The server generates strategy data and sends it to the user's device, where specific advice for each platform is displayed in a user-friendly dashboard format.

[1345] 6. Feedback Collection:

[1346] Feedback data from users is collected and reflected in future strategy generation. Since the feedback includes emotional data, the data collected by the emotion engine is also taken into account.

[1347] Terminal

[1348] 1. Receiving and displaying the strategy:

[1349] The terminal receives strategic data from the server and visually displays it, providing specific advice to the user in the form of a dashboard.

[1350] 2. Collecting Emotional Data:

[1351] The user's facial expressions and voice data are collected through a webcam and microphone and sent to a server, which then identifies the user's emotions in real time.

[1352] User

[1353] 1. Strategy Implementation:

[1354] Users post content to each platform according to the content strategy from the server. Based on data, for example, users can post long videos to YouTube and short videos to TikTok to increase viewer engagement.

[1355] 2. Emotion-based regulation:

[1356] It adjusts content direction based on real-time feedback from the server. For example, if the emotion engine detects that the user is dissatisfied, it automatically adjusts its strategy.

[1357] 3. Providing Feedback:

[1358] The results after posting content are collected and feedback, including emotional data, is sent to the server, which then obtains the data necessary for future strategy generation.

[1359] Specific examples

[1360] For example, User B distributes videos on YouTube and TikTok. The server analyzes the viewing data obtained from User B and User B's emotional data during the distribution (e.g., emotion recognition data from facial expressions and voice). Based on this data, the server generates a content strategy that recommends "long explanatory videos" on YouTube and "short, fun skits" on TikTok. User B then posts a long video on YouTube and a short video on TikTok. The viewing data and emotional data after posting are then sent to the server as feedback, which the server uses to generate the next strategy.

[1361] In this way, the system can provide more accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement across platforms.

[1362] The processing flow will be explained below.

[1363] Step 1:

[1364] The server sends requests to the API endpoints of each digital platform (YouTube, TikTok, Instagram, etc.) to obtain viewing data, including the number of views, viewer demographics, viewing time, completion rate, number of likes and comments, etc.

[1365] Step 2:

[1366] The server converts the raw data it acquires into a unified format to eliminate differences between platforms and facilitate subsequent analysis.

[1367] Step 3:

[1368] The server analyzes the aggregated viewing data, using statistical methods and machine learning algorithms to identify patterns and trends in viewer behavior.

[1369] Step 4:

[1370] The server evaluates the performance of each platform based on the analysis results, including the number of views, engagement rate, and viewing time, and analyzes how each indicator contributes.

[1371] Step 5:

[1372] The server uses an emotion engine to analyze facial expressions and voice data collected from the user's device, and identifies the user's emotional state through the analysis.

[1373] Step 6:

[1374] The server combines the results of the viewing data analysis with user sentiment data to generate the optimal content strategy for each platform. For example, YouTube recommends long videos, while TikTok recommends short videos.

[1375] Step 7:

[1376] The server sends the generated content strategy to the user's device, where a notification is displayed, allowing the user to confirm specific actions based on the strategy.

[1377] Step 8:

[1378] The device receives notifications from the server and visually displays strategies to the user, providing specific advice for each platform in the form of a dashboard.

[1379] Step 9:

[1380] Users post content to each platform based on a content strategy suggested by the server, for example, posting a long-form explainer video to YouTube and a short, fun skit to TikTok.

[1381] Step 10:

[1382] The device collects the user's facial expressions and voice data in real time, analyzes it through an emotion engine, and sends it to a server, allowing changes in the user's emotions to be grasped in real time.

[1383] Step 11:

[1384] The user evaluates the results of the content strategy and their emotional state, and then inputs the feedback into the terminal. The feedback includes viewing data and emotional data.

[1385] Step 12:

[1386] The device collects feedback data from users and sends it to the server, which uses this feedback to improve the strategy generation process and provide more accurate advice in the future.

[1387] Through this specific process, the system can provide content strategies that take into account the user's emotional state and effectively acquire audiences on each platform.

[1388] Example 2

[1389] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1390] Conventional content strategy generation systems were able to generate strategies based on the analysis of viewing data, but were unable to generate strategies that took into account viewer emotions. As a result, strategies that did not reflect viewer reactions or emotions resulted in the provision of less than optimal content. Furthermore, strategies that took into account the characteristics of each platform across multiple digital platforms were not sufficiently generated.

[1391] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting viewing data, a means for converting the collected viewing data into a unified format and analyzing it, a means for collecting user facial expression and voice data and recognizing emotions, a means for generating an optimal content strategy for each platform based on the analysis results and emotion data, a means for notifying the user of the generated content strategy on the user's terminal and visually displaying it, and a means for collecting feedback data from the user and reflecting it in future strategy generation. This makes it possible to generate a more accurate content strategy that takes into account not only viewing data but also viewer emotions. It is also possible to provide a strategy that takes into account the characteristics of each platform.

[1392] "Viewing data" refers to data including the number of views on digital platforms, viewing time, viewing completion rate, viewer attributes, number of likes and comments, etc.

[1393] The "unified format" is a data format that converts viewing data collected from multiple digital platforms into a format that is easy to analyze.

[1394] "Facial expression data" refers to data relating to the facial expressions of a user captured through a webcam.

[1395] "Voice data" refers to data relating to the user's speech or voice acquired through a microphone.

[1396] "Emotion recognition" means analyzing facial expression data and voice data to identify the user's emotional state (for example, joy, sadness, surprise, etc.).

[1397] The "analysis results" are analysis results based on viewing data and emotional data, and indicate the behavioral patterns and emotional tendencies of viewers.

[1398] "Content strategy" refers to the type, content, timing, etc. of content posted on digital platforms.

[1399] A "user terminal" is a device (e.g., a PC, a smartphone, a tablet, etc.) that visually displays strategic data and collects feedback from users.

[1400] "Feedback data" refers to data provided by users that includes opinions, results, and sentiment data regarding content strategies.

[1401] This invention is a system that collects and analyzes viewing data to generate optimal content strategies for each platform. Furthermore, by combining it with an emotion engine that recognizes user emotions, it provides a more accurate content strategy.

[1402] server

[1403] 1. Collection of viewing data:

[1404] The server obtains viewing data from digital platforms such as YouTube and TikTok through APIs, using OAuth for authentication, and collects data such as the number of views, viewer attributes, viewing time, completion rate, likes, and comments.

[1405] 2. Data Analysis:

[1406] The server uses Python's pandas library to convert the collected viewing data into a unified format, then analyzes the data using machine learning algorithms such as scikit-learn to identify patterns in viewer behavior.

[1407] 3. Emotion Recognition with Emotion Engine:

[1408] The server collects facial and voice data from the user's device in real time and recognizes emotions. It uses the OpenCV library to analyze facial data and the Google Cloud Speech-to-Text API to analyze voice data.

[1409] 4. Performance evaluation and strategy generation:

[1410] The server evaluates the performance of each platform based on viewing data analysis and sentiment data, and then uses a generative AI model to generate the optimal content strategy for each platform.

[1411] 5. Strategic Notification:

[1412] The server sends the generated strategy to the user's device, where it is visually displayed in a dashboard format using a front-end framework such as React.js.

[1413] 6. Feedback Collection:

[1414] The server collects feedback from users, including viewing data and emotional data, and reflects this feedback in future strategy generation.

[1415] Terminal

[1416] 1. Receiving and displaying the strategy:

[1417] The terminal receives strategy data from the server and displays it to the user in a dashboard format, allowing the user to visually grasp specific advice for each platform.

[1418] 2. Collecting Emotional Data:

[1419] The device collects the user's facial expressions and voice data through a webcam and microphone and transmits it to a server in real time.

[1420] User

[1421] 1. Strategy Implementation:

[1422] Users follow the content strategy provided by the server to post content appropriate for each platform, for example, posting long videos to YouTube and short videos to TikTok.

[1423] 2. Emotion-based regulation:

[1424] Based on real-time feedback from the server, users can adjust the direction of their content. When the emotion engine recognizes the user's satisfaction, it automatically adjusts the strategy.

[1425] 3. Providing Feedback:

[1426] After posting content, users send feedback including performance data and emotional data to the server, which then acquires the data necessary for generating the next strategy.

[1427] Specific examples

[1428] For example, User B distributes videos on YouTube and TikTok. The server analyzes the viewing data obtained from User B and User B's emotional data during distribution (e.g., emotion recognition data from facial expressions and voice). Based on the analysis results, the server generates a content strategy that recommends long explanatory videos on YouTube and short, entertaining skits on TikTok. User B follows this strategy and posts long videos on YouTube and short videos on TikTok. The viewing data and emotional data after posting are then sent to the server as feedback, which the server uses to generate the next strategy.

[1429] For example, here is an example of a prompt to input to a generative AI model:

[1430] "If the average watch time of viewers on YouTube is increasing, what type of video should I post next?"

[1431] As a result, this system can provide highly accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement on each platform.

[1432] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1433] Step 1:

[1434] The server connects to the API of each digital platform (e.g., YouTube, TikTok) to collect viewing data. The server performs OAuth authentication using the API key and secret key, and sends an HTTP request to obtain viewing data (number of views, viewer attributes, viewing time, viewing completion rate, number of likes, number of comments, etc.) from the data endpoint. The input data is the API endpoint URL and authentication information, and the output is viewing data in JSON format.

[1435] Step 2:

[1436] The server converts the acquired viewing data into a unified format. Specifically, it uses the Python pandas library to convert raw data into data frame format. The input of this step is viewing data in JSON format, and the output is viewing data in a unified format (data frame format).

[1437] Step 3:

[1438] The server analyzes the converted viewing data to identify patterns and trends in viewer behavior. Specifically, it uses a scikit-learn clustering algorithm to identify viewer behavior patterns. The input to this step is viewing data in a data frame format, and the output is clustered viewer behavior patterns.

[1439] Step 4:

[1440] The device uses a webcam and microphone to collect the user's facial and voice data and transmits it to the server in real time. The input is the user's real-time facial and voice data, and the output is raw emotion data sent to the server.

[1441] Step 5:

[1442] The server analyzes the facial and voice data sent from the device to identify the user's emotions. Specifically, it uses the OpenCV library to analyze the facial data and the Google Cloud Speech-to-Text API to analyze the voice data. The input of this step is the raw emotion data sent from the device, and the output is the analyzed emotion data.

[1443] Step 6:

[1444] The server combines the analysis results of the viewing data with the emotion data to evaluate the performance of each platform. The analysis results and emotion data are integrated to calculate a performance index for each platform. The input is the clustered viewing data and the analyzed emotion data, and the output is a performance index for each platform.

[1445] Step 7:

[1446] The server uses a generative AI model to generate the optimal content strategy for each platform, for example suggesting long-form explainer videos for YouTube and short, fun skits for TikTok. The input for this step is performance metrics, and the output is the optimal content strategy for each platform.

[1447] Step 8:

[1448] The server sends the generated strategy data to the user's device, which then visually displays it. The device uses React.js to display the strategy in a dashboard format and provide specific advice to the user. The input of this step is the generated content strategy, and the output is the visual advice on the dashboard.

[1449] Step 9:

[1450] The user posts content appropriate for each platform according to the content strategy provided by the server. Specifically, the user posts long videos to YouTube and short videos to TikTok. The input of this step is the content strategy, and the output is the content posted to each platform.

[1451] Step 10:

[1452] After posting content, users collect performance and emotion data and send it to the server. The feedback data includes viewing data and user emotion data. The input of this step is performance data and emotion data, and the output is feedback data sent to the server.

[1453] Step 11:

[1454] The server analyzes the feedback data collected from users and reflects it in the next strategy generation. The feedback data is stored in a database and used for future strategy generation. The input of this step is the feedback data, and the output is the analyzed feedback information.

[1455] (Application example 2)

[1456] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1457] Content distribution on modern digital platforms requires analyzing user viewing data and generating optimal content strategies for each platform. However, current systems rely on analyzing viewing data and lack the ability to generate strategies that take into account the user's emotional state. This makes it difficult to provide individually optimized strategies that reflect user feedback and emotional changes in real time.

[1458] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting viewing data, means for analyzing the collected viewing data and evaluating performance for each platform, means including an emotion engine for collecting and analyzing user emotion data, means for generating an optimal content strategy for each platform based on the analysis results and the emotion data, means for notifying users of the generated content strategy, and means for collecting feedback from users and reflecting it in future strategy generation. As a result, by combining and analyzing viewing data and user emotion data, it is possible to generate an individually optimal content strategy in real time and maximize user engagement.

[1459] "Viewing data" refers to information such as the number of viewers of content on digital platforms, viewing time, completion rate, number of likes and comments, etc.

[1460] An "emotion engine" refers to a system that analyzes a user's facial expressions and voice data to identify the user's emotional state in real time.

[1461] "Server" refers to the core processing system that collects and analyzes viewing and sentiment data to generate and inform optimal content strategies for each platform.

[1462] "Platform performance" is a metric that shows how successful content is on each digital platform and encompasses multiple factors such as number of views, viewing time, and engagement rate.

[1463] "Content strategy" refers to a plan that uses viewing and sentiment data to suggest the most appropriate type of content and posting timing for each platform.

[1464] "Feedback" refers to information provided by users, including their reactions and impressions after viewing content, viewing data, and emotional data.

[1465] The present invention provides a system that combines an emotion engine that collects and analyzes viewing data and recognizes the user's emotions. Specific embodiments of this system will be described below.

[1466] System configuration

[1467] server

[1468] The server includes the following means:

[1469] 1. Collection of viewing data:

[1470] The server retrieves viewing data from the API endpoints of each digital platform (e.g., video platform), including the number of views, viewer attributes, viewing time, completion rate, number of likes and comments, etc.

[1471] 2. Data Analysis:

[1472] The raw data is then converted into a unified format and analyzed to identify patterns and trends in viewer behavior using statistical methods and machine learning algorithms.

[1473] 3. Emotion Recognition with Emotion Engine:

[1474] The server uses an emotion engine to analyze facial and voice data from the user's device to identify the user's emotions, for example, using emotion recognition models built with TensorFlow and Keras.

[1475] 4. Performance evaluation and strategy generation:

[1476] We evaluate the performance of each platform based on the results of viewing data analysis and user sentiment data, and then generate the optimal content strategy for each platform based on the evaluation results.

[1477] 5. Strategic Notification:

[1478] The server sends the generated strategies to the user's terminal via the Internet, where they are visually displayed in a user-friendly dashboard format.

[1479] 6. Feedback Collection:

[1480] Feedback data from users is collected and reflected in future strategy generation. Since the feedback includes emotional data, the data collected by the emotion engine is also taken into account.

[1481] Terminal

[1482] The terminal includes the following means:

[1483] 1. Receiving and displaying the strategy:

[1484] The device receives the content strategy sent from the server and provides specific advice in the form of a dashboard.

[1485] 2. Collecting Emotional Data:

[1486] The smartphone's camera and microphone are used to collect the user's facial expressions and voice data, which are then sent to a server, allowing the user's emotions to be identified in real time.

[1487] User

[1488] The user includes the following means:

[1489] 1. Strategy Implementation:

[1490] Users post content to each platform based on the content strategy provided by the server. For example, users can post long videos to YouTube and short videos to TikTok to increase viewer engagement.

[1491] 2. Emotion-based regulation:

[1492] It adjusts content direction based on real-time feedback from the server. For example, if the emotion engine detects that the user is dissatisfied, it automatically adjusts its strategy.

[1493] 3. Providing Feedback:

[1494] The results after posting content are collected and feedback, including emotional data, is sent to the server, which then obtains the data necessary for future strategy generation.

[1495] Specific examples

[1496] The following is a specific example:

[1497] Example of viewing data obtained from the platform: "Average viewing time 320 seconds, 15,000 views, 120 comments"

[1498] Example of user sentiment analysis result: "Emotion 'happy', probability 0.85"

[1499] Example prompt for a generative AI model: "Generate the optimal content strategy based on viewing data and sentiment data. Viewing data: average viewing time 320 seconds, 15,000 views, 120 comments. Sentiment data: sentiment 'happy', probability 0.85."

[1500] In this way, the system can provide more accurate content strategies based on user sentiment, helping to maximize audience acquisition and engagement across platforms.

[1501] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1502] Step 1:

[1503] Collecting viewing data

[1504] The server collects viewing data from each digital platform. Specifically, it accesses API endpoints such as YouTube and TikTok to obtain data such as the number of views, viewer attributes, viewing time, viewing completion rate, number of likes and comments, etc. The server receives raw data from the platforms as viewing data as input and outputs it as a data list.

[1505] Step 2:

[1506] Data analysis

[1507] The server converts the collected viewing data into a unified format and analyzes it. It uses statistical methods and machine learning algorithms to identify viewer behavior patterns and trends. Specifically, it calculates indicators such as viewing time distribution and engagement rate, and generates the analysis results as output.

[1508] Step 3:

[1509] Collecting Emotional Data

[1510] The device uses the smartphone's camera and microphone to collect the user's facial and voice data and transmits that data to a server. Specifically, when the user uses the app, the camera and microphone are activated, capturing facial and voice data in real time and transmitting it to the server. In this process, raw data obtained from the camera and microphone is input and output as emotion data.

[1511] Step 4:

[1512] Emotion Analysis

[1513] The server analyzes the received facial and voice data to identify the user's emotions. This analysis uses an emotion recognition model built with TensorFlow or Keras, for example. Specifically, image processing technology is used to extract facial features and classify emotions based on those features. This outputs emotion labels and their probabilities as analysis results.

[1514] Step 5:

[1515] Performance Evaluation and Strategy Generation

[1516] The server evaluates the performance of each platform based on the analysis of viewing data and emotional data, and generates an optimal content strategy. Specifically, it evaluates the viewing data and user emotional state for each platform, and generates the most efficient content strategy from the evaluation results using an AI model. The generated content strategy is then output.

[1517] Step 6:

[1518] Strategic Notification

[1519] The server notifies the user of the generated content strategy. Specifically, the strategy data is sent via the Internet and visualized in a dashboard format on the user's device. This notification allows the user to easily understand the strategy.

[1520] Step 7:

[1521] Implementing strategies and gathering feedback

[1522] Users post content to each platform based on the content strategy provided by the server. After posting, users provide feedback to the server, including viewing data and emotional data. Specifically, the number of views and comments on the posted video, as well as the user's own emotional state, are sent as input to the server, which then reflects this in future strategy generation.

[1523] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1524] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1525] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1526] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1527] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1528] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1529] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1530] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1531] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1532] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1533] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1534] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1535] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1536] 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.

[1537] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1538] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1539] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1540] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1541] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1542] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1543] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1544] The following is further disclosed regarding the above embodiment.

[1545] (Claim 1)

[1546] a means for collecting viewing data;

[1547] A means of analyzing the collected viewing data and evaluating performance on each platform,

[1548] A means for generating optimal content strategies for each platform based on the analysis results;

[1549] a means for informing users of the generated content strategy;

[1550] A means for collecting user feedback and incorporating it into future strategy generation;

[1551] A system including:

[1552] (Claim 2)

[1553] 10. The system of claim 1, wherein viewing data is collected from multiple digital platforms via the Internet.

[1554] (Claim 3)

[1555] The system of claim 1, wherein the results of the viewing data analysis are taken into account to generate different content strategies for each platform.

[1556] "Example 1"

[1557] (Claim 1)

[1558] a means for collecting viewing data;

[1559] A means for converting collected viewing data into a unified format and performing data cleansing;

[1560] A means of analyzing the viewing data after data cleansing to identify viewer behavior patterns and trends;

[1561] A means to evaluate the performance of each platform based on the analysis results, and

[1562] A means of generating optimal content strategies for each platform using generative AI models; and

[1563] A means of communicating the generated content strategy to users in a user-friendly dashboard format; and

[1564] A means for collecting user feedback and incorporating it into future strategy generation;

[1565] A system including:

[1566] (Claim 2)

[1567] 10. The system of claim 1, wherein the system collects viewing data from multiple digital platforms via the internet and sends API requests to retrieve the viewing data.

[1568] (Claim 3)

[1569] The system of claim 1, wherein the results of viewing data analysis are taken into account to generate different content strategies for each platform using the natural language generation capabilities of the generative AI model.

[1570] "Application Example 1"

[1571] (Claim 1)

[1572] a means for collecting viewing data;

[1573] A means of analyzing the collected viewing data and evaluating performance on each platform,

[1574] A means for generating optimal content strategies for each platform based on the analysis results;

[1575] a means for informing users of the generated content strategy;

[1576] A means for collecting user feedback and incorporating it into future strategy generation;

[1577] a means for providing a user interface optimized for smartphones and visually displaying advice;

[1578] A means to continuously optimize and update machine learning models based on feedback data.

[1579] A system including:

[1580] (Claim 2)

[1581] 10. The system of claim 1, wherein viewing data is collected from multiple digital platforms via the Internet.

[1582] (Claim 3)

[1583] The system of claim 1, wherein the results of the viewing data analysis are taken into account to generate different content strategies for each platform.

[1584] "Example 2: Combining Emotion Engines"

[1585] (Claim 1)

[1586] a means for collecting viewing data;

[1587] A means of converting the collected viewing data into a unified format and analyzing it;

[1588] A means for collecting facial expression and voice data of a user and recognizing emotions;

[1589] A means for generating optimal content strategies for each platform based on the analysis results and sentiment data;

[1590] A means for notifying the generated content strategy to a user's terminal and visually displaying it;

[1591] A means for collecting feedback data from users and reflecting it in future strategy generation;

[1592] A system including:

[1593] (Claim 2)

[1594] 10. The system of claim 1, wherein viewing data is collected from multiple digital platforms via the Internet and emotion data is collected in real time from a user's device.

[1595] (Claim 3)

[1596] The system of claim 1, wherein the results of the viewing data analysis and the sentiment data are taken into consideration to generate different content strategies for each platform.

[1597] "Application example 2 when combining emotion engines"

[1598] (Claim 1)

[1599] a means for collecting viewing data;

[1600] A means of analyzing the collected viewing data and evaluating performance on each platform,

[1601] means for collecting and analyzing user emotion data, the emotion engine comprising:

[1602] A means for generating optimal content strategies for each platform based on the analysis results and sentiment data;

[1603] a means for informing users of the generated content strategy;

[1604] A means for collecting user feedback and incorporating it into future strategy generation;

[1605] A system including:

[1606] (Claim 2)

[1607] 10. The system of claim 1, wherein viewing data is collected from multiple digital platforms via the Internet, and emotion data is collected from users using an emotion engine.

[1608] (Claim 3)

[1609] The system of claim 1, wherein the results of the viewing data analysis and sentiment data are taken into account to generate different content strategies for each platform. [Explanation of symbols]

[1610] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting viewing data; A means of analyzing the collected viewing data and evaluating performance on each platform, A means for generating optimal content strategies for each platform based on the analysis results; a means for informing users of the generated content strategy; A means for collecting user feedback and incorporating it into future strategy generation; A system including:

2. 10. The system of claim 1, wherein the system collects viewing data from multiple digital platforms via the Internet.

3. The system of claim 1 , wherein the results of the analysis of viewing data are taken into account to generate different content strategies for each platform.

Images