system

Abstract

We provide the system. [Solution] Means of collecting user data, A means for analyzing the user data using natural language processing, Methods for collecting and analyzing trend data, A means for generating advice for content creation based on the aforementioned user data and trend data, Means for providing the aforementioned advice to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Influencers and content creators are required to continuously send attractive content that incorporates trends while maintaining their unique personalities in order to increase their influence. However, to achieve this, it is necessary to effectively analyze past posting and reaction data and receive strategic advice based on the latest trends. However, it is difficult for all creators to conduct such analysis on their own, and as a result, there is a risk of falling into mass-produced content. The present invention aims to provide a system that provides accurate advice on content creation based on a user's past data and trend data in order to solve such problems.

Means for Solving the Problems

[0005] This invention relates to a system that includes means for collecting user data and analyzing it using natural language processing, and further includes means for collecting and analyzing trend data. This allows the system to identify success factors based on information obtained from users' past posts and reactions, and to generate strategic content creation advice aligned with current trends. The generated advice is provided to the user and presented in a visualized format, enabling the user to effectively create influential content that aligns with trends while leveraging their own individuality.

[0006] "User data" refers to information related to user activity on social media, such as the content of posts, posting dates and times, number of likes, and comments.

[0007] "Natural language processing" refers to the techniques used by computers to understand, analyze, and generate human language, and specifically to techniques used for analyzing text data.

[0008] "Trend data" refers to information that shows the latest trends and interests related to a specific field or content over a specific period of time.

[0009] "Means for generating advice" refers to a method or apparatus for automatically generating advice on content creation and strategic communication directed at users, based on user data and trend data.

[0010] "Means of visualization" refers to methods or devices for presenting generated advice in a visual format, such as diagrams or graphs, in a way that is easy for the user to understand. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] The system of this invention consists of a server, a terminal, and a user. The server is primarily responsible for collecting and analyzing user data, collecting trend data, and generating advice. The terminal presents visualized advice to the user, and the user utilizes the provided advice based on their own activities.

[0033] Specifically, the server first collects text data from the user's posting history, as well as reaction data such as reactions and comments. The collected data is analyzed using natural language processing techniques to extract success factors and characteristics in the user's activities. At the same time, the server collects relevant trend data from external social media platforms and news sites to identify current trends.

[0034] Next, the server generates content creation advice tailored to the user based on the collected and analyzed data. This advice may include specific post content, posting timing, and recommended keywords and hashtags. The generated advice is then provided to the user via their device.

[0035] The terminal visualizes the advice received from the server using a graphical interface such as a dashboard, making it easy for users to understand. Based on the advice provided, users can plan and implement more impactful content strategies while leveraging their individuality. Users can also send feedback to the server, and the system uses this feedback to further improve the advice.

[0036] For example, in the case of a user who posts about fashion, the server analyzes the user's past posts and reaction data to determine that outfits using natural materials were popular. Furthermore, it identifies that "sustainable fashion" is gaining attention based on current trend data. The user is then advised to "post outfits using sustainable materials on weekend afternoons." In this way, users can create effective content that incorporates trends while maintaining their individuality.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The server accesses the user's past posting database and collects user data such as post content, posting date and time, number of likes, and content and number of comments. The collected data is structured and prepared for analysis.

[0040] Step 2:

[0041] The server analyzes user data collected using natural language processing (NLP) techniques. Specifically, it performs text tokenization, stemming, and rooming to clean the text. Then, it extracts recurring themes and topics from user posts.

[0042] Step 3:

[0043] The server performs sentiment analysis based on reaction data, evaluating positive, negative, and neutral responses. This helps identify which posts are particularly engaging and successful.

[0044] Step 4:

[0045] The server uses APIs from external social media platforms and related news sites to collect trending data. It retrieves specific keywords, hashtags, and trending topics to analyze current trends.

[0046] Step 5:

[0047] The server generates content creation advice tailored to the user based on the analysis results. It combines the user's past success factors with current trends to determine the theme of a new post, the optimal posting time, the hashtags to use, and the recommended format (video, image, text, etc.).

[0048] Step 6:

[0049] The server sends the generated advice to the terminal, which visualizes and displays it on a dashboard. Users can intuitively understand the advice and use it to plan their next content.

[0050] Step 7:

[0051] Users post content based on the advice they receive. They also send feedback to the server via their device to improve the service, which the system uses to enhance the accuracy of future advice.

[0052] (Example 1)

[0053] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0054] Conventional information gathering and analysis systems have struggled to effectively utilize information on user activities and trends, and to provide content creation support tailored to individual needs. As a result, users have been unable to obtain the information and advice necessary to create and disseminate content quickly and accurately.

[0055] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0056] In this invention, the server includes means for collecting information about users, means for analyzing said information using natural language processing, and means for collecting and analyzing information on current trends. This makes it possible to quickly and accurately provide users with advice for creating individually optimized content.

[0057] "User information" refers to data including user behavior, preferences, posting history, and reactions to those postings.

[0058] "Natural language processing" refers to the technology of using computers to analyze, understand, and generate human language.

[0059] "Information on trends" refers to data about topics or subjects that attract widespread interest at a particular time.

[0060] "Advice" refers to specific suggestions, recommendations, or guidance that are helpful to users when creating content.

[0061] "Means" refers to technical methods, devices, or techniques used to achieve a specific objective.

[0062] The system of this invention mainly consists of a server, a terminal, and a user. The server is responsible for collecting and analyzing user-related data and combining it with external trend information to generate advice for creating content suitable for the user. Specifically, the server uses APIs to collect user posting history, reaction data, comments, etc., from social media platforms and news sites. It also collects external trend information and stores it in a database.

[0063] The server applies natural language processing techniques to the collected data to analyze important keywords and user sentiment. It uses Sentiment Analysis and Keyword Extraction algorithms to identify the success factors of user content. Furthermore, it analyzes trend information and uses machine learning models to identify current trends. The models utilize specific APIs and natural language processing libraries (e.g., TENSORFLOW® and NLTK).

[0064] Based on the generated data, the server uses a generation AI model to generate advice for creating content for the user. For example, a prompt might be sent to the AI ​​in the form of, "Suggest the optimal solution for fashion posts based on past success stories," to obtain specific suggestions.

[0065] The generated advice is provided to the user via a terminal. The terminal has a user interface designed to present the advice in a visually easy-to-understand format. The information is displayed in a dashboard format and designed to be intuitively understandable to the user. Based on this advice, the user plans and creates new content. Furthermore, the user can contribute to system improvement by sending feedback to the server through a feedback function. This feedback is used to continuously improve the quality of the advice provided by the system.

[0066] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0067] Step 1:

[0068] The server uses APIs to collect user data such as user posting history, reaction data, and comments from social media platforms and news sites. Inputs include user account information and social media URLs, while output is a set of user information stored in a database. JavaScript® and Python are used for data crawling and API calls.

[0069] Step 2:

[0070] The server performs analysis by applying natural language processing techniques to the collected user data. In this step, Sentiment Analysis and Keyword Extraction are performed using the user data stored as input. The output is the user's sentiment score and a list of extracted keywords. Libraries such as TensorFlow and NLTK are used to analyze the data.

[0071] Step 3:

[0072] The server collects and analyzes information about current trends from external sources. In this step, the input is online data such as news articles and trends, and the output is trending topics and related keywords. Machine learning is used to automatically extract frequently occurring topics and keywords. Web scraping is performed using Python to collect data.

[0073] Step 4:

[0074] The server uses a generative AI model to generate advice for creating optimal content for the user. The input is the analysis results obtained in steps 2 and 3, and the output is advice that includes specific suggestions. The generative AI model is given the prompt, "Suggest the optimal solution for fashion posts based on past success stories," and generates specific ideas.

[0075] Step 5:

[0076] The terminal receives generated advice and visualizes and presents it in a user-friendly format. The input is the advice received from the server, and the output is a dashboard or graphical interface that the user can view. Front-end technologies using JavaScript and HTML / CSS are used to organize and display the information.

[0077] Step 6:

[0078] The user creates content based on the provided advice and returns feedback on the results to the server. The input is the results and opinions of the actions the user has taken, and the output is data stored on the server as feedback information. This allows the system to improve the accuracy of future advice.

[0079] (Application Example 1)

[0080] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0081] In today's information society, individual information providers need to formulate optimal information dissemination strategies based on their past communication history and the reactions of their recipients. However, there is a lack of technology to effectively analyze past information and current trends and generate personalized advice. As a result, many information providers are unable to obtain appropriate guidance and are unable to maximize their influence.

[0082] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0083] In this invention, the server includes means for collecting user information, means for analyzing the user information using natural language processing, and means for collecting and analyzing trending data. This enables users to receive optimal guidance based on their past communication history and trends, and to further formulate personalized information dissemination strategies.

[0084] "User information" refers to data that includes the past content of information providers and the responses of recipients.

[0085] "Natural language processing" is a technology that allows computers to analyze and understand human language, and in this invention, it is used to analyze user information.

[0086] "Current trends data" refers to a collection of information that indicates current fashions and trends in society and the market.

[0087] "Guidelines" are specific advice and suggestions that users should follow to optimize their information dissemination.

[0088] A "personalized information dissemination strategy" is an effective and efficient information dissemination plan that users develop based on their own characteristics and needs.

[0089] This invention is a system consisting of a server that collects and analyzes information, a terminal that presents the information, and a user who ultimately utilizes the information.

[0090] The server collects user information and performs analysis using natural language processing. This allows for a detailed analysis of users' past information sharing and responses, and the extraction of success factors. Furthermore, the server collects trending data from external sources to identify current trends and fads. In this process, the server uses natural language processing technology based on TensorFlow and additional APIs (such as Google® Cloud Vision API) to process text and image data.

[0091] Based on the analysis results, the server generates personalized information dissemination guidelines for each user. These guidelines may include specific information content and timing. The generated guidelines are visualized in an easy-to-understand format and sent to the user's device. The device displays these guidelines in a dashboard format to assist the user in formulating their own information dissemination strategy.

[0092] Users build their own information dissemination strategies based on the provided guidelines and implement optimal information dissemination. For example, if a user is disseminating information about travel, analysis might reveal that past posts with a sea theme were popular, and that beach resorts are currently trending. Based on this information, the server generates specific guidelines such as "It would be good to post information with a beach resort theme next weekend" and presents them to the user via their device.

[0093] An example of a prompt in a generative AI model would be: "The user's past posts often include images of beaches, which are very popular. Furthermore, beach resorts are currently trending. Based on this information, please provide the user with the best guidance for their next post."

[0094] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0095] Step 1:

[0096] The server collects user information. This information includes past posts, browsing history, and reaction data (such as "likes" and comments). This information is collected on the server as input data, and a dataset for analysis is prepared as output. Specifically, a database management system is used to obtain log data regarding user behavior.

[0097] Step 2:

[0098] The server analyzes user information using natural language processing. The input is the dataset prepared in Step 1, and natural language processing techniques (e.g., TensorFlow) are applied to identify user interests and success factors. The output is user behavioral characteristics based on the analysis. Specifically, text analysis is performed to identify frequently occurring words and sentiment analysis.

[0099] Step 3:

[0100] The server collects trending data from external sources. It obtains trend information using web scraping and APIs as input and transfers it to the server. The output is a dataset showing current trends. Specifically, it obtains trending information from the Twitter API and news feeds.

[0101] Step 4:

[0102] The server integrates user information and trending data to generate guidelines. The input combines user characteristics from step 2 and trending data from step 3, and uses a generative AI model to create optimal guidelines. The output is specific advice regarding particular information dissemination. Specifically, the generative model might suggest, "It would be good to disseminate information with a beach resort theme next weekend."

[0103] Step 5:

[0104] The terminal visualizes the guidelines received from the server and presents them to the user. The input is the guideline information generated in step 4, and the output is a dashboard that the user can view. Specifically, the guidelines are displayed on a web interface or mobile app and designed to be easily understood by the user.

[0105] Step 6:

[0106] Users optimize their information dissemination strategy based on the provided guidelines. They receive the guidelines provided in Step 5 as input and develop their own information dissemination plan as output. Specifically, users adjust their content creation and posting schedules according to the guidelines and disseminate new information at the appropriate time.

[0107] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0108] This invention is a system that provides users with more personalized content creation advice by utilizing user-submitted data and trend data, and further combining them with an emotion engine. This system consists of a server, terminals, and users, with the server primarily handling data collection, analysis, and advice generation, and the terminals visualizing the advice.

[0109] The server first accesses the user's past posting database to collect user data such as post content, posting time, number of likes, and comment data. In this process, the data is structured and prepared for use with the sentiment engine. Next, analysis is performed using natural language processing techniques to analyze not only the theme and topic of each post, but also the emotional aspects (positive, negative, neutral) contained in the post using the sentiment engine.

[0110] Furthermore, the server collects trend data from external social media platforms and relevant information sources and analyzes recent trends. Based on this trend data, along with analyzed user data and sentiment data, it generates content creation advice optimized for each individual user. Specifically, it suggests content styles and themes that promote specific emotions, based on the user's past success factors and current emotional state.

[0111] The generated advice is sent to the device and provided to the user. The device visualizes this information on a dashboard, allowing users to immediately use it in their daily creative activities. The visualized advice also shows emotional outcomes, allowing users to plan posts that align with their emotional state.

[0112] As a concrete example, let's say there's a user who primarily posts about travel. The server analyzes that "landscape photos" in that user's posts elicit particularly positive emotional responses. Combining this with trend data, it generates advice that posting about travel destinations and experiences themed around "relaxation" would be effective. In this way, users can effectively create content that incorporates the latest trends while being mindful of their strengths and the emotional impact they have on others.

[0113] The following describes the processing flow.

[0114] Step 1:

[0115] The server accesses the user's posting history database and collects user data such as post content, posting date and time, number of likes, and comment content. This data collection process converts the data into an appropriate format for preparation for natural language processing and sentiment analysis.

[0116] Step 2:

[0117] The server uses natural language processing (NLP) techniques to analyze the collected user data. After tokenizing the text data and performing stemming and rooming, it analyzes which themes and topics are most frequent. It also uses a sentiment engine to automatically determine the sentiment (positive, negative, neutral) embedded in each post.

[0118] Step 3:

[0119] The server collects current trend data from external social media platforms and specialized content sites, identifying particularly noteworthy topics, popular keywords, and hashtags.

[0120] Step 4:

[0121] The server generates personalized content creation advice based on analyzed user data and trend data. Leveraging sentiment analysis results from the sentiment engine, it suggests posting styles and themes tailored to the emotions the user wants to evoke. It also determines the appropriate timing and format for posting (e.g., text, images, videos).

[0122] Step 5:

[0123] The server sends the generated advice to the terminal, which then presents it to the user in a visualized format. The user can easily understand and utilize the provided advice through a graphical interface such as a dashboard.

[0124] Step 6:

[0125] Based on the advice provided, users plan their next content and actually post it. They can also send feedback to the server via their device, which allows for continuous improvement of the quality of the advice.

[0126] (Example 2)

[0127] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0128] Current information generation systems face challenges in creating information tailored to the individual needs of users and insufficient provision of effective content guidelines based on emotions and trends.

[0129] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0130] In this invention, the server includes means for collecting information, means for analyzing the information using natural language processing, and means for collecting and analyzing external data. This makes it possible to provide guidelines that are suitable for the user's needs and to generate effective information.

[0131] "Means of collecting information" refers to a system that aggregates a user's past communication content and related data, and accesses a database to obtain the necessary information.

[0132] "Means for analyzing the information using natural language processing" refers to a technical method that processes the acquired information using a computer and automatically analyzes the theme and emotions of the content.

[0133] "Methods for collecting and analyzing external data" refers to techniques for obtaining trends and related data from various sources on the internet, organizing and classifying them, and understanding current trends.

[0134] "Means for creating guidelines for information generation based on analyzed information and external data" refers to an algorithm that combines collected information and trend data to propose the most suitable information creation policy for the user.

[0135] "Means of providing generated guidelines to users" refers to a mechanism for presenting the created guidelines to users visually or by other means, so that they can be used in actual information generation activities.

[0136] "Means for analyzing users' responses to communications and identifying the factors for information success" refers to the process of analyzing users' evaluations and responses to past communications and extracting the factors for their success.

[0137] "Means of visualizing the aforementioned guidelines and presenting them in a format that is easy for users to understand" refers to a method of visually displaying the generated information generation guidelines using graphs, tables, charts, etc., and providing them in a format that users can easily understand and utilize.

[0138] A description of the embodiment for carrying out the invention will be provided.

[0139] This invention is a system for providing users with personalized information generation guidelines. This system consists of three components: a server, a terminal, and a user.

[0140] The server first collects the user's past communication data. This data collection uses an API to connect to a database and a program to execute SQL queries to manipulate the database. This program is implemented in a scripting language such as Python. Next, the server uses natural language processing techniques to analyze the user's communication content. Specifically, it uses libraries such as NLTK and SpaCy to tokenize text and classify sentiment. It can also utilize external sentiment analysis tools such as the Google Cloud Natural Language API.

[0141] Next, the server collects trend data from external sources. This involves using web scraping tools such as Beautiful Soup or Selenium to obtain real-time trend information. The collected user data and trend data are then integrated, and a generative AI model is used to create guidelines for information generation. Ideally, a sophisticated natural language generation model, such as GPT-4 (registered trademark), should be used for this purpose. An example of a prompt used here might be, "Based on past successes and current trends, propose guidelines for generating information that will have a positive impact on users."

[0142] The generated guidelines are sent from the server to the terminal, where the terminal visualizes this information. JavaScript libraries such as D3.js and Chart.js are used for visualization, displaying it as a dashboard. This allows users to easily understand the guidelines and utilize them in their own information generation activities.

[0143] Based on the provided guidelines, users generate new information and send feedback to the server. This feedback is used to improve future guideline generation. Through this process, the system can continuously provide users with valuable guidelines and improve the quality of information generation.

[0144] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0145] Step 1:

[0146] The server accesses the user database and collects the user's past communication data. The input to this process is a specific user ID, and the output is a collection of various data such as the user's posts, comments, and number of reactions. SQL queries are used to extract information from the database, and data retrieval is automated using a Python script.

[0147] Step 2:

[0148] The server analyzes the collected data using natural language processing techniques. The input is the text data obtained in step 1, and the output is the results of topic and sentiment analysis. Libraries such as NLTK and SpaCy are used to tokenize and analyze the text, and sentiment labels such as positive, negative, and neutral are assigned.

[0149] Step 3:

[0150] The server collects trend data from external sources. The input to this process is target keywords and hashtags, and the output is a dataset of trend information. Web pages are scraped using Beautiful Soup and Selenium to obtain trend information in real time.

[0151] Step 4:

[0152] The server uses analyzed user data and trend data to input prompts into a generative AI model, creating guidelines for information generation. The input consists of user sentiment analysis results and trend data, while the output is specific guidelines that should be provided to the user. The generative AI model uses GPT-4 or similar technologies and is given the prompt, "Propose guidelines for generating information that will have a positive impact on the user."

[0153] Step 5:

[0154] The server sends the generated guidelines to the terminal. The terminal visualizes the received guidelines on a dashboard. The input is the guidelines generated from the server, and the output is the visualized information presented to the user. Libraries such as D3.js and Chart.js are used for visualization, displaying the guidelines in a user-friendly format.

[0155] Step 6:

[0156] Based on the provided guidelines, users send feedback to the server to generate information. The input consists of the user's evaluation and impressions after use, while the output is feedback data that helps improve the guidelines for the next cycle. This feedback is recorded in the server's database and used in the next cycle.

[0157] (Application Example 2)

[0158] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0159] With the increasing diversification of information distribution in modern times, there is a challenge in accurately suggesting information resources that match the individual interests and emotional states of users. In particular, there is a need to suggest information resources that take into account users' past successes and emotional responses, but conventional systems have found it difficult to achieve this efficiently.

[0160] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0161] In this invention, the server includes means for collecting user information, means for analyzing the user information using natural language processing, and means for collecting and analyzing trending information. This makes it possible to analyze the user's emotional state and suggest information resources that are appropriate to it.

[0162] "User information" refers to data related to a user, such as their past activity history, ratings, and comments.

[0163] "Natural language processing" is a technology that enables computers to understand and analyze text written by humans.

[0164] "Trend information" refers to data about topics or subjects that have gained widespread popularity within a specific period.

[0165] "Information resources" refers to all content and media that users can consume or utilize.

[0166] "Emotional state" refers to the user's emotions at that particular moment, inferred from their text data and other information.

[0167] To implement this invention, it is necessary to construct a system in which three elements—a server, a terminal, and a user—work in coordination.

[0168] The server is responsible for collecting user information and trending information, and analyzing the necessary data. User information includes past viewing history, ratings, and comments, which the server collects. Trending information is collected from external sources. Using this information, natural language processing is performed to analyze the user's emotional state. Based on this, the server generates advice to suggest the most suitable information resources. This process includes using sentiment analysis tools such as Amazon Comprehend and collecting trending information using the Twitter API.

[0169] The terminal plays a role in visualizing the advice sent from the server and presenting it in a format that is easy for the user to understand intuitively. This information is displayed on a dashboard designed, for example, using Flutter®, and suggests information resources tailored to the user's needs.

[0170] Users can select and utilize information resources that interest them based on the advice provided using their own devices. This allows users to enjoy content that matches their emotional state.

[0171] For example, if a movie-loving user is determined to be in a "relaxed" state through server analysis, new and trending movies, or works with a relaxing theme tailored to their mood, will be suggested to that user. Through this process, users can obtain the most suitable information resources for their current emotional state. It is possible to generate suggestions using a prompt such as, "Suggest relaxing movies based on the user's recent positive emotional state."

[0172] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0173] Step 1:

[0174] The server retrieves user information. Specifically, it collects user viewing history, ratings, and comments from the database. At this stage, the input is user information from the database, and the output is the collected structured data.

[0175] Step 2:

[0176] The server analyzes user information collected using natural language processing. This process utilizes Amazon Comprehend to extract emotional aspects from text data. The input is structured user information, and the output is analyzed data including emotional states. Specifically, it performs sentiment analysis on evaluation comments and assigns positive, negative, or neutral labels.

[0177] Step 3:

[0178] The server collects trending information from external sources. This step uses the Twitter API to retrieve the latest topics and trending data that users are interested in. The input is raw data from external sources, and the output is analyzable trending data. Specifically, trending keywords are extracted and stored in a database.

[0179] Step 4:

[0180] The server generates advice to suggest the most suitable information resources to the user, based on the analyzed user information and collected trend information. This process uses a generative AI model, taking a prompt as input and outputting the best suggestions. For example, it might use the prompt, "Based on the user's recent positive emotional state, please suggest a relaxing movie."

[0181] Step 5:

[0182] The terminal visualizes the advice received from the server. The input is the advice data sent from the server, and the output is a dashboard display that the user can visually confirm. Specifically, it is displayed on the interface using Flutter.

[0183] Step 6:

[0184] The user refers to visualized advice on the device, selects and uses information resources of interest based on that advice. This step primarily involves the user selecting the most suitable information resources; the input is visualized advice, and the output is actionable actions corresponding to the user's selection.

[0185] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0186] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0187] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0188] [Second Embodiment]

[0189] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0190] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0191] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0192] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0193] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0194] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0195] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0196] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0197] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0198] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0199] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0200] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0201] The system of this invention consists of a server, a terminal, and a user. The server is primarily responsible for collecting and analyzing user data, collecting trend data, and generating advice. The terminal presents visualized advice to the user, and the user utilizes the provided advice based on their own activities.

[0202] Specifically, the server first collects text data from the user's posting history, as well as reaction data such as reactions and comments. The collected data is analyzed using natural language processing techniques to extract success factors and characteristics in the user's activities. At the same time, the server collects relevant trend data from external social media platforms and news sites to identify current trends.

[0203] Next, the server generates content creation advice tailored to the user based on the collected and analyzed data. This advice may include specific post content, posting timing, and recommended keywords and hashtags. The generated advice is then provided to the user via their device.

[0204] The terminal visualizes the advice received from the server using a graphical interface such as a dashboard, making it easy for users to understand. Based on the advice provided, users can plan and implement more impactful content strategies while leveraging their individuality. Users can also send feedback to the server, and the system uses this feedback to further improve the advice.

[0205] For example, in the case of a user who posts about fashion, the server analyzes the user's past posts and reaction data to determine that outfits using natural materials were popular. Furthermore, it identifies that "sustainable fashion" is gaining attention based on current trend data. The user is then advised to "post outfits using sustainable materials on weekend afternoons." In this way, users can create effective content that incorporates trends while maintaining their individuality.

[0206] The following describes the processing flow.

[0207] Step 1:

[0208] The server accesses the user's past posting database and collects user data such as post content, posting date and time, number of likes, and content and number of comments. The collected data is structured and prepared for analysis.

[0209] Step 2:

[0210] The server analyzes user data collected using natural language processing (NLP) techniques. Specifically, it performs text tokenization, stemming, and rooming to clean the text. Then, it extracts recurring themes and topics from user posts.

[0211] Step 3:

[0212] The server performs sentiment analysis based on reaction data, evaluating positive, negative, and neutral responses. This helps identify which posts are particularly engaging and successful.

[0213] Step 4:

[0214] The server uses APIs from external social media platforms and related news sites to collect trending data. It retrieves specific keywords, hashtags, and trending topics to analyze current trends.

[0215] Step 5:

[0216] The server generates content creation advice tailored to the user based on the analysis results. It combines the user's past success factors with current trends to determine the theme of a new post, the optimal posting time, the hashtags to use, and the recommended format (video, image, text, etc.).

[0217] Step 6:

[0218] The server sends the generated advice to the terminal, which visualizes and displays it on a dashboard. Users can intuitively understand the advice and use it to plan their next content.

[0219] Step 7:

[0220] Users post content based on the advice they receive. They also send feedback to the server via their device to improve the service, which the system uses to enhance the accuracy of future advice.

[0221] (Example 1)

[0222] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0223] Conventional information gathering and analysis systems have struggled to effectively utilize information on user activities and trends, and to provide content creation support tailored to individual needs. As a result, users have been unable to obtain the information and advice necessary to create and disseminate content quickly and accurately.

[0224] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0225] In this invention, the server includes means for collecting information about users, means for analyzing said information using natural language processing, and means for collecting and analyzing information on current trends. This makes it possible to quickly and accurately provide users with advice for creating individually optimized content.

[0226] "User information" refers to data including user behavior, preferences, posting history, and reactions to those postings.

[0227] "Natural language processing" refers to the technology of using computers to analyze, understand, and generate human language.

[0228] "Information on trends" refers to data about topics or subjects that attract widespread interest at a particular time.

[0229] "Advice" refers to specific suggestions, recommendations, or guidance that are helpful to users when creating content.

[0230] "Means" refers to technical methods, devices, or techniques used to achieve a specific objective.

[0231] The system of this invention mainly consists of a server, a terminal, and a user. The server is responsible for collecting and analyzing user-related data and combining it with external trend information to generate advice for creating content suitable for the user. Specifically, the server uses APIs to collect user posting history, reaction data, comments, etc., from social media platforms and news sites. It also collects external trend information and stores it in a database.

[0232] The server applies natural language processing techniques to the collected data to analyze important keywords and user sentiment. It uses Sentiment Analysis and Keyword Extraction algorithms to identify the success factors of user content. Furthermore, it analyzes trend information and uses machine learning models to identify current trends. The models utilize specific APIs and natural language processing libraries (e.g., TensorFlow and NLTK).

[0233] Based on the generated data, the server uses a generation AI model to generate advice for creating content for the user. For example, a prompt might be sent to the AI ​​in the form of, "Suggest the optimal solution for fashion posts based on past success stories," to obtain specific suggestions.

[0234] The generated advice is provided to the user via a terminal. The terminal has a user interface designed to present the advice in a visually easy-to-understand format. The information is displayed in a dashboard format and designed to be intuitively understandable to the user. Based on this advice, the user plans and creates new content. Furthermore, the user can contribute to system improvement by sending feedback to the server through a feedback function. This feedback is used to continuously improve the quality of the advice provided by the system.

[0235] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0236] Step 1:

[0237] The server uses APIs to collect user data such as user posting history, reaction data, and comments from social media platforms and news sites. Inputs include user account information and social media URLs, while output is a set of user information stored in a database. JavaScript and Python are used for data crawling and API calls.

[0238] Step 2:

[0239] The server performs analysis by applying natural language processing techniques to the collected user data. In this step, Sentiment Analysis and Keyword Extraction are performed using the user data stored as input. The output is the user's sentiment score and a list of extracted keywords. Libraries such as TensorFlow and NLTK are used to analyze the data.

[0240] Step 3:

[0241] The server collects and analyzes information about current trends from external sources. In this step, the input is online data such as news articles and trends, and the output is trending topics and related keywords. Machine learning is used to automatically extract frequently occurring topics and keywords. Web scraping is performed using Python to collect data.

[0242] Step 4:

[0243] The server uses a generative AI model to generate advice for creating optimal content for the user. The input is the analysis results obtained in steps 2 and 3, and the output is advice that includes specific suggestions. The generative AI model is given the prompt, "Suggest the optimal solution for fashion posts based on past success stories," and generates specific ideas.

[0244] Step 5:

[0245] The terminal receives generated advice and visualizes and presents it in a user-friendly format. The input is the advice received from the server, and the output is a dashboard or graphical interface that the user can view. Front-end technologies using JavaScript and HTML / CSS are used to organize and display the information.

[0246] Step 6:

[0247] The user creates content based on the provided advice and returns feedback on the results to the server. The input is the results and opinions of the actions the user has taken, and the output is data stored on the server as feedback information. This allows the system to improve the accuracy of future advice.

[0248] (Application Example 1)

[0249] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0250] In today's information society, individual information providers need to formulate optimal information dissemination strategies based on their past communication history and the reactions of their recipients. However, there is a lack of technology to effectively analyze past information and current trends and generate personalized advice. As a result, many information providers are unable to obtain appropriate guidance and are unable to maximize their influence.

[0251] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0252] In this invention, the server includes means for collecting user information, means for analyzing the user information using natural language processing, and means for collecting and analyzing trending data. This enables users to receive optimal guidance based on their past communication history and trends, and to further formulate personalized information dissemination strategies.

[0253] "User information" refers to data that includes the past content of information providers and the responses of recipients.

[0254] "Natural language processing" is a technology that allows computers to analyze and understand human language, and in this invention, it is used to analyze user information.

[0255] "Current trends data" refers to a collection of information that indicates current fashions and trends in society and the market.

[0256] "Guidelines" are specific advice and suggestions that users should follow to optimize their information dissemination.

[0257] A "personalized information dissemination strategy" is an effective and efficient information dissemination plan that users develop based on their own characteristics and needs.

[0258] This invention is a system consisting of a server that collects and analyzes information, a terminal that presents the information, and a user who ultimately utilizes the information.

[0259] The server collects user information and performs analysis using natural language processing. This allows for a detailed analysis of users' past information sharing and responses, and the extraction of success factors. Furthermore, the server collects trending data from external sources to identify current trends and fads. In this process, the server uses natural language processing techniques based on TensorFlow and additional APIs (such as the Google Cloud Vision API) to process text and image data.

[0260] Based on the analysis results, the server generates personalized information dissemination guidelines for each user. These guidelines may include specific information content and timing. The generated guidelines are visualized in an easy-to-understand format and sent to the user's device. The device displays these guidelines in a dashboard format to assist the user in formulating their own information dissemination strategy.

[0261] Users build their own information dissemination strategies based on the provided guidelines and implement optimal information dissemination. For example, if a user is disseminating information about travel, analysis might reveal that past posts with a sea theme were popular, and that beach resorts are currently trending. Based on this information, the server generates specific guidelines such as "It would be good to post information with a beach resort theme next weekend" and presents them to the user via their device.

[0262] An example of a prompt in a generative AI model would be: "The user's past posts often include images of beaches, which are very popular. Furthermore, beach resorts are currently trending. Based on this information, please provide the user with the best guidance for their next post."

[0263] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0264] Step 1:

[0265] The server collects user information. This information includes past posts, browsing history, and reaction data (such as "likes" and comments). This information is collected on the server as input data, and a dataset for analysis is prepared as output. Specifically, a database management system is used to obtain log data regarding user behavior.

[0266] Step 2:

[0267] The server analyzes user information using natural language processing. The input is the dataset prepared in Step 1, and natural language processing techniques (e.g., TensorFlow) are applied to identify user interests and success factors. The output is user behavioral characteristics based on the analysis. Specifically, text analysis is performed to identify frequently occurring words and sentiment analysis.

[0268] Step 3:

[0269] The server collects trending data from external sources. It obtains trend information using web scraping and APIs as input and transfers it to the server. The output is a dataset showing current trends. Specifically, it obtains trending information from the Twitter API and news feeds.

[0270] Step 4:

[0271] The server integrates user information and trending data to generate guidelines. The input combines user characteristics from step 2 and trending data from step 3, and uses a generative AI model to create optimal guidelines. The output is specific advice regarding particular information dissemination. Specifically, the generative model might suggest, "It would be good to disseminate information with a beach resort theme next weekend."

[0272] Step 5:

[0273] The terminal visualizes the guidelines received from the server and presents them to the user. The input is the guideline information generated in step 4, and the output is a dashboard that the user can view. Specifically, the guidelines are displayed on a web interface or mobile app and designed to be easily understood by the user.

[0274] Step 6:

[0275] Users optimize their information dissemination strategy based on the provided guidelines. They receive the guidelines provided in Step 5 as input and develop their own information dissemination plan as output. Specifically, users adjust their content creation and posting schedules according to the guidelines and disseminate new information at the appropriate time.

[0276] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0277] This invention is a system that provides users with more personalized content creation advice by utilizing user-submitted data and trend data, and further combining them with an emotion engine. This system consists of a server, terminals, and users, with the server primarily handling data collection, analysis, and advice generation, and the terminals visualizing the advice.

[0278] The server first accesses the user's past posting database to collect user data such as post content, posting time, number of likes, and comment data. In this process, the data is structured and prepared for use with the sentiment engine. Next, analysis is performed using natural language processing techniques to analyze not only the theme and topic of each post, but also the emotional aspects (positive, negative, neutral) contained in the post using the sentiment engine.

[0279] Furthermore, the server collects trend data from external social media platforms and relevant information sources and analyzes recent trends. Based on this trend data, along with analyzed user data and sentiment data, it generates content creation advice optimized for each individual user. Specifically, it suggests content styles and themes that promote specific emotions, based on the user's past success factors and current emotional state.

[0280] The generated advice is sent to the device and provided to the user. The device visualizes this information on a dashboard, allowing users to immediately use it in their daily creative activities. The visualized advice also shows emotional outcomes, allowing users to plan posts that align with their emotional state.

[0281] As a concrete example, let's say there's a user who primarily posts about travel. The server analyzes that "landscape photos" in that user's posts elicit particularly positive emotional responses. Combining this with trend data, it generates advice that posting about travel destinations and experiences themed around "relaxation" would be effective. In this way, users can effectively create content that incorporates the latest trends while being mindful of their strengths and the emotional impact they have on others.

[0282] The following describes the processing flow.

[0283] Step 1:

[0284] The server accesses the user's posting history database and collects user data such as the content of the post, the posting date and time, the number of likes, and the content of comments. In this data collection, the data is converted into an appropriate format for natural language processing and sentiment analysis preparation.

[0285] Step 2:

[0286] The server analyzes the collected user data using natural language processing (NLP) techniques. After tokenizing the text data and performing stemming and lemmatization, it analyzes what themes and topics are prevalent. Also, using a sentiment engine, it automatically determines the sentiment (positive, negative, neutral) embedded in each post.

[0287] Step 3:

[0288] The server collects current trend data from external social media platforms and specialized content sites. At that time, it identifies topics of particular interest, popular keywords, and hashtags.

[0289] Step 4:

[0290] Based on the analyzed user data and trend data, the server generates content creation advice for individual users. Utilizing the results of sentiment analysis obtained from the sentiment engine, it proposes posting styles and themes according to the emotions the user wants to evoke. It also determines the appropriate posting timing and format (e.g., text, image, video).

[0291] Step 5:

[0292] The server sends the generated advice to the terminal, and the terminal presents it to the user in a visualized format. The user can easily understand and utilize the provided advice through a graphical interface such as a dashboard.

[0293] Step 6:

[0294] Based on the advice provided, users plan their next content and actually post it. They can also send feedback to the server via their device, which allows for continuous improvement of the quality of the advice.

[0295] (Example 2)

[0296] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0297] Current information generation systems face challenges in creating information tailored to the individual needs of users and insufficient provision of effective content guidelines based on emotions and trends.

[0298] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0299] In this invention, the server includes means for collecting information, means for analyzing the information using natural language processing, and means for collecting and analyzing external data. This makes it possible to provide guidelines that are suitable for the user's needs and to generate effective information.

[0300] "Means of collecting information" refers to a system that aggregates a user's past communication content and related data, and accesses a database to obtain the necessary information.

[0301] "Means for analyzing the information using natural language processing" refers to a technical method that processes the acquired information using a computer and automatically analyzes the theme and emotions of the content.

[0302] "Methods for collecting and analyzing external data" refers to techniques for obtaining trends and related data from various sources on the internet, organizing and classifying them, and understanding current trends.

[0303] The means for creating guidelines for information generation based on the analyzed information and external data is an algorithm that combines the collected information and trend data to propose a guideline for creating information that is most suitable for the user.

[0304] The means for providing the generated guidelines to the user is a mechanism for presenting the created guidelines to the user visually or in other ways so that they can be used in actual information generation activities.

[0305] The means for analyzing the user's response to communication and identifying the success factors of information is a process of analyzing the evaluation and response of the user's past communication and extracting the success factors.

[0306] The means for visualizing the guidelines and presenting them in a user-friendly format is a method of visually displaying the generated guidelines for information generation in graphs, tables, charts, etc., and providing them in a format that users can easily understand and utilize.

[0307] The embodiments for implementing the invention will be described.

[0308] This invention is a system for providing guidelines for personalized information generation to users. This system is composed of a server, a terminal, and a user.

[0309] First, the server collects the user's past communication data. For data collection, an API for connecting to the database and a program for executing SQL queries for database operations are used. This program is implemented in a scripting language such as Python. Next, the server utilizes natural language processing technology to analyze the user's communication content. Specifically, libraries such as NLTK and SpaCy are used to perform text tokenization and sentiment classification. Also, external sentiment analysis tools such as the Google Cloud Natural Language API can be utilized.

[0310] Next, the server collects trend data from external sources. This involves using web scraping tools such as Beautiful Soup or Selenium to obtain real-time trend information. The collected user data and trend data are then integrated, and a generative AI model is used to create guidelines for information generation. Ideally, a sophisticated natural language generation model, such as GPT-4, should be used. An example of a prompt used here might be, "Based on past successes and current trends, propose guidelines for generating information that will have a positive impact on users."

[0311] The generated guidelines are sent from the server to the terminal, where the terminal visualizes this information. JavaScript libraries such as D3.js and Chart.js are used for visualization, displaying it as a dashboard. This allows users to easily understand the guidelines and utilize them in their own information generation activities.

[0312] Based on the provided guidelines, users generate new information and send feedback to the server. This feedback is used to improve future guideline generation. Through this process, the system can continuously provide users with valuable guidelines and improve the quality of information generation.

[0313] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0314] Step 1:

[0315] The server accesses the user database and collects the user's past communication data. The input to this process is a specific user ID, and the output is a collection of various data such as the user's posts, comments, and number of reactions. SQL queries are used to extract information from the database, and data retrieval is automated using a Python script.

[0316] Step 2:

[0317] The server analyzes the collected data using natural language processing techniques. The input is the text data obtained in step 1, and the output is the results of topic and sentiment analysis. Libraries such as NLTK and SpaCy are used to tokenize and analyze the text, and sentiment labels such as positive, negative, and neutral are assigned.

[0318] Step 3:

[0319] The server collects trend data from external sources. The input to this process is target keywords and hashtags, and the output is a dataset of trend information. Web pages are scraped using Beautiful Soup and Selenium to obtain trend information in real time.

[0320] Step 4:

[0321] The server uses analyzed user data and trend data to input prompts into a generative AI model, creating guidelines for information generation. The input consists of user sentiment analysis results and trend data, while the output is specific guidelines that should be provided to the user. The generative AI model uses GPT-4 or similar technologies and is given the prompt, "Propose guidelines for generating information that will have a positive impact on the user."

[0322] Step 5:

[0323] The server sends the generated guidelines to the terminal. The terminal visualizes the received guidelines on a dashboard. The input is the guidelines generated from the server, and the output is the visualized information presented to the user. Libraries such as D3.js and Chart.js are used for visualization, displaying the guidelines in a user-friendly format.

[0324] Step 6:

[0325] Based on the provided guidelines, users send feedback to the server to generate information. The input consists of the user's evaluation and impressions after use, while the output is feedback data that helps improve the guidelines for the next cycle. This feedback is recorded in the server's database and used in the next cycle.

[0326] (Application Example 2)

[0327] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0328] With the increasing diversification of information distribution in modern times, there is a challenge in accurately suggesting information resources that match the individual interests and emotional states of users. In particular, there is a need to suggest information resources that take into account users' past successes and emotional responses, but conventional systems have found it difficult to achieve this efficiently.

[0329] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0330] In this invention, the server includes means for collecting user information, means for analyzing the user information using natural language processing, and means for collecting and analyzing trending information. This makes it possible to analyze the user's emotional state and suggest information resources that are appropriate to it.

[0331] "User information" refers to data related to a user, such as their past activity history, ratings, and comments.

[0332] "Natural language processing" is a technology that enables computers to understand and analyze text written by humans.

[0333] "Trend information" refers to data about topics or subjects that have gained widespread popularity within a specific period.

[0334] "Information resources" refers to all content and media that users can consume or utilize.

[0335] "Emotional state" refers to the user's emotions at that particular moment, inferred from their text data and other information.

[0336] To implement this invention, it is necessary to construct a system in which three elements—a server, a terminal, and a user—work in coordination.

[0337] The server is responsible for collecting user information and trending information, and analyzing the necessary data. User information includes past viewing history, ratings, and comments, which the server collects. Trending information is collected from external sources. Using this information, natural language processing is performed to analyze the user's emotional state. Based on this, the server generates advice to suggest the most suitable information resources. This process includes using sentiment analysis tools such as Amazon Comprehend and collecting trending information using the Twitter API.

[0338] The terminal plays a role in visualizing the advice sent from the server and presenting it in a format that is easy for the user to understand intuitively. This information is displayed, for example, on a dashboard designed using Flutter, and suggests information resources tailored to the user's needs.

[0339] Users can select and utilize information resources that interest them based on the advice provided using their own devices. This allows users to enjoy content that matches their emotional state.

[0340] For example, if a movie-loving user is determined to be in a "relaxed" state through server analysis, new and trending movies, or works with a relaxing theme tailored to their mood, will be suggested to that user. Through this process, users can obtain the most suitable information resources for their current emotional state. It is possible to generate suggestions using a prompt such as, "Suggest relaxing movies based on the user's recent positive emotional state."

[0341] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0342] Step 1:

[0343] The server retrieves user information. Specifically, it collects user viewing history, ratings, and comments from the database. At this stage, the input is user information from the database, and the output is the collected structured data.

[0344] Step 2:

[0345] The server analyzes user information collected using natural language processing. This process utilizes Amazon Comprehend to extract emotional aspects from text data. The input is structured user information, and the output is analyzed data including emotional states. Specifically, it performs sentiment analysis on evaluation comments and assigns positive, negative, or neutral labels.

[0346] Step 3:

[0347] The server collects trending information from external sources. This step uses the Twitter API to retrieve the latest topics and trending data that users are interested in. The input is raw data from external sources, and the output is analyzable trending data. Specifically, trending keywords are extracted and stored in a database.

[0348] Step 4:

[0349] The server generates advice to suggest the most suitable information resources to the user, based on the analyzed user information and collected trend information. This process uses a generative AI model, taking a prompt as input and outputting the best suggestions. For example, it might use the prompt, "Based on the user's recent positive emotional state, please suggest a relaxing movie."

[0350] Step 5:

[0351] The terminal visualizes the advice received from the server. The input is the advice data sent from the server, and the output is a dashboard display that the user can visually confirm. Specifically, it is displayed on the interface using Flutter.

[0352] Step 6:

[0353] The user refers to visualized advice on the device, selects and uses information resources of interest based on that advice. This step primarily involves the user selecting the most suitable information resources; the input is visualized advice, and the output is actionable actions corresponding to the user's selection.

[0354] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0355] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0356] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0357] [Third Embodiment]

[0358] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0359] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0360] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0361] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0362] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0363] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0364] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0365] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0366] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0367] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0368] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0369] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0370] The system of this invention consists of a server, a terminal, and a user. The server is primarily responsible for collecting and analyzing user data, collecting trend data, and generating advice. The terminal presents visualized advice to the user, and the user utilizes the provided advice based on their own activities.

[0371] Specifically, the server first collects text data from the user's posting history, as well as reaction data such as reactions and comments. The collected data is analyzed using natural language processing techniques to extract success factors and characteristics in the user's activities. At the same time, the server collects relevant trend data from external social media platforms and news sites to identify current trends.

[0372] Next, the server generates content creation advice tailored to the user based on the collected and analyzed data. This advice may include specific post content, posting timing, and recommended keywords and hashtags. The generated advice is then provided to the user via their device.

[0373] The terminal visualizes the advice received from the server using a graphical interface such as a dashboard, making it easy for users to understand. Based on the advice provided, users can plan and implement more impactful content strategies while leveraging their individuality. Users can also send feedback to the server, and the system uses this feedback to further improve the advice.

[0374] For example, in the case of a user who posts about fashion, the server analyzes the user's past posts and reaction data to determine that outfits using natural materials were popular. Furthermore, it identifies that "sustainable fashion" is gaining attention based on current trend data. The user is then advised to "post outfits using sustainable materials on weekend afternoons." In this way, users can create effective content that incorporates trends while maintaining their individuality.

[0375] The following describes the processing flow.

[0376] Step 1:

[0377] The server accesses the user's past posting database and collects user data such as post content, posting date and time, number of likes, and content and number of comments. The collected data is structured and prepared for analysis.

[0378] Step 2:

[0379] The server analyzes user data collected using natural language processing (NLP) techniques. Specifically, it performs text tokenization, stemming, and rooming to clean the text. Then, it extracts recurring themes and topics from user posts.

[0380] Step 3:

[0381] The server performs sentiment analysis based on reaction data, evaluating positive, negative, and neutral responses. This helps identify which posts are particularly engaging and successful.

[0382] Step 4:

[0383] The server uses APIs from external social media platforms and related news sites to collect trending data. It retrieves specific keywords, hashtags, and trending topics to analyze current trends.

[0384] Step 5:

[0385] The server generates content creation advice tailored to the user based on the analysis results. It combines the user's past success factors with current trends to determine the theme of a new post, the optimal posting time, the hashtags to use, and the recommended format (video, image, text, etc.).

[0386] Step 6:

[0387] The server sends the generated advice to the terminal, which visualizes and displays it on a dashboard. Users can intuitively understand the advice and use it to plan their next content.

[0388] Step 7:

[0389] Users post content based on the advice they receive. They also send feedback to the server via their device to improve the service, which the system uses to enhance the accuracy of future advice.

[0390] (Example 1)

[0391] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0392] Conventional information gathering and analysis systems have struggled to effectively utilize information on user activities and trends, and to provide content creation support tailored to individual needs. As a result, users have been unable to obtain the information and advice necessary to create and disseminate content quickly and accurately.

[0393] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0394] In this invention, the server includes means for collecting information about users, means for analyzing said information using natural language processing, and means for collecting and analyzing information on current trends. This makes it possible to quickly and accurately provide users with advice for creating individually optimized content.

[0395] "User information" refers to data including user behavior, preferences, posting history, and reactions to those postings.

[0396] "Natural language processing" refers to the technology of using computers to analyze, understand, and generate human language.

[0397] "Information on trends" refers to data about topics or subjects that attract widespread interest at a particular time.

[0398] "Advice" refers to specific suggestions, recommendations, or guidance that are helpful to users when creating content.

[0399] "Means" refers to technical methods, devices, or techniques used to achieve a specific objective.

[0400] The system of this invention mainly consists of a server, a terminal, and a user. The server is responsible for collecting and analyzing user-related data and combining it with external trend information to generate advice for creating content suitable for the user. Specifically, the server uses APIs to collect user posting history, reaction data, comments, etc., from social media platforms and news sites. It also collects external trend information and stores it in a database.

[0401] The server applies natural language processing techniques to the collected data to analyze important keywords and user sentiment. It uses Sentiment Analysis and Keyword Extraction algorithms to identify the success factors of user content. Furthermore, it analyzes trend information and uses machine learning models to identify current trends. The models utilize specific APIs and natural language processing libraries (e.g., TensorFlow and NLTK).

[0402] Based on the generated data, the server uses a generation AI model to generate advice for creating content for the user. For example, a prompt might be sent to the AI ​​in the form of, "Suggest the optimal solution for fashion posts based on past success stories," to obtain specific suggestions.

[0403] The generated advice is provided to the user via a terminal. The terminal has a user interface designed to present the advice in a visually easy-to-understand format. The information is displayed in a dashboard format and designed to be intuitively understandable to the user. Based on this advice, the user plans and creates new content. Furthermore, the user can contribute to system improvement by sending feedback to the server through a feedback function. This feedback is used to continuously improve the quality of the advice provided by the system.

[0404] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0405] Step 1:

[0406] The server uses APIs to collect user data such as user posting history, reaction data, and comments from social media platforms and news sites. Inputs include user account information and social media URLs, while output is a set of user information stored in a database. JavaScript and Python are used for data crawling and API calls.

[0407] Step 2:

[0408] The server performs analysis by applying natural language processing techniques to the collected user data. In this step, Sentiment Analysis and Keyword Extraction are performed using the user data stored as input. The output is the user's sentiment score and a list of extracted keywords. Libraries such as TensorFlow and NLTK are used to analyze the data.

[0409] Step 3:

[0410] The server collects and analyzes information about current trends from external sources. In this step, the input is online data such as news articles and trends, and the output is trending topics and related keywords. Machine learning is used to automatically extract frequently occurring topics and keywords. Web scraping is performed using Python to collect data.

[0411] Step 4:

[0412] The server uses a generative AI model to generate advice for creating optimal content for the user. The input is the analysis results obtained in steps 2 and 3, and the output is advice that includes specific suggestions. The generative AI model is given the prompt, "Suggest the optimal solution for fashion posts based on past success stories," and generates specific ideas.

[0413] Step 5:

[0414] The terminal receives generated advice and visualizes and presents it in a user-friendly format. The input is the advice received from the server, and the output is a dashboard or graphical interface that the user can view. Front-end technologies using JavaScript and HTML / CSS are used to organize and display the information.

[0415] Step 6:

[0416] The user creates content based on the provided advice and returns feedback on the results to the server. The input is the results and opinions of the actions the user has taken, and the output is data stored on the server as feedback information. This allows the system to improve the accuracy of future advice.

[0417] (Application Example 1)

[0418] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0419] In today's information society, individual information providers need to formulate optimal information dissemination strategies based on their past communication history and the reactions of their recipients. However, there is a lack of technology to effectively analyze past information and current trends and generate personalized advice. As a result, many information providers are unable to obtain appropriate guidance and are unable to maximize their influence.

[0420] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0421] In this invention, the server includes means for collecting user information, means for analyzing the user information using natural language processing, and means for collecting and analyzing trending data. This enables users to receive optimal guidance based on their past communication history and trends, and to further formulate personalized information dissemination strategies.

[0422] "User information" refers to data that includes the past content of information providers and the responses of recipients.

[0423] "Natural language processing" is a technology that allows computers to analyze and understand human language, and in this invention, it is used to analyze user information.

[0424] "Current trends data" refers to a collection of information that indicates current fashions and trends in society and the market.

[0425] "Guidelines" are specific advice and suggestions that users should follow to optimize their information dissemination.

[0426] A "personalized information dissemination strategy" is an effective and efficient information dissemination plan that users develop based on their own characteristics and needs.

[0427] This invention is a system consisting of a server that collects and analyzes information, a terminal that presents the information, and a user who ultimately utilizes the information.

[0428] The server collects user information and performs analysis using natural language processing. This allows for a detailed analysis of users' past information sharing and responses, and the extraction of success factors. Furthermore, the server collects trending data from external sources to identify current trends and fads. In this process, the server uses natural language processing techniques based on TensorFlow and additional APIs (such as the Google Cloud Vision API) to process text and image data.

[0429] Based on the analysis results, the server generates personalized information dissemination guidelines for each user. These guidelines may include specific information content and timing. The generated guidelines are visualized in an easy-to-understand format and sent to the user's device. The device displays these guidelines in a dashboard format to assist the user in formulating their own information dissemination strategy.

[0430] Users build their own information dissemination strategies based on the provided guidelines and implement optimal information dissemination. For example, if a user is disseminating information about travel, analysis might reveal that past posts with a sea theme were popular, and that beach resorts are currently trending. Based on this information, the server generates specific guidelines such as "It would be good to post information with a beach resort theme next weekend" and presents them to the user via their device.

[0431] An example of a prompt in a generative AI model would be: "The user's past posts often include images of beaches, which are very popular. Furthermore, beach resorts are currently trending. Based on this information, please provide the user with the best guidance for their next post."

[0432] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0433] Step 1:

[0434] The server collects user information. This information includes past posts, browsing history, and reaction data (such as "likes" and comments). This information is collected on the server as input data, and a dataset for analysis is prepared as output. Specifically, a database management system is used to obtain log data regarding user behavior.

[0435] Step 2:

[0436] The server analyzes user information using natural language processing. The input is the dataset prepared in Step 1, and natural language processing techniques (e.g., TensorFlow) are applied to identify user interests and success factors. The output is user behavioral characteristics based on the analysis. Specifically, text analysis is performed to identify frequently occurring words and sentiment analysis.

[0437] Step 3:

[0438] The server collects trending data from external sources. It obtains trend information using web scraping and APIs as input and transfers it to the server. The output is a dataset showing current trends. Specifically, it obtains trending information from the Twitter API and news feeds.

[0439] Step 4:

[0440] The server integrates user information and trending data to generate guidelines. The input combines user characteristics from step 2 and trending data from step 3, and uses a generative AI model to create optimal guidelines. The output is specific advice regarding particular information dissemination. Specifically, the generative model might suggest, "It would be good to disseminate information with a beach resort theme next weekend."

[0441] Step 5:

[0442] The terminal visualizes the guidelines received from the server and presents them to the user. The input is the guideline information generated in step 4, and the output is a dashboard that the user can view. Specifically, the guidelines are displayed on a web interface or mobile app and designed to be easily understood by the user.

[0443] Step 6:

[0444] Users optimize their information dissemination strategy based on the provided guidelines. They receive the guidelines provided in Step 5 as input and develop their own information dissemination plan as output. Specifically, users adjust their content creation and posting schedules according to the guidelines and disseminate new information at the appropriate time.

[0445] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0446] This invention is a system that provides users with more personalized content creation advice by utilizing user-submitted data and trend data, and further combining them with an emotion engine. This system consists of a server, terminals, and users, with the server primarily handling data collection, analysis, and advice generation, and the terminals visualizing the advice.

[0447] The server first accesses the user's past posting database to collect user data such as post content, posting time, number of likes, and comment data. In this process, the data is structured and prepared for use with the sentiment engine. Next, analysis is performed using natural language processing techniques to analyze not only the theme and topic of each post, but also the emotional aspects (positive, negative, neutral) contained in the post using the sentiment engine.

[0448] Furthermore, the server collects trend data from external social media platforms and relevant information sources and analyzes recent trends. Based on this trend data, along with analyzed user data and sentiment data, it generates content creation advice optimized for each individual user. Specifically, it suggests content styles and themes that promote specific emotions, based on the user's past success factors and current emotional state.

[0449] The generated advice is sent to the device and provided to the user. The device visualizes this information on a dashboard, allowing users to immediately use it in their daily creative activities. The visualized advice also shows emotional outcomes, allowing users to plan posts that align with their emotional state.

[0450] As a concrete example, let's say there's a user who primarily posts about travel. The server analyzes that "landscape photos" in that user's posts elicit particularly positive emotional responses. Combining this with trend data, it generates advice that posting about travel destinations and experiences themed around "relaxation" would be effective. In this way, users can effectively create content that incorporates the latest trends while being mindful of their strengths and the emotional impact they have on others.

[0451] The following describes the processing flow.

[0452] Step 1:

[0453] The server accesses the user's posting history database and collects user data such as post content, posting date and time, number of likes, and comment content. This data collection process converts the data into an appropriate format for preparation for natural language processing and sentiment analysis.

[0454] Step 2:

[0455] The server uses natural language processing (NLP) techniques to analyze the collected user data. After tokenizing the text data and performing stemming and rooming, it analyzes which themes and topics are most frequent. It also uses a sentiment engine to automatically determine the sentiment (positive, negative, neutral) embedded in each post.

[0456] Step 3:

[0457] The server collects current trend data from external social media platforms and specialized content sites, identifying particularly noteworthy topics, popular keywords, and hashtags.

[0458] Step 4:

[0459] The server generates personalized content creation advice based on analyzed user data and trend data. Leveraging sentiment analysis results from the sentiment engine, it suggests posting styles and themes tailored to the emotions the user wants to evoke. It also determines the appropriate timing and format for posting (e.g., text, images, videos).

[0460] Step 5:

[0461] The server sends the generated advice to the terminal, which then presents it to the user in a visualized format. The user can easily understand and utilize the provided advice through a graphical interface such as a dashboard.

[0462] Step 6:

[0463] Based on the advice provided, users plan their next content and actually post it. They can also send feedback to the server via their device, which allows for continuous improvement of the quality of the advice.

[0464] (Example 2)

[0465] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0466] Current information generation systems face challenges in creating information tailored to the individual needs of users and insufficient provision of effective content guidelines based on emotions and trends.

[0467] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0468] In this invention, the server includes means for collecting information, means for analyzing the information using natural language processing, and means for collecting and analyzing external data. This makes it possible to provide guidelines that are suitable for the user's needs and to generate effective information.

[0469] "Means of collecting information" refers to a system that aggregates a user's past communication content and related data, and accesses a database to obtain the necessary information.

[0470] "Means for analyzing the information using natural language processing" refers to a technical method that processes the acquired information using a computer and automatically analyzes the theme and emotions of the content.

[0471] "Methods for collecting and analyzing external data" refers to techniques for obtaining trends and related data from various sources on the internet, organizing and classifying them, and understanding current trends.

[0472] "Means for creating guidelines for information generation based on analyzed information and external data" refers to an algorithm that combines collected information and trend data to propose the most suitable information creation policy for the user.

[0473] "Means of providing generated guidelines to users" refers to a mechanism for presenting the created guidelines to users visually or by other means, so that they can be used in actual information generation activities.

[0474] "Means for analyzing users' responses to communications and identifying the factors for information success" refers to the process of analyzing users' evaluations and responses to past communications and extracting the factors for their success.

[0475] "Means of visualizing the aforementioned guidelines and presenting them in a format that is easy for users to understand" refers to a method of visually displaying the generated information generation guidelines using graphs, tables, charts, etc., and providing them in a format that users can easily understand and utilize.

[0476] A description of the embodiment for carrying out the invention will be provided.

[0477] This invention is a system for providing users with personalized information generation guidelines. This system consists of three components: a server, a terminal, and a user.

[0478] The server first collects the user's past communication data. This data collection uses an API to connect to a database and a program to execute SQL queries to manipulate the database. This program is implemented in a scripting language such as Python. Next, the server uses natural language processing techniques to analyze the user's communication content. Specifically, it uses libraries such as NLTK and SpaCy to tokenize text and classify sentiment. It can also utilize external sentiment analysis tools such as the Google Cloud Natural Language API.

[0479] Next, the server collects trend data from external sources. This involves using web scraping tools such as Beautiful Soup or Selenium to obtain real-time trend information. The collected user data and trend data are then integrated, and a generative AI model is used to create guidelines for information generation. Ideally, a sophisticated natural language generation model, such as GPT-4, should be used. An example of a prompt used here might be, "Based on past successes and current trends, propose guidelines for generating information that will have a positive impact on users."

[0480] The generated guidelines are sent from the server to the terminal, where the terminal visualizes this information. JavaScript libraries such as D3.js and Chart.js are used for visualization, displaying it as a dashboard. This allows users to easily understand the guidelines and utilize them in their own information generation activities.

[0481] Based on the provided guidelines, users generate new information and send feedback to the server. This feedback is used to improve future guideline generation. Through this process, the system can continuously provide users with valuable guidelines and improve the quality of information generation.

[0482] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0483] Step 1:

[0484] The server accesses the user database and collects the user's past communication data. The input to this process is a specific user ID, and the output is a collection of various data such as the user's posts, comments, and number of reactions. SQL queries are used to extract information from the database, and data retrieval is automated using a Python script.

[0485] Step 2:

[0486] The server analyzes the collected data using natural language processing techniques. The input is the text data obtained in step 1, and the output is the results of topic and sentiment analysis. Libraries such as NLTK and SpaCy are used to tokenize and analyze the text, and sentiment labels such as positive, negative, and neutral are assigned.

[0487] Step 3:

[0488] The server collects trend data from external sources. The input to this process is target keywords and hashtags, and the output is a dataset of trend information. Web pages are scraped using Beautiful Soup and Selenium to obtain trend information in real time.

[0489] Step 4:

[0490] The server uses analyzed user data and trend data to input prompts into a generative AI model, creating guidelines for information generation. The input consists of user sentiment analysis results and trend data, while the output is specific guidelines that should be provided to the user. The generative AI model uses GPT-4 or similar technologies and is given the prompt, "Propose guidelines for generating information that will have a positive impact on the user."

[0491] Step 5:

[0492] The server sends the generated guidelines to the terminal. The terminal visualizes the received guidelines on a dashboard. The input is the guidelines generated from the server, and the output is the visualized information presented to the user. Libraries such as D3.js and Chart.js are used for visualization, displaying the guidelines in a user-friendly format.

[0493] Step 6:

[0494] Based on the provided guidelines, users send feedback to the server to generate information. The input consists of the user's evaluation and impressions after use, while the output is feedback data that helps improve the guidelines for the next cycle. This feedback is recorded in the server's database and used in the next cycle.

[0495] (Application Example 2)

[0496] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0497] With the increasing diversification of information distribution in modern times, there is a challenge in accurately suggesting information resources that match the individual interests and emotional states of users. In particular, there is a need to suggest information resources that take into account users' past successes and emotional responses, but conventional systems have found it difficult to achieve this efficiently.

[0498] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0499] In this invention, the server includes means for collecting user information, means for analyzing the user information using natural language processing, and means for collecting and analyzing trending information. This makes it possible to analyze the user's emotional state and suggest information resources that are appropriate to it.

[0500] "User information" refers to data related to a user, such as their past activity history, ratings, and comments.

[0501] "Natural language processing" is a technology that enables computers to understand and analyze text written by humans.

[0502] "Trend information" refers to data about topics or subjects that have gained widespread popularity within a specific period.

[0503] "Information resources" refers to all content and media that users can consume or utilize.

[0504] "Emotional state" refers to the user's emotions at that particular moment, inferred from their text data and other information.

[0505] To implement this invention, it is necessary to construct a system in which three elements—a server, a terminal, and a user—work in coordination.

[0506] The server is responsible for collecting user information and trending information, and analyzing the necessary data. User information includes past viewing history, ratings, and comments, which the server collects. Trending information is collected from external sources. Using this information, natural language processing is performed to analyze the user's emotional state. Based on this, the server generates advice to suggest the most suitable information resources. This process includes using sentiment analysis tools such as Amazon Comprehend and collecting trending information using the Twitter API.

[0507] The terminal plays a role in visualizing the advice sent from the server and presenting it in a format that is easy for the user to understand intuitively. This information is displayed, for example, on a dashboard designed using Flutter, and suggests information resources tailored to the user's needs.

[0508] Users can select and utilize information resources that interest them based on the advice provided using their own devices. This allows users to enjoy content that matches their emotional state.

[0509] For example, if a movie-loving user is determined to be in a "relaxed" state through server analysis, new and trending movies, or works with a relaxing theme tailored to their mood, will be suggested to that user. Through this process, users can obtain the most suitable information resources for their current emotional state. It is possible to generate suggestions using a prompt such as, "Suggest relaxing movies based on the user's recent positive emotional state."

[0510] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0511] Step 1:

[0512] The server retrieves user information. Specifically, it collects user viewing history, ratings, and comments from the database. At this stage, the input is user information from the database, and the output is the collected structured data.

[0513] Step 2:

[0514] The server analyzes user information collected using natural language processing. This process utilizes Amazon Comprehend to extract emotional aspects from text data. The input is structured user information, and the output is analyzed data including emotional states. Specifically, it performs sentiment analysis on evaluation comments and assigns positive, negative, or neutral labels.

[0515] Step 3:

[0516] The server collects trending information from external sources. This step uses the Twitter API to retrieve the latest topics and trending data that users are interested in. The input is raw data from external sources, and the output is analyzable trending data. Specifically, trending keywords are extracted and stored in a database.

[0517] Step 4:

[0518] The server generates advice to suggest the most suitable information resources to the user, based on the analyzed user information and collected trend information. This process uses a generative AI model, taking a prompt as input and outputting the best suggestions. For example, it might use the prompt, "Based on the user's recent positive emotional state, please suggest a relaxing movie."

[0519] Step 5:

[0520] The terminal visualizes the advice received from the server. The input is the advice data sent from the server, and the output is a dashboard display that the user can visually confirm. Specifically, it is displayed on the interface using Flutter.

[0521] Step 6:

[0522] The user refers to visualized advice on the device, selects and uses information resources of interest based on that advice. This step primarily involves the user selecting the most suitable information resources; the input is visualized advice, and the output is actionable actions corresponding to the user's selection.

[0523] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0524] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0525] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0526] [Fourth Embodiment]

[0527] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0528] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0529] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0530] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0531] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0532] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0533] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0534] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0535] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0536] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0537] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0538] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0539] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0540] The system of this invention consists of a server, a terminal, and a user. The server is primarily responsible for collecting and analyzing user data, collecting trend data, and generating advice. The terminal presents visualized advice to the user, and the user utilizes the provided advice based on their own activities.

[0541] Specifically, the server first collects text data from the user's posting history, as well as reaction data such as reactions and comments. The collected data is analyzed using natural language processing techniques to extract success factors and characteristics in the user's activities. At the same time, the server collects relevant trend data from external social media platforms and news sites to identify current trends.

[0542] Next, the server generates content creation advice tailored to the user based on the collected and analyzed data. This advice may include specific post content, posting timing, and recommended keywords and hashtags. The generated advice is then provided to the user via their device.

[0543] The terminal visualizes the advice received from the server using a graphical interface such as a dashboard, making it easy for users to understand. Based on the advice provided, users can plan and implement more impactful content strategies while leveraging their individuality. Users can also send feedback to the server, and the system uses this feedback to further improve the advice.

[0544] For example, in the case of a user who posts about fashion, the server analyzes the user's past posts and reaction data to determine that outfits using natural materials were popular. Furthermore, it identifies that "sustainable fashion" is gaining attention based on current trend data. The user is then advised to "post outfits using sustainable materials on weekend afternoons." In this way, users can create effective content that incorporates trends while maintaining their individuality.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] The server accesses the user's past posting database and collects user data such as post content, posting date and time, number of likes, and content and number of comments. The collected data is structured and prepared for analysis.

[0548] Step 2:

[0549] The server analyzes user data collected using natural language processing (NLP) techniques. Specifically, it performs text tokenization, stemming, and rooming to clean the text. Then, it extracts recurring themes and topics from user posts.

[0550] Step 3:

[0551] The server performs sentiment analysis based on reaction data, evaluating positive, negative, and neutral responses. This helps identify which posts are particularly engaging and successful.

[0552] Step 4:

[0553] The server uses APIs from external social media platforms and related news sites to collect trending data. It retrieves specific keywords, hashtags, and trending topics to analyze current trends.

[0554] Step 5:

[0555] The server generates content creation advice tailored to the user based on the analysis results. It combines the user's past success factors with current trends to determine the theme of a new post, the optimal posting time, the hashtags to use, and the recommended format (video, image, text, etc.).

[0556] Step 6:

[0557] The server sends the generated advice to the terminal, which visualizes and displays it on a dashboard. Users can intuitively understand the advice and use it to plan their next content.

[0558] Step 7:

[0559] Users post content based on the advice they receive. They also send feedback to the server via their device to improve the service, which the system uses to enhance the accuracy of future advice.

[0560] (Example 1)

[0561] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0562] Conventional information gathering and analysis systems have struggled to effectively utilize information on user activities and trends, and to provide content creation support tailored to individual needs. As a result, users have been unable to obtain the information and advice necessary to create and disseminate content quickly and accurately.

[0563] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0564] In this invention, the server includes means for collecting information about users, means for analyzing said information using natural language processing, and means for collecting and analyzing information on current trends. This makes it possible to quickly and accurately provide users with advice for creating individually optimized content.

[0565] "User information" refers to data including user behavior, preferences, posting history, and reactions to those postings.

[0566] "Natural language processing" refers to the technology of using computers to analyze, understand, and generate human language.

[0567] "Information on trends" refers to data about topics or subjects that attract widespread interest at a particular time.

[0568] "Advice" refers to specific suggestions, recommendations, or guidance that are helpful to users when creating content.

[0569] "Means" refers to technical methods, devices, or techniques used to achieve a specific objective.

[0570] The system of this invention mainly consists of a server, a terminal, and a user. The server is responsible for collecting and analyzing user-related data and combining it with external trend information to generate advice for creating content suitable for the user. Specifically, the server uses APIs to collect user posting history, reaction data, comments, etc., from social media platforms and news sites. It also collects external trend information and stores it in a database.

[0571] The server applies natural language processing techniques to the collected data to analyze important keywords and user sentiment. It uses Sentiment Analysis and Keyword Extraction algorithms to identify the success factors of user content. Furthermore, it analyzes trend information and uses machine learning models to identify current trends. The models utilize specific APIs and natural language processing libraries (e.g., TensorFlow and NLTK).

[0572] Based on the generated data, the server uses a generation AI model to generate advice for creating content for the user. For example, a prompt might be sent to the AI ​​in the form of, "Suggest the optimal solution for fashion posts based on past success stories," to obtain specific suggestions.

[0573] The generated advice is provided to the user via a terminal. The terminal has a user interface designed to present the advice in a visually easy-to-understand format. The information is displayed in a dashboard format and designed to be intuitively understandable to the user. Based on this advice, the user plans and creates new content. Furthermore, the user can contribute to system improvement by sending feedback to the server through a feedback function. This feedback is used to continuously improve the quality of the advice provided by the system.

[0574] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0575] Step 1:

[0576] The server uses APIs to collect user data such as user posting history, reaction data, and comments from social media platforms and news sites. Inputs include user account information and social media URLs, while output is a set of user information stored in a database. JavaScript and Python are used for data crawling and API calls.

[0577] Step 2:

[0578] The server performs analysis by applying natural language processing techniques to the collected user data. In this step, Sentiment Analysis and Keyword Extraction are performed using the user data stored as input. The output is the user's sentiment score and a list of extracted keywords. Libraries such as TensorFlow and NLTK are used to analyze the data.

[0579] Step 3:

[0580] The server collects and analyzes information about current trends from external sources. In this step, the input is online data such as news articles and trends, and the output is trending topics and related keywords. Machine learning is used to automatically extract frequently occurring topics and keywords. Web scraping is performed using Python to collect data.

[0581] Step 4:

[0582] The server uses a generative AI model to generate advice for creating optimal content for the user. The input is the analysis results obtained in steps 2 and 3, and the output is advice that includes specific suggestions. The generative AI model is given the prompt, "Suggest the optimal solution for fashion posts based on past success stories," and generates specific ideas.

[0583] Step 5:

[0584] The terminal receives generated advice and visualizes and presents it in a user-friendly format. The input is the advice received from the server, and the output is a dashboard or graphical interface that the user can view. Front-end technologies using JavaScript and HTML / CSS are used to organize and display the information.

[0585] Step 6:

[0586] The user creates content based on the provided advice and returns feedback on the results to the server. The input is the results and opinions of the actions the user has taken, and the output is data stored on the server as feedback information. This allows the system to improve the accuracy of future advice.

[0587] (Application Example 1)

[0588] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0589] In today's information society, individual information providers need to formulate optimal information dissemination strategies based on their past communication history and the reactions of their recipients. However, there is a lack of technology to effectively analyze past information and current trends and generate personalized advice. As a result, many information providers are unable to obtain appropriate guidance and are unable to maximize their influence.

[0590] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0591] In this invention, the server includes means for collecting user information, means for analyzing the user information using natural language processing, and means for collecting and analyzing trending data. This enables users to receive optimal guidance based on their past communication history and trends, and to further formulate personalized information dissemination strategies.

[0592] "User information" refers to data that includes the past content of information providers and the responses of recipients.

[0593] "Natural language processing" is a technology that allows computers to analyze and understand human language, and in this invention, it is used to analyze user information.

[0594] "Current trends data" refers to a collection of information that indicates current fashions and trends in society and the market.

[0595] "Guidelines" are specific advice and suggestions that users should follow to optimize their information dissemination.

[0596] A "personalized information dissemination strategy" is an effective and efficient information dissemination plan that users develop based on their own characteristics and needs.

[0597] This invention is a system consisting of a server that collects and analyzes information, a terminal that presents the information, and a user who ultimately utilizes the information.

[0598] The server collects user information and performs analysis using natural language processing. This allows for a detailed analysis of users' past information sharing and responses, and the extraction of success factors. Furthermore, the server collects trending data from external sources to identify current trends and fads. In this process, the server uses natural language processing techniques based on TensorFlow and additional APIs (such as the Google Cloud Vision API) to process text and image data.

[0599] Based on the analysis results, the server generates personalized information dissemination guidelines for each user. These guidelines may include specific information content and timing. The generated guidelines are visualized in an easy-to-understand format and sent to the user's device. The device displays these guidelines in a dashboard format to assist the user in formulating their own information dissemination strategy.

[0600] Users build their own information dissemination strategies based on the provided guidelines and implement optimal information dissemination. For example, if a user is disseminating information about travel, analysis might reveal that past posts with a sea theme were popular, and that beach resorts are currently trending. Based on this information, the server generates specific guidelines such as "It would be good to post information with a beach resort theme next weekend" and presents them to the user via their device.

[0601] An example of a prompt in a generative AI model would be: "The user's past posts often include images of beaches, which are very popular. Furthermore, beach resorts are currently trending. Based on this information, please provide the user with the best guidance for their next post."

[0602] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0603] Step 1:

[0604] The server collects user information. This information includes past posts, browsing history, and reaction data (such as "likes" and comments). This information is collected on the server as input data, and a dataset for analysis is prepared as output. Specifically, a database management system is used to obtain log data regarding user behavior.

[0605] Step 2:

[0606] The server analyzes user information using natural language processing. The input is the dataset prepared in Step 1, and natural language processing techniques (e.g., TensorFlow) are applied to identify user interests and success factors. The output is user behavioral characteristics based on the analysis. Specifically, text analysis is performed to identify frequently occurring words and sentiment analysis.

[0607] Step 3:

[0608] The server collects trending data from external sources. It obtains trend information using web scraping and APIs as input and transfers it to the server. The output is a dataset showing current trends. Specifically, it obtains trending information from the Twitter API and news feeds.

[0609] Step 4:

[0610] The server integrates user information and trending data to generate guidelines. The input combines user characteristics from step 2 and trending data from step 3, and uses a generative AI model to create optimal guidelines. The output is specific advice regarding particular information dissemination. Specifically, the generative model might suggest, "It would be good to disseminate information with a beach resort theme next weekend."

[0611] Step 5:

[0612] The terminal visualizes the guidelines received from the server and presents them to the user. The input is the guideline information generated in step 4, and the output is a dashboard that the user can view. Specifically, the guidelines are displayed on a web interface or mobile app and designed to be easily understood by the user.

[0613] Step 6:

[0614] Users optimize their information dissemination strategy based on the provided guidelines. They receive the guidelines provided in Step 5 as input and develop their own information dissemination plan as output. Specifically, users adjust their content creation and posting schedules according to the guidelines and disseminate new information at the appropriate time.

[0615] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0616] This invention is a system that provides users with more personalized content creation advice by utilizing user-submitted data and trend data, and further combining them with an emotion engine. This system consists of a server, terminals, and users, with the server primarily handling data collection, analysis, and advice generation, and the terminals visualizing the advice.

[0617] The server first accesses the user's past posting database to collect user data such as post content, posting time, number of likes, and comment data. In this process, the data is structured and prepared for use with the sentiment engine. Next, analysis is performed using natural language processing techniques to analyze not only the theme and topic of each post, but also the emotional aspects (positive, negative, neutral) contained in the post using the sentiment engine.

[0618] Furthermore, the server collects trend data from external social media platforms and relevant information sources and analyzes recent trends. Based on this trend data, along with analyzed user data and sentiment data, it generates content creation advice optimized for each individual user. Specifically, it suggests content styles and themes that promote specific emotions, based on the user's past success factors and current emotional state.

[0619] The generated advice is sent to the device and provided to the user. The device visualizes this information on a dashboard, allowing users to immediately use it in their daily creative activities. The visualized advice also shows emotional outcomes, allowing users to plan posts that align with their emotional state.

[0620] As a concrete example, let's say there's a user who primarily posts about travel. The server analyzes that "landscape photos" in that user's posts elicit particularly positive emotional responses. Combining this with trend data, it generates advice that posting about travel destinations and experiences themed around "relaxation" would be effective. In this way, users can effectively create content that incorporates the latest trends while being mindful of their strengths and the emotional impact they have on others.

[0621] The following describes the processing flow.

[0622] Step 1:

[0623] The server accesses the user's posting history database and collects user data such as post content, posting date and time, number of likes, and comment content. This data collection process converts the data into an appropriate format for preparation for natural language processing and sentiment analysis.

[0624] Step 2:

[0625] The server uses natural language processing (NLP) techniques to analyze the collected user data. After tokenizing the text data and performing stemming and rooming, it analyzes which themes and topics are most frequent. It also uses a sentiment engine to automatically determine the sentiment (positive, negative, neutral) embedded in each post.

[0626] Step 3:

[0627] The server collects current trend data from external social media platforms and specialized content sites, identifying particularly noteworthy topics, popular keywords, and hashtags.

[0628] Step 4:

[0629] The server generates personalized content creation advice based on analyzed user data and trend data. Leveraging sentiment analysis results from the sentiment engine, it suggests posting styles and themes tailored to the emotions the user wants to evoke. It also determines the appropriate timing and format for posting (e.g., text, images, videos).

[0630] Step 5:

[0631] The server sends the generated advice to the terminal, which then presents it to the user in a visualized format. The user can easily understand and utilize the provided advice through a graphical interface such as a dashboard.

[0632] Step 6:

[0633] Based on the advice provided, users plan their next content and actually post it. They can also send feedback to the server via their device, which allows for continuous improvement of the quality of the advice.

[0634] (Example 2)

[0635] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0636] Current information generation systems face challenges in creating information tailored to the individual needs of users and insufficient provision of effective content guidelines based on emotions and trends.

[0637] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0638] In this invention, the server includes means for collecting information, means for analyzing the information using natural language processing, and means for collecting and analyzing external data. This makes it possible to provide guidelines that are suitable for the user's needs and to generate effective information.

[0639] "Means of collecting information" refers to a system that aggregates a user's past communication content and related data, and accesses a database to obtain the necessary information.

[0640] "Means for analyzing the information using natural language processing" refers to a technical method that processes the acquired information using a computer and automatically analyzes the theme and emotions of the content.

[0641] "Methods for collecting and analyzing external data" refers to techniques for obtaining trends and related data from various sources on the internet, organizing and classifying them, and understanding current trends.

[0642] "Means for creating guidelines for information generation based on analyzed information and external data" refers to an algorithm that combines collected information and trend data to propose the most suitable information creation policy for the user.

[0643] "Means of providing generated guidelines to users" refers to a mechanism for presenting the created guidelines to users visually or by other means, so that they can be used in actual information generation activities.

[0644] "Means for analyzing users' responses to communications and identifying the factors for information success" refers to the process of analyzing users' evaluations and responses to past communications and extracting the factors for their success.

[0645] "Means of visualizing the aforementioned guidelines and presenting them in a format that is easy for users to understand" refers to a method of visually displaying the generated information generation guidelines using graphs, tables, charts, etc., and providing them in a format that users can easily understand and utilize.

[0646] A description of the embodiment for carrying out the invention will be provided.

[0647] This invention is a system for providing users with personalized information generation guidelines. This system consists of three components: a server, a terminal, and a user.

[0648] The server first collects the user's past communication data. This data collection uses an API to connect to a database and a program to execute SQL queries to manipulate the database. This program is implemented in a scripting language such as Python. Next, the server uses natural language processing techniques to analyze the user's communication content. Specifically, it uses libraries such as NLTK and SpaCy to tokenize text and classify sentiment. It can also utilize external sentiment analysis tools such as the Google Cloud Natural Language API.

[0649] Next, the server collects trend data from external sources. This involves using web scraping tools such as Beautiful Soup or Selenium to obtain real-time trend information. The collected user data and trend data are then integrated, and a generative AI model is used to create guidelines for information generation. Ideally, a sophisticated natural language generation model, such as GPT-4, should be used. An example of a prompt used here might be, "Based on past successes and current trends, propose guidelines for generating information that will have a positive impact on users."

[0650] The generated guidelines are sent from the server to the terminal, where the terminal visualizes this information. JavaScript libraries such as D3.js and Chart.js are used for visualization, displaying it as a dashboard. This allows users to easily understand the guidelines and utilize them in their own information generation activities.

[0651] Based on the provided guidelines, users generate new information and send feedback to the server. This feedback is used to improve future guideline generation. Through this process, the system can continuously provide users with valuable guidelines and improve the quality of information generation.

[0652] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0653] Step 1:

[0654] The server accesses the user database and collects the user's past communication data. The input to this process is a specific user ID, and the output is a collection of various data such as the user's posts, comments, and number of reactions. SQL queries are used to extract information from the database, and data retrieval is automated using a Python script.

[0655] Step 2:

[0656] The server analyzes the collected data using natural language processing techniques. The input is the text data obtained in step 1, and the output is the results of topic and sentiment analysis. Libraries such as NLTK and SpaCy are used to tokenize and analyze the text, and sentiment labels such as positive, negative, and neutral are assigned.

[0657] Step 3:

[0658] The server collects trend data from external sources. The input to this process is target keywords and hashtags, and the output is a dataset of trend information. Web pages are scraped using Beautiful Soup and Selenium to obtain trend information in real time.

[0659] Step 4:

[0660] The server uses analyzed user data and trend data to input prompts into a generative AI model, creating guidelines for information generation. The input consists of user sentiment analysis results and trend data, while the output is specific guidelines that should be provided to the user. The generative AI model uses GPT-4 or similar technologies and is given the prompt, "Propose guidelines for generating information that will have a positive impact on the user."

[0661] Step 5:

[0662] The server sends the generated guidelines to the terminal. The terminal visualizes the received guidelines on a dashboard. The input is the guidelines generated from the server, and the output is the visualized information presented to the user. Libraries such as D3.js and Chart.js are used for visualization, displaying the guidelines in a user-friendly format.

[0663] Step 6:

[0664] Based on the provided guidelines, users send feedback to the server to generate information. The input consists of the user's evaluation and impressions after use, while the output is feedback data that helps improve the guidelines for the next cycle. This feedback is recorded in the server's database and used in the next cycle.

[0665] (Application Example 2)

[0666] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0667] With the increasing diversification of information distribution in modern times, there is a challenge in accurately suggesting information resources that match the individual interests and emotional states of users. In particular, there is a need to suggest information resources that take into account users' past successes and emotional responses, but conventional systems have found it difficult to achieve this efficiently.

[0668] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0669] In this invention, the server includes means for collecting user information, means for analyzing the user information using natural language processing, and means for collecting and analyzing trending information. This makes it possible to analyze the user's emotional state and suggest information resources that are appropriate to it.

[0670] "User information" refers to data related to a user, such as their past activity history, ratings, and comments.

[0671] "Natural language processing" is a technology that enables computers to understand and analyze text written by humans.

[0672] "Trend information" refers to data about topics or subjects that have gained widespread popularity within a specific period.

[0673] "Information resources" refers to all content and media that users can consume or utilize.

[0674] "Emotional state" refers to the user's emotions at that particular moment, inferred from their text data and other information.

[0675] To implement this invention, it is necessary to construct a system in which three elements—a server, a terminal, and a user—work in coordination.

[0676] The server is responsible for collecting user information and trending information, and analyzing the necessary data. User information includes past viewing history, ratings, and comments, which the server collects. Trending information is collected from external sources. Using this information, natural language processing is performed to analyze the user's emotional state. Based on this, the server generates advice to suggest the most suitable information resources. This process includes using sentiment analysis tools such as Amazon Comprehend and collecting trending information using the Twitter API.

[0677] The terminal plays a role in visualizing the advice sent from the server and presenting it in a format that is easy for the user to understand intuitively. This information is displayed, for example, on a dashboard designed using Flutter, and suggests information resources tailored to the user's needs.

[0678] Users can select and utilize information resources that interest them based on the advice provided using their own devices. This allows users to enjoy content that matches their emotional state.

[0679] For example, if a movie-loving user is determined to be in a "relaxed" state through server analysis, new and trending movies, or works with a relaxing theme tailored to their mood, will be suggested to that user. Through this process, users can obtain the most suitable information resources for their current emotional state. It is possible to generate suggestions using a prompt such as, "Suggest relaxing movies based on the user's recent positive emotional state."

[0680] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0681] Step 1:

[0682] The server retrieves user information. Specifically, it collects user viewing history, ratings, and comments from the database. At this stage, the input is user information from the database, and the output is the collected structured data.

[0683] Step 2:

[0684] The server analyzes user information collected using natural language processing. This process utilizes Amazon Comprehend to extract emotional aspects from text data. The input is structured user information, and the output is analyzed data including emotional states. Specifically, it performs sentiment analysis on evaluation comments and assigns positive, negative, or neutral labels.

[0685] Step 3:

[0686] The server collects trending information from external sources. This step uses the Twitter API to retrieve the latest topics and trending data that users are interested in. The input is raw data from external sources, and the output is analyzable trending data. Specifically, trending keywords are extracted and stored in a database.

[0687] Step 4:

[0688] The server generates advice to suggest the most suitable information resources to the user, based on the analyzed user information and collected trend information. This process uses a generative AI model, taking a prompt as input and outputting the best suggestions. For example, it might use the prompt, "Based on the user's recent positive emotional state, please suggest a relaxing movie."

[0689] Step 5:

[0690] The terminal visualizes the advice received from the server. The input is the advice data sent from the server, and the output is a dashboard display that the user can visually confirm. Specifically, it is displayed on the interface using Flutter.

[0691] Step 6:

[0692] The user refers to visualized advice on the device, selects and uses information resources of interest based on that advice. This step primarily involves the user selecting the most suitable information resources; the input is visualized advice, and the output is actionable actions corresponding to the user's selection.

[0693] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0694] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0695] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0696] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0697] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0698] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0699] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0700] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0701] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0702] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0703] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0704] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0705] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0706] 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.

[0707] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0708] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0709] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0710] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0711] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0712] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0713] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0714] The following is further disclosed regarding the embodiments described above.

[0715] (Claim 1)

[0716] Means of collecting user data,

[0717] A means for analyzing the user data using natural language processing,

[0718] Methods for collecting and analyzing trend data,

[0719] A means for generating advice for content creation based on the aforementioned user data and trend data,

[0720] Means for providing the aforementioned advice to the user,

[0721] A system that includes this.

[0722] (Claim 2)

[0723] The system according to claim 1, comprising means for analyzing user reactions to posts based on the user data and identifying success factors for content.

[0724] (Claim 3)

[0725] The system according to claim 1, comprising means for visualizing the aforementioned advice and presenting it in a format that is easy for the user to understand.

[0726] "Example 1"

[0727] (Claim 1)

[0728] Means of collecting information about users,

[0729] A means for analyzing the information using natural language processing,

[0730] Means for collecting and analyzing information on current trends,

[0731] A means for generating advice for content creation based on the aforementioned user information and trend information,

[0732] A means of visually presenting and providing the aforementioned advice to the user,

[0733] A system that includes this.

[0734] (Claim 2)

[0735] The system according to claim 1, comprising means for analyzing user reactions to posts and identifying success factors for content based on the information relating to the user.

[0736] (Claim 3)

[0737] The system according to claim 1, comprising means for presenting the generated advice in a format that the user can intuitively understand.

[0738] "Application Example 1"

[0739] (Claim 1)

[0740] Means of collecting user information,

[0741] A means for analyzing the user information using natural language processing,

[0742] Means for collecting and analyzing trending data,

[0743] A means for generating guidelines for information dissemination based on the aforementioned user information and trend data,

[0744] Means for providing the aforementioned guidelines to the user,

[0745] Based on the aforementioned guidelines, the following means are provided to support users in formulating personalized information dissemination strategies:

[0746] A system that includes this.

[0747] (Claim 2)

[0748] The system according to claim 1, comprising means for analyzing user responses to posts based on the user information and identifying factors for the success of the information.

[0749] (Claim 3)

[0750] The system according to claim 1, comprising means for visualizing the aforementioned guidelines and presenting them in a format that is easy for the user to understand.

[0751] "Example 2 of combining an emotion engine"

[0752] (Claim 1)

[0753] Means of collecting information,

[0754] A means for analyzing the information using natural language processing,

[0755] Means for collecting and analyzing external data,

[0756] A means of creating guidelines for information generation based on analyzed information and external data,

[0757] Means for providing the generated guidelines to users,

[0758] A system that includes this.

[0759] (Claim 2)

[0760] The system according to claim 1, comprising means for analyzing the user's response to communication based on the aforementioned information and identifying the success factors of the information.

[0761] (Claim 3)

[0762] The system according to claim 1, comprising means for visualizing the aforementioned guidelines and presenting them in a format that is easy for users to understand.

[0763] "Application example 2 when combining with an emotional engine"

[0764] (Claim 1)

[0765] Means of collecting user information,

[0766] A means for analyzing the user information using natural language processing,

[0767] Means for collecting and analyzing trend information,

[0768] A means for generating advice for creating information resources based on the aforementioned user information and trend information,

[0769] Means for providing the aforementioned advice to the user,

[0770] A means of analyzing the user's emotional state and suggesting suitable information resources,

[0771] A system that includes this.

[0772] (Claim 2)

[0773] The system according to claim 1, comprising means for analyzing the user's response to information intake based on the user information and identifying the success factors of the information resource.

[0774] (Claim 3)

[0775] The system according to claim 1, comprising means for visualizing the aforementioned advice and presenting it in a format that is easy for the user to understand. [Explanation of Symbols]

[0776] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting user data, A means for analyzing the user data using natural language processing, Methods for collecting and analyzing trend data, A means for generating advice for content creation based on the aforementioned user data and trend data, Means for providing the aforementioned advice to the user, A system that includes this.

2. The system according to claim 1, comprising means for analyzing user reactions to posts based on the user data and identifying success factors for content.

3. The system according to claim 1, comprising means for visualizing the aforementioned advice and presenting it in a format that is easy for the user to understand.

Images