System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting data; means for pre-processing the collected data; analytical means using generative artificial intelligence for integrating the pre-processed data; and means for storing and displaying the results of the analysis.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's society, consumer needs and trends are changing rapidly and diversified, and companies need to respond quickly to these changes. However, traditional market research methods require a lot of time and effort, making them less responsive and more costly. Trend data is also scattered across multiple social networking services, and there is a lack of effective ways to collect and analyze it. Furthermore, the data obtained often contains irrelevant information and duplicate data, making manual cleansing of it inefficient. [Means for solving the problem]

[0005] This invention provides a data processing system that automatically collects trend data from multiple social networking services, cleans it, and converts it into a unified format. It then analyzes the preprocessed data using generative AI and extracts market needs from the integrated trend data. It also includes a means for saving the analysis results and providing them on a dashboard that users can visually check. This system enables users to quickly and efficiently grasp market trends and develop and plan products based on them.

[0006] A "means for collecting data" is a means for automatically obtaining trend data from multiple social network services.

[0007] "Preprocessing of collected data" refers to processing such as filtering and format conversion to remove irrelevant information and duplicate data from the collected trend data.

[0008] "Generative AI analytics" refers to artificial intelligence-based techniques used to integrate and analyze pre-processed data, which can combine information from different data sources to generate meaningful insights.

[0009] "Means for saving and displaying analysis results" refers to the means for saving the analysis results obtained by the generative AI in a database and displaying them on a dashboard or other device that can be visually confirmed by the user.

[0010] A "social network service" is an internet service for sharing information and interacting online, and in this context refers specifically to a platform that provides trend data.

[0011] "Trend data" is information about topics and keywords frequently mentioned by users on social networking services within a specific period of time.

[0012] "Cleansing" is a preprocessing process that removes irrelevant information and duplicate data from collected data to make it suitable for analysis.

[0013] "Market needs" refer to the demands and desires related to the products and services that consumers currently desire, and are important information for companies to use in designing product development and marketing strategies.

[0014] A "dashboard" is a visual interface that allows users to easily view and understand analysis results, and displays data in the form of graphs, charts, etc. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention relates to a system that automatically collects trend data from multiple social network services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. Specific embodiments for implementing this system are described below.

[0037] First, the server uses a data collection means to collect trend data from multiple social networking services, such as YouTube (registered trademark) and X (formerly Twitter). Specifically, the server obtains data related to a specified keyword (e.g., "plant cultivation app") through the API of each SNS. This data includes video information on YouTube (title, poster, number of views, posting date, etc.) and tweet information on X (formerly Twitter) (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0038] Next, the server preprocesses the collected data. First, data cleansing is performed to remove irrelevant information and duplicate data. Specifically, filtering rules are applied to remove advertisements and spam posts, and duplicate data is identified and deleted or merged. Next, a data format unification procedure is performed to convert data from different social media platforms into entities with a standard format (for example, YouTube title as "title," poster as "author," number of views as "views," tweet content from X (formerly Twitter) as "content," user name as "username," and posting date and time as "date").

[0039] The server then supplies the unified data to the Generator AI, which then integrates and analyzes the preprocessed trend data. For example, it merges data sets related to "plant growing apps" obtained from YouTube and X (formerly Twitter) to extract and analyze common keywords and patterns. The Generator AI then generates insights based on the functions and features desired by users and current trends. For example, it extracts user-desired features such as "real-time growth records" and "plant watering notifications."

[0040] The server also has a means for storing the analysis results of the generative AI in a database and displaying them on a dashboard that can be visually accessed by users. Specifically, the server creates templates for visualizing the analysis results and providing them in formats that are easy for users to understand (graphs, charts, etc.). Users can then access the dashboard using their devices and view information based on current trends and market needs.

[0041] For example, when a user accesses the dashboard, trend data and market needs related to "plant cultivation apps" (such as real-time growth records, watering notification functions, and fertilizer information functions) are displayed. This allows users to efficiently develop and plan new products.

[0042] The processing flow will be explained below.

[0043] Step 1:

[0044] The server begins collecting data. Specifically, it obtains trend data for a specific keyword (e.g., "plant cultivation app") through the APIs of YouTube and X (formerly Twitter). It collects video information (title, poster, number of views, posting date, etc.) from the YouTube API, and tweet information (content, user name, posting date and time, number of retweets, number of likes, etc.) from the X (formerly Twitter) API.

[0045] Step 2:

[0046] The server stores the collected trend data in a database, which makes the data easily accessible for subsequent processing.

[0047] Step 3:

[0048] The server performs data cleansing, applying filtering rules to remove irrelevant information such as advertisements and spam posts, and identifying duplicate data, removing or merging the duplicates.

[0049] Step 4:

[0050] The server converts the preprocessed data into a unified format. It maps video information obtained from YouTube and tweet information obtained from X (formerly Twitter) to common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0051] Step 5:

[0052] The server provides the unified data to the Generator AI, which then analyzes the pre-processed data and extracts interesting patterns and insights from the integrated trend data. For example, it analyzes the features of a "plant growing app" and the functions users want.

[0053] Step 6:

[0054] The server stores the results of the generated AI's analysis in a database, allowing users to access this data later.

[0055] Step 7:

[0056] The server visualizes the analysis results and creates templates for displaying them on a dashboard. For example, it converts the analysis results into graphs and charts and provides them in a format that is easy for users to understand.

[0057] Step 8:

[0058] Users access the dashboard using their devices. On the dashboard, users can view current trends and market needs and use them to develop and plan products. For example, analysis results for a "plant cultivation app" are displayed on the dashboard, and users can check information such as real-time growth records, watering notification functions, and fertilizer information functions.

[0059] Example 1

[0060] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0061] Conventional trend data analysis systems have the drawback of requiring a lot of time and effort to collect, preprocess, and integrate data from multiple online communication platforms. Furthermore, it is difficult to standardize different data formats or visualize data, resulting in analysis results that are often difficult to understand intuitively. This makes it difficult for users to make quick and accurate decisions.

[0062] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0063] In this invention, the server includes a means for collecting data, a means for pre-processing the collected data, a means for unifying the pre-processed data, an analysis means using generative AI to integrate the pre-processed data, a means for saving and displaying the analysis results, and a means for visualizing the analysis results, thereby enabling the efficient collection of trend data from multiple online communication platforms, unifying the data into a standard format, and analyzing and visualizing the data using generative AI, thereby enabling users to quickly and accurately grasp market trends.

[0064] "Data collection instrument" means a combination of software and hardware for collecting data based on designated keywords from online communication platforms.

[0065] A "pre-processing means" is a part of the system that runs algorithms and rules on collected data to cleanse and format it.

[0066] "Data formatting standardization measures" are procedures and programs for converting data collected from different platforms into a common format.

[0067] "Generative AI-based analytical tools" are AI models that analyze collected and pre-processed data to generate common patterns and insights.

[0068] "Means for storing and displaying" refers to the system configuration for storing the analysis results in a database and displaying the results to the user using a visualization template.

[0069] A "visualization tool" is a software component that intuitively displays analysis results in graphs, charts, etc.

[0070] "Multiple online communication platforms" refer to services aimed at sharing information and communicating over the Internet, such as YouTube and X (formerly Twitter).

[0071] The present invention relates to a system that automatically collects trend data from multiple online communication platforms, preprocesses and integrates it, analyzes it using generative artificial intelligence (generative AI), and stores and displays the results in a database. Specific embodiments for implementing the present invention are described below.

[0072] First, the server uses data collection means to collect trend data from multiple online communication platforms, such as YouTube and X (formerly Twitter). To do this, it uses the API of each platform. For example, it uses the YouTube API to collect video information related to "plant growing apps" (title, poster, number of views, posting date), and then uses the X (formerly Twitter) API to obtain tweet information related to the same keyword (tweet content, user name, posting date and time, number of retweets, number of likes).

[0073] Next, the server preprocesses the collected data. This data cleansing process removes irrelevant information and duplicate data. Specifically, it applies filtering rules to remove advertisements and spam posts, and identifies and merges or deletes duplicate data. It then standardizes data from different platforms into a standard format. For example, it converts YouTube video titles to "title," posters to "authors," view counts to "views," tweet content from X (formerly Twitter) to "content," usernames to "username," and posting dates and times to "date."

[0074] The server then supplies the preprocessed data to a generative AI, which analyzes the combined data set and extracts common keywords and patterns. For example, it analyzes data related to "plant-growing apps" and extracts the functions and features desired by users (e.g., "real-time growth records" and "plant watering notifications"). The generative AI performs this analysis using natural language processing and machine learning techniques.

[0075] The server further includes a means for storing the analysis results of the generative AI in a database and displaying them on a dashboard that can be visually accessed by users. Visualization templates such as graphs and charts are used to visualize the analysis results. This allows users to access the dashboard using their terminals and easily check trend data and market needs.

[0076] For example, when a user accesses the dashboard, the latest trend data and market needs for "plant cultivation apps" (e.g., "real-time growth record," "watering notification function," "fertilizer information provision function") are displayed. Based on this information, users can efficiently develop and plan new products.

[0077] Examples of prompts include the following as input to a generative AI model:

[0078] "Collect data related to 'plant growing apps' from YouTube and X (formerly Twitter), preprocess it (data cleansing and formatting), and then feed it to the generative AI to analyze common keywords and market needs. Store the results in a database and visualize them on a dashboard for display to users."

[0079] In this way, a concrete form for carrying out the invention is provided, and it becomes possible to construct a system that allows users to efficiently collect and analyze trend data and visually understand the results.

[0080] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0081] Step 1: Data collection

[0082] The server collects trend data from multiple online communication platforms such as YouTube and X (formerly Twitter). It uses a specified keyword (e.g., "plant cultivation app") as input. Specifically, the server sends a request to the YouTube API to obtain video information (title, poster, number of views, and posting date) that matches the keyword. Similarly, it uses the X (formerly Twitter) API to obtain tweet information (tweet content, user name, posting date and time, number of retweets, and number of likes) that matches the keyword. The output is the collected dataset.

[0083] Step 2: Data cleansing

[0084] The server preprocesses the collected data. It takes as input the dataset collected in step 1. Specifically, it applies filtering rules to remove irrelevant information (advertisements, spam posts), and identifies and removes or merges duplicates of identical data. The output is a cleansed dataset.

[0085] Step 3: Standardize data formats

[0086] The server formats the cleansed data into a standard format. The cleansed dataset from step 2 is used as input. Specifically, it converts YouTube video information and X (formerly Twitter) tweet information into a unified format. For example, the YouTube title is converted to "title," the poster is converted to "author," the number of views is converted to "views," the content of X's tweet is converted to "content," the user name is converted to "username," and the posting date and time is converted to "date." The output is a dataset unified into a standard format.

[0087] Step 4: Data analysis

[0088] The server supplies the preprocessed data to the Generative AI. The unified dataset from step 3 is used as input. Specifically, the Generative AI analyzes the unified dataset and extracts common keywords and patterns. For example, it identifies functions and features related to a "plant growing app" (e.g., real-time growth recording, watering notification function, etc.). The output is the analysis results.

[0089] Step 5: Save the analysis results

[0090] The server stores the analysis results from the generated AI in a database. It uses the analysis results obtained in step 4 as input. Specifically, it inserts the analysis results into the appropriate table in the database for quick access. The output is the analysis results stored in the database.

[0091] Step 6: Refresh the dashboard

[0092] The server visualizes the analysis results and updates the dashboard. It uses the analysis results saved in step 5 as input. Specifically, it converts the results into graphs and charts and displays them on the dashboard in a user-friendly format. The output is an updated dashboard with the visualized analysis results.

[0093] Step 7: User Views Dashboard

[0094] The user accesses the dashboard using a device and checks the analysis results. The dashboard updated in step 6 is used as input. Specifically, the user opens a browser, accesses the dashboard URL, and views the latest trend data and market needs related to "plant cultivation apps" (e.g., "real-time growth records," "watering notification function," etc.). The output is the information obtained by the user.

[0095] (Application example 1)

[0096] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0097] Traditional advertising strategies often involve manually collecting and analyzing trend data, making it difficult to quickly respond to market changes. Furthermore, there is a lack of automated systems for aggregating data from multiple social networking services and formulating effective advertising strategies. Therefore, there is a need to quickly deliver advertising messages and campaigns based on the latest trends in real time.

[0098] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0099] In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, an analysis means using generative artificial intelligence to integrate the preprocessed data, a means for saving and displaying the analysis results, and a means for visualizing the generated analysis results and proposing advertising strategies. This makes it possible to automatically collect and analyze trend data from multiple social network services in real time and quickly propose effective advertising messages and campaigns.

[0100] "Data collection instrument" means any device or software that automatically obtains trend data from multiple social networking services.

[0101] "Means for pre-processing collected data" refers to systems and processes for removing irrelevant information and redundant data from collected trend data and standardizing the data format.

[0102] "Analytical means using generative artificial intelligence to integrate pre-processed data" refers to algorithms or programs that integrate pre-processed data and analyze it using AI to extract trends and patterns.

[0103] "Means for storing and displaying analysis results" refers to software or tools for storing the results of AI analysis in a database and displaying them in a visual format such as graphs or charts.

[0104] "Means for visualizing the generated analysis results and proposing advertising strategies" refers to systems or applications that visually display the results to propose ideas and messages for advertising campaigns based on the analysis results generated by AI.

[0105] "Social Network Service" means an online platform that enables users to share content and communicate.

[0106] "Trend Data" refers to data and information on social networking services that reflects user interests and topics within a specific period of time.

[0107] To implement this invention, a server, a data collection mechanism, a data preprocessing mechanism, a generation AI analysis mechanism, a display mechanism, and a user terminal are required.

[0108] Data collection

[0109] The server obtains trend data using APIs that collect data from multiple social networking services. Data related to a specific keyword, such as "plant growing app," is automatically obtained from YouTube and X (formerly Twitter). This data collection process is carried out using YouTube's API key and Twitter's Bearer token.

[0110] Data Preprocessing

[0111] The collected data is cleansed by a data preprocessing mechanism within the server. Specifically, irrelevant information and spam posts are filtered out, and duplicate data is deleted. In addition, data obtained from different social networking services is converted into a standard format (e.g., YouTube video titles are standardized as "title" and Twitter tweet content as "content").

[0112] Generative AI analysis

[0113] The pre-processed data is fed into a generative AI analysis mechanism on the server. An AI model (e.g., GPT-3 (registered trademark)) is used to analyze the data and extract trends and patterns. The AI ​​uses prompts to generate messages and ideas for advertising campaigns. For example, the analysis can be performed using prompts such as:

[0114] "Analyze the following YouTube video and suggest advertising strategies:\nThis plant care app offers real-time growth recording and watering notifications. What advertising messages would be effective for promoting these features?"

[0115] Saving and displaying results

[0116] The analysis results generated by the generative AI are stored in a database. The stored results are visualized in the form of a dashboard by the server's display mechanism. The dashboard uses Matplotlib or a similar visualization tool to display the analysis results in visual formats such as graphs and charts.

[0117] User device operation

[0118] Users access the dashboard using devices such as smartphones or smart glasses, which displays analyzed advertising campaign suggestions and messages, allowing users to quickly develop advertising strategies suited to their market.

[0119] This allows users to quickly respond to the latest trends and execute effective advertising campaigns. The entire process is automated, eliminating the need for manual data collection and analysis.

[0120] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0121] Step 1:

[0122] Data collection

[0123] The server collects trend data related to specific keywords from social networking services such as YouTube and Twitter. Specifically, it uses YouTube's API key to obtain video information (title, number of views, poster, posting date, etc.), and uses Twitter's Bearer token to obtain tweet information (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0124] Input: Keywords (e.g. "plant growing app"), YouTube API key, Twitter Bearer token

[0125] Output: Trend data (video information, tweet information)

[0126] Step 2:

[0127] Data Preprocessing

[0128] The server preprocesses the collected trend data. First, it filters out irrelevant information (such as advertisements and spam posts) and duplicate data. Second, it standardizes the data format. For example, YouTube video information is converted to "title," "author," "views," and "date," while Twitter tweet information is converted to "content," "username," "likes," and "date."

[0129] Input: Trend data

[0130] Output: Preprocessed data in a standard format

[0131] Step 3:

[0132] Generative AI analysis

[0133] The server then supplies the preprocessed data to a generative AI model (e.g., GPT-3) for analysis. Specifically, the data is integrated and common keywords and patterns are extracted. The generative AI model then uses a prompt to generate analysis results. For example, the prompt could be, "Analyze the following YouTube video and suggest advertising strategies:\nThis plant care app offers real-time growth recording and watering notifications. What advertising messages would be effective for promoting these features?"

[0134] Input: Preprocessed data in standard format, prompt statements

[0135] Output: AI analysis results (advertising strategy proposals)

[0136] Step 4:

[0137] Saving and displaying results

[0138] The server stores the analysis results of the generative AI in a database. When storing the results, they are appropriately categorized by item. The stored data is then used to display the results on a dashboard. On the dashboard, the analysis results are visualized using graphs and charts, allowing users to view the results in an easily understandable format.

[0139] Input: AI analysis results

[0140] Output: Data stored in a database, visualized dashboard

[0141] Step 5:

[0142] User Use

[0143] Users access the dashboard using a smartphone or smart glasses, view the displayed analysis results, and confirm the proposed advertising strategies and messages. By providing data in an easy-to-understand format, users can quickly develop advertising campaigns that are suited to their market.

[0144] Input: Visualized dashboard

[0145] Output: User browsing and advertising strategy development

[0146] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] The present invention relates to a system that automatically collects trend data from multiple social networking services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. Additionally, by combining it with an emotion engine that recognizes user emotions, it provides deeper insight into market needs. A specific embodiment for implementing this system is described below.

[0148] 1. Data collection phase:

[0149] The server uses data collection means to collect trend data from multiple social networking services such as YouTube and X (formerly Twitter). Specifically, the server obtains data related to specified keywords (e.g., "plant cultivation app") through the API of each SNS. This data includes video information on YouTube (title, poster, number of views, posting date, etc.) and tweet information on X (formerly Twitter) (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0150] 2. Data preprocessing phase:

[0151] The server stores the collected trend data in a database and performs data cleansing. Specifically, it applies filtering rules to remove advertisements and spam posts, and identifies and deletes or merges duplicates of the same data. The server then converts the preprocessed data into a unified format. It formats video information obtained from YouTube and tweet information obtained from X (formerly Twitter) into entities with common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0152] 3. Analysis phase by generative AI:

[0153] The server provides the unified data to the Generator AI for analysis. The Generator AI integrates the pre-processed trend data and extracts interesting patterns and insights. For example, it analyzes the features of a "plant growing app" and the functions users want (e.g., real-time growth records, watering notifications, etc.).

[0154] 4. Use of Emotion Engine:

[0155] The server collects users' emotional data and uses an emotion engine to preprocess and analyze it. The emotion engine recognizes users' emotions and generates necessary metadata. For example, it collects users' emotional reactions (e.g., joy, sadness, surprise, anger, etc.) to videos and tweets they have watched.

[0156] 5. Analysis and display of integrated data:

[0157] The server integrates the emotion data and trend data and uses generative AI to extract market needs. The analysis results are saved in a database and a template is created for display on a dashboard. For example, based on the emotion data, positive reactions and requests from users regarding a "plant growing app" can be identified and displayed on the dashboard.

[0158] 6. User Use of the Dashboard:

[0159] Users can access the dashboard on their devices to view current trends and market needs, as well as insights based on user sentiment data. For example, the market needs for a "plant growing app" are shown as positive emotional responses to features like real-time growth tracking and watering notifications.

[0160] This system allows companies to perform trend analysis that takes into account user emotional data, enabling them to gain a deeper understanding of the market and plan products with greater precision.

[0161] The processing flow will be explained below.

[0162] Step 1:

[0163] The server uses data collection means to collect trend data from multiple social networking services, such as YouTube and X (formerly Twitter). Specifically, the server obtains data related to designated keywords, such as "plant cultivation app," through the API of each SNS. This data includes YouTube video information (title, poster, number of views, posting date, etc.) and X (formerly Twitter) tweet information (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0164] Step 2:

[0165] The server stores the collected trend data in a database, which makes the data easily accessible for subsequent processing.

[0166] Step 3:

[0167] The server performs data cleansing, applying filtering rules to remove irrelevant information such as advertisements and spam posts, and identifying duplicate data, removing or merging the duplicates.

[0168] Step 4:

[0169] The server converts the preprocessed data into a unified format. It formats the video information obtained from YouTube and the tweet information obtained from X (formerly Twitter) into entities with common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0170] Step 5:

[0171] The server provides the unified data to the generation AI, which then analyzes the pre-processed trend data and extracts interesting patterns and insights from the unified trend data. For example, it analyzes the features of a "plant growing app" and the functions users want (e.g., real-time growth records, watering notifications, etc.).

[0172] Step 6:

[0173] The server uses an emotion engine that recognizes users' emotions to collect emotional data provided by users. For example, it obtains emotional responses (e.g., joy, sadness, surprise, anger, etc.) to videos or tweets that users have watched. This emotional data is collected through users' activities (e.g., comments, likes, shares).

[0174] Step 7:

[0175] The server preprocesses the emotion data, removing irrelevant emotion information and noise data, and converts the emotion data into a unified format, preparing it for feeding to the generative AI.

[0176] Step 8:

[0177] The server integrates the emotion data and trend data and performs a comprehensive analysis using generative AI. This allows for the extraction of deeper insights that reflect user emotions, rather than just trends. For example, it identifies users' positive emotional reactions to a "plant growing app" and their specific requests for specific features.

[0178] Step 9:

[0179] The server stores the analysis results of the generative AI in a database, which includes the integrated results of trend data and emotion data.

[0180] Step 10:

[0181] The server visualizes the analysis results and creates templates for displaying them on a dashboard. For example, it converts the analysis results into graphs and charts and provides them in a format that is easy for users to understand.

[0182] Step 11:

[0183] Users can access the dashboard on their devices to view insights based on current trends and market needs, as well as user sentiment data. For example, market needs for a "plant growing app" are displayed, showing users' positive reactions to features like real-time growth tracking and watering notifications. This information can be used to efficiently develop and plan new products.

[0184] Example 2

[0185] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0186] Conventional market analysis systems have difficulty effectively integrating and analyzing trend data collected from multiple social networking services. In particular, the complexity of data preprocessing, sentiment data analysis, and the extraction of market needs through advanced analysis using generative AI models makes it difficult for companies to obtain fast and accurate insights.

[0187] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, a means for converting the preprocessed data into a unified format, an analysis means using a generative AI model to analyze the data converted into the unified format, and a means for saving and displaying the analysis results. This enables efficient collection, preprocessing, integration, and analysis of trend data from multiple social network services, making it possible to quickly obtain accurate insights into market needs based on user sentiment data.

[0188] "Means for data collection" refers to technical means, such as APIs and scraping technologies, used to obtain trend data based on specified keywords from multiple social networking services.

[0189] "Means for pre-processing collected data" refers to technical means for improving the quality of data by filtering and cleansing the acquired data, removing irrelevant information and duplicate data, etc.

[0190] The "means for converting preprocessed data into a unified format" refers to a technical means for converting data obtained from different social network services into common data items and into a consistent format.

[0191] "Analysis methods using generative AI models" are technical methods that provide data converted into a unified format, perform advanced analysis using generative AI models, and extract interesting patterns and insights.

[0192] "Means for storing and displaying analysis results" refers to the technical means for storing the analysis results of the generative AI model in a database and providing dashboards and templates for visually displaying them.

[0193] A "social network service" is a service that allows users to share information and interact with each other over the Internet, and refers to platforms such as YouTube and X (formerly Twitter).

[0194] This invention relates to a system that automatically collects trend data from multiple social networking services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. In addition, by combining it with an emotion engine that recognizes user emotions, it provides deeper insight into market needs. A specific embodiment for implementing this system is shown below.

[0195] The server collects trend data based on specified keywords via APIs from YouTube, X (formerly Twitter), etc. For example, for the keyword "plant growing app," it collects information such as the video title, poster, number of views, and posting date from YouTube, and information such as tweet content, user name, posting date and time, number of retweets, and number of likes from X (formerly Twitter).

[0196] The collected data is temporarily stored in a database by the server. After that, data cleansing is performed, applying filtering rules to remove advertisements and spam posts and removing or merging duplicate data. Next, the preprocessed data is reformatted into common data items and converted into a unified format. For example, video information from YouTube and tweet information from X (formerly Twitter) are reformatted into entities such as "title," "author," "content," and "username."

[0197] The server then feeds the unified data to a generative AI model for analysis. The generative AI extracts interesting patterns and insights from the integrated trend data. For example, it analyzes the features associated with a "plant growing app" and the features users want (such as real-time growth tracking and watering notifications).

[0198] In addition, the server uses an emotion engine to collect and preprocess users' emotion data to recognize their emotional reactions to the videos and tweets they watch (e.g., joy, sadness, surprise, anger, etc.). This emotion data is also analyzed and integrated with trend data.

[0199] The server then analyzes the integrated data again using a generative AI model to extract market needs. The analysis results are then stored in a database and templates are created for display on a dashboard. For example, the server identifies market needs for a "plant growing app" based on emotional data and displays positive emotional responses to features such as real-time growth records and watering notifications on a dashboard.

[0200] Finally, users can access the dashboard using their devices to view insights based on current trends, market needs, and sentiment data. For example, the market needs for a "plant growing app" are displayed, showing positive reactions to features like real-time growth tracking and watering notifications. This system allows companies to conduct trend analysis incorporating user sentiment data, enabling them to gain a deeper understanding of the market and develop more accurate product plans.

[0201] Prompt Sentence Examples

[0202] To research the market needs for a "plant growing app," please collect social media data using the following keywords. Also, analyze users' emotional responses to identify market needs. Display the results on a dashboard.

[0203] In this way, the server, terminals, and users cooperate to collect, preprocess, analyze, and display data, thereby realizing a system that can grasp market needs efficiently and accurately.

[0204] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0205] Step 1: Data collection

[0206] The server sends a request to the APIs of multiple social networking services, such as YouTube and X (formerly Twitter), using a specified keyword (e.g., "plant growing app"). This request obtains information from YouTube, such as the video title, poster, number of views, and posting date, and information from X (formerly Twitter), such as the tweet content, user name, posting date and time, number of retweets, and number of likes. The input data is the specified keyword, and the output data is detailed information obtained from each SNS.

[0207] Step 2: Storing and Cleansing the Data

[0208] The collected data is temporarily stored in a database. The server then applies filtering rules to remove advertisements and spam posts. It also identifies duplicates of the same data and deletes or merges them. The input data is the collected social media information, and the output data is the filtered, clean data.

[0209] Step 3: Standardize data formatting

[0210] The server converts the preprocessed data into a unified format. Specifically, it formats video information obtained from YouTube and tweet information obtained from X (formerly Twitter) into common data items such as "title," "author," "content," and "username." The input data is cleaned SNS information, and the output data is data converted into a unified format.

[0211] Step 4: Analyze the data with a generative AI model

[0212] The server supplies the data converted into a unified format to the generative AI model. The generative AI model analyzes the data and extracts insights. For example, it extracts the features of a "plant growing app" and the functions desired by users (real-time growth records, watering notification functions, etc.). The input data is SNS data converted into a unified format, and the output data is the insights analyzed by the generative AI model.

[0213] Step 5: Analyze the emotion data with the emotion engine

[0214] The server uses an emotion engine to collect and preprocess user emotion data. Specifically, it obtains reaction data to recognize users' emotional responses (e.g., joy, sadness, surprise, anger, etc.) to videos and tweets they have watched. The input data is the user's reaction data, and the output data is the analyzed emotion data.

[0215] Step 6: Reanalyzing the integrated data

[0216] The server integrates the analysis results from the generative AI model with the sentiment data, and then re-analyzes it using the generative AI model. This allows for deeper insights that integrate trends and sentiment. The input data is the analyzed insights and sentiment data, and the output data is the integrated market needs.

[0217] Step 7: Save and view the analysis results

[0218] The server stores the generated insights and market needs in a database and creates templates for displaying them on a dashboard. The input data is the consolidated market needs, and the output data is the data displayed on the dashboard.

[0219] Step 8: Users interact with the dashboard

[0220] Users access the dashboard using a device and view insights based on trends, market needs, and sentiment data displayed in real time. The input data are the authentication information to access the dashboard, and the output data are the insights visualized on the dashboard.

[0221] In this way, data is processed and analyzed at each step, and the results are finally displayed on a dashboard. This series of processes creates a system that can efficiently and accurately grasp market needs.

[0222] (Application example 2)

[0223] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0224] Conventional advertising analysis systems lack the functionality to comprehensively analyze social media trend data and user emotional data to plan advertising effectiveness and targeting strategies. As a result, it has been difficult for marketers to obtain specific insights to improve the effectiveness of their advertising campaigns. Furthermore, because analysis does not include emotional data, it has been difficult to improve advertising to reflect users' emotional reactions.

[0225] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0226] In this invention, the server includes a means for collecting data, a means for pre-processing the collected data, an analysis means using generative artificial intelligence to integrate the pre-processed data, a means for saving and displaying the analysis results, a means using an emotion engine to collect and analyze emotion data, and a means for extracting market needs and interesting patterns from the analysis results and providing advertising effectiveness and targeting strategies. This makes it possible to comprehensively analyze trend data on social media and user emotion data and provide specific insights to improve the effectiveness of advertising campaigns.

[0227] A "data collection instrument" is a device or system used to collect trend data and sentiment data from multiple social network services.

[0228] "Pre-processing means" refers to devices or systems that filter collected data and remove irrelevant information and duplicate data.

[0229] "Analysis means using generative artificial intelligence" refers to a device or system that integrates pre-processed data and analyzes it using a generative AI model.

[0230] "Means for saving and displaying analysis results" refers to devices or systems that save the analysis results of the generative AI model in a database and display them in a form that can be viewed by users.

[0231] "Means using an emotion engine" refers to a device or system for collecting and analyzing emotion data and identifying a user's emotional response.

[0232] "Means for extracting market needs and interesting patterns" refers to devices and systems that identify market demands and unique patterns based on the analysis results of generative artificial intelligence and emotion engines.

[0233] "Means for providing advertising effectiveness and targeting strategies" refers to devices or systems that propose strategies to increase the effectiveness of advertising campaigns based on analysis results and emotional data.

[0234] The system to realize this application example performs a series of processes: data collection, data preprocessing, analysis using generative AI, use of an emotion engine, analysis and display of the integrated data, and user use of a dashboard.

[0235] 1. Data Collection:

[0236] The server automatically collects trend data related to advertisements through the APIs of various social media services (e.g., video sharing platforms and microblogging services). This data includes the content of posts related to advertisements, user names, posting dates and times, number of reactions (e.g., likes and retweets), number of views, etc. For example, for advertisements related to plant cultivation, data is collected using keywords such as "real-time growth record."

[0237] 2. Data Preprocessing:

[0238] The server stores the collected data in a database and performs data cleansing. Specifically, it uses Python's Pandas library to filter the data, remove irrelevant information and spam posts, and eliminate duplicate data. It then converts the data into a standard format. For example, the post content is formatted as "content," the user name as "username," and the number of reactions as "reaction_count."

[0239] 3. Generative AI analysis:

[0240] The preprocessed data is fed to a generative AI model (e.g., OpenAI® GPT-4®) for analysis. The generative AI model extracts interesting patterns from the aggregated trend data and analyzes advertising features and user interest points. For example, it identifies features users want (e.g., time-lapse of growth process) from comments about "real-time growth record."

[0241] 4. Use of Emotion Engine:

[0242] The server uses an emotion engine (e.g., IBM Watson® Emotion Analysis) to analyze users' emotions regarding the collected data. The emotion engine is used to collect and analyze users' emotional responses (e.g., joy, surprise, anger, sadness, etc.) to each advertisement, which is useful for understanding how the advertisement is received.

[0243] 5. Analysis and display of integrated data:

[0244] The server combines the analysis results from the generative AI with those from the emotion engine and stores them in a database. Furthermore, based on these results, it provides predictions of advertising effectiveness and targeting strategies. Using dashboard software (e.g., Plotly Dash), it visualizes these results and displays them in a form that can be used by marketers. For example, if users like an ad about "real-time growth records," it displays that reaction as positive.

[0245] 6. User Use of the Dashboard:

[0246] Users can access the dashboard via their devices (e.g., smartphones or PCs) and view insights based on current trends, market needs, and user sentiment data. This allows them to identify areas for improvement in advertising campaigns and develop effective marketing strategies. For example, the dashboard can display "real-time growth records" showing a high number of positive emotional responses to advertising, allowing them to plan new advertising campaigns based on that information.

[0247] Example prompt sentence:

[0248] "Please share the results of your analysis of the positive comments on the 'Real-time Plant Growth Record' video on a video sharing platform. Please also include data on viewer sentiment, and identify market needs and areas for improvement in advertising."

[0249] As described above, embodiments of the present invention enable marketers to analyze the effectiveness of their advertising and optimize their advertising strategies based on insights derived from emotion data.

[0250] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0251] Step 1:

[0252] The server calls the APIs of multiple social network services to collect trend and sentiment data related to a specified keyword (e.g., "plant cultivation"). The API endpoints and keywords of each SNS are required as input, and the collected raw data (e.g., video information, tweet content, number of reactions, etc.) is obtained as output.

[0253] Step 2:

[0254] The server stores the collected raw data in a database and performs data cleansing. Specifically, it uses Pandas to filter irrelevant information and spam posts and remove duplicate data. The collected raw data is required as input, and the cleansed data is obtained as output.

[0255] Step 3:

[0256] The server converts the cleansed data into a standard format, specifically formatting the data to correspond to data items (e.g., "title", "author", "content", "username", etc.). It takes the cleansed data as input and gets the formatted data as output.

[0257] Step 4:

[0258] The server then supplies the formatted data to a generative AI (e.g., OpenAI GPT-4) for analysis. The inputs are the formatted data and a prompt, and the output is the analysis results (e.g., user interest points and ad features) from the generative AI model. A specific example of a prompt might be, "Please tell me the results of your analysis of the comments that show positive reactions to the 'Real-time Plant Growth Record' video on a video sharing platform. Please extract market needs and areas for improvement in the ad, especially including viewer sentiment data."

[0259] Step 5:

[0260] The server uses an emotion engine (e.g., IBM Watson Emotion Analysis) to analyze the user's emotional response based on the formatted data. As input, the formatted data is required, and as output, the emotion analysis results (e.g., emotion data such as joy, surprise, sadness, etc.) are obtained.

[0261] Step 6:

[0262] The server integrates the analysis results of the generative AI model and the emotion engine, and stores the final analysis results in a database. Specifically, it extracts market needs and interesting patterns, and identifies advertising effectiveness and targeting strategies. The analysis results of the generative AI model and the emotion engine are required as input, and the integrated analysis results are obtained as output.

[0263] Step 7:

[0264] The server visualizes the integrated analysis results in the form of a dashboard. Specifically, it uses dashboard software such as Plotly Dash to display them in a format that can be easily interpreted by marketers. The integrated analysis results are required as input, and the visualized dashboard is obtained as output.

[0265] Step 8:

[0266] Users access the dashboard using their devices to view insights into the effectiveness of their advertising campaigns and market needs. The input is the user's access request, and the output is the analysis results displayed on the dashboard, providing users with concrete data to optimize their advertising strategies.

[0267] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0268] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0269] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0270] [Second embodiment]

[0271] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0272] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0273] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0274] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0275] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0276] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0277] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0278] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0279] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0280] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0281] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0282] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0283] The present invention relates to a system that automatically collects trend data from multiple social network services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. Specific embodiments for implementing this system are described below.

[0284] First, the server uses data collection means to collect trend data from multiple social networking services, such as YouTube and X (formerly Twitter). Specifically, the server obtains data related to a specified keyword (e.g., "plant cultivation app") through the API of each SNS. This data includes video information on YouTube (title, poster, number of views, posting date, etc.) and tweet information on X (formerly Twitter) (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0285] Next, the server preprocesses the collected data. First, data cleansing is performed to remove irrelevant information and duplicate data. Specifically, filtering rules are applied to remove advertisements and spam posts, and duplicate data is identified and deleted or merged. Next, a data format unification procedure is performed to convert data from different social media platforms into entities with a standard format (for example, YouTube title as "title," poster as "author," number of views as "views," tweet content from X (formerly Twitter) as "content," user name as "username," and posting date and time as "date").

[0286] The server then supplies the unified data to the Generator AI, which then integrates and analyzes the preprocessed trend data. For example, it merges data sets related to "plant growing apps" obtained from YouTube and X (formerly Twitter) to extract and analyze common keywords and patterns. The Generator AI then generates insights based on the functions and features desired by users and current trends. For example, it extracts user-desired features such as "real-time growth records" and "plant watering notifications."

[0287] The server also has a means for storing the analysis results of the generative AI in a database and displaying them on a dashboard that can be visually accessed by users. Specifically, the server creates templates for visualizing the analysis results and providing them in formats that are easy for users to understand (graphs, charts, etc.). Users can then access the dashboard using their devices and view information based on current trends and market needs.

[0288] For example, when a user accesses the dashboard, trend data and market needs related to "plant cultivation apps" (such as real-time growth records, watering notification functions, and fertilizer information functions) are displayed. This allows users to efficiently develop and plan new products.

[0289] The processing flow will be explained below.

[0290] Step 1:

[0291] The server begins collecting data. Specifically, it obtains trend data for a specific keyword (e.g., "plant cultivation app") through the APIs of YouTube and X (formerly Twitter). It collects video information (title, poster, number of views, posting date, etc.) from the YouTube API, and tweet information (content, user name, posting date and time, number of retweets, number of likes, etc.) from the X (formerly Twitter) API.

[0292] Step 2:

[0293] The server stores the collected trend data in a database, which makes the data easily accessible for subsequent processing.

[0294] Step 3:

[0295] The server performs data cleansing, applying filtering rules to remove irrelevant information such as advertisements and spam posts, and identifying duplicate data, removing or merging the duplicates.

[0296] Step 4:

[0297] The server converts the preprocessed data into a unified format. It maps video information obtained from YouTube and tweet information obtained from X (formerly Twitter) to common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0298] Step 5:

[0299] The server provides the unified data to the Generator AI, which then analyzes the pre-processed data and extracts interesting patterns and insights from the integrated trend data. For example, it analyzes the features of a "plant growing app" and the functions users want.

[0300] Step 6:

[0301] The server stores the results of the generated AI's analysis in a database, allowing users to access this data later.

[0302] Step 7:

[0303] The server visualizes the analysis results and creates templates for displaying them on a dashboard. For example, it converts the analysis results into graphs and charts and provides them in a format that is easy for users to understand.

[0304] Step 8:

[0305] Users access the dashboard using their devices. On the dashboard, users can view current trends and market needs and use them to develop and plan products. For example, analysis results for a "plant cultivation app" are displayed on the dashboard, and users can check information such as real-time growth records, watering notification functions, and fertilizer information functions.

[0306] Example 1

[0307] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0308] Conventional trend data analysis systems have the drawback of requiring a lot of time and effort to collect, preprocess, and integrate data from multiple online communication platforms. Furthermore, it is difficult to standardize different data formats or visualize data, resulting in analysis results that are often difficult to understand intuitively. This makes it difficult for users to make quick and accurate decisions.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0310] In this invention, the server includes a means for collecting data, a means for pre-processing the collected data, a means for unifying the pre-processed data, an analysis means using generative AI to integrate the pre-processed data, a means for saving and displaying the analysis results, and a means for visualizing the analysis results, thereby enabling the efficient collection of trend data from multiple online communication platforms, unifying the data into a standard format, and analyzing and visualizing the data using generative AI, thereby enabling users to quickly and accurately grasp market trends.

[0311] "Data collection instrument" means a combination of software and hardware for collecting data based on designated keywords from online communication platforms.

[0312] A "pre-processing means" is a part of the system that runs algorithms and rules on collected data to cleanse and format it.

[0313] "Data formatting standardization measures" are procedures and programs for converting data collected from different platforms into a common format.

[0314] "Generative AI-based analytical tools" are AI models that analyze collected and pre-processed data to generate common patterns and insights.

[0315] "Means for storing and displaying" refers to the system configuration for storing the analysis results in a database and displaying the results to the user using a visualization template.

[0316] A "visualization tool" is a software component that intuitively displays analysis results in graphs, charts, etc.

[0317] "Multiple online communication platforms" refer to services aimed at sharing information and communicating over the Internet, such as YouTube and X (formerly Twitter).

[0318] The present invention relates to a system that automatically collects trend data from multiple online communication platforms, preprocesses and integrates it, analyzes it using generative artificial intelligence (generative AI), and stores and displays the results in a database. Specific embodiments for implementing the present invention are described below.

[0319] First, the server uses data collection means to collect trend data from multiple online communication platforms, such as YouTube and X (formerly Twitter). To do this, it uses the API of each platform. For example, it uses the YouTube API to collect video information related to "plant growing apps" (title, poster, number of views, posting date), and then uses the X (formerly Twitter) API to obtain tweet information related to the same keyword (tweet content, user name, posting date and time, number of retweets, number of likes).

[0320] Next, the server preprocesses the collected data. This data cleansing process removes irrelevant information and duplicate data. Specifically, it applies filtering rules to remove advertisements and spam posts, and identifies and merges or deletes duplicate data. It then standardizes data from different platforms into a standard format. For example, it converts YouTube video titles to "title," posters to "authors," view counts to "views," tweet content from X (formerly Twitter) to "content," usernames to "username," and posting dates and times to "date."

[0321] The server then supplies the preprocessed data to a generative AI, which analyzes the combined data set and extracts common keywords and patterns. For example, it analyzes data related to "plant-growing apps" and extracts the functions and features desired by users (e.g., "real-time growth records" and "plant watering notifications"). The generative AI performs this analysis using natural language processing and machine learning techniques.

[0322] The server further includes a means for storing the analysis results of the generative AI in a database and displaying them on a dashboard that can be visually accessed by users. Visualization templates such as graphs and charts are used to visualize the analysis results. This allows users to access the dashboard using their terminals and easily check trend data and market needs.

[0323] For example, when a user accesses the dashboard, the latest trend data and market needs for "plant cultivation apps" (e.g., "real-time growth record," "watering notification function," "fertilizer information provision function") are displayed. Based on this information, users can efficiently develop and plan new products.

[0324] Examples of prompts include the following as input to a generative AI model:

[0325] "Collect data related to 'plant growing apps' from YouTube and X (formerly Twitter), preprocess it (data cleansing and formatting), and then feed it to the generative AI to analyze common keywords and market needs. Store the results in a database and visualize them on a dashboard for display to users."

[0326] In this way, a concrete form for carrying out the invention is provided, and it becomes possible to construct a system that allows users to efficiently collect and analyze trend data and visually understand the results.

[0327] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0328] Step 1: Data collection

[0329] The server collects trend data from multiple online communication platforms such as YouTube and X (formerly Twitter). It uses a specified keyword (e.g., "plant cultivation app") as input. Specifically, the server sends a request to the YouTube API to obtain video information (title, poster, number of views, and posting date) that matches the keyword. Similarly, it uses the X (formerly Twitter) API to obtain tweet information (tweet content, user name, posting date and time, number of retweets, and number of likes) that matches the keyword. The output is the collected dataset.

[0330] Step 2: Data cleansing

[0331] The server preprocesses the collected data. It takes as input the dataset collected in step 1. Specifically, it applies filtering rules to remove irrelevant information (advertisements, spam posts), and identifies and removes or merges duplicates of identical data. The output is a cleansed dataset.

[0332] Step 3: Standardize data formats

[0333] The server formats the cleansed data into a standard format. The cleansed dataset from step 2 is used as input. Specifically, it converts YouTube video information and X (formerly Twitter) tweet information into a unified format. For example, the YouTube title is converted to "title," the poster is converted to "author," the number of views is converted to "views," the content of X's tweet is converted to "content," the user name is converted to "username," and the posting date and time is converted to "date." The output is a dataset unified into a standard format.

[0334] Step 4: Data analysis

[0335] The server supplies the preprocessed data to the Generative AI. The unified dataset from step 3 is used as input. Specifically, the Generative AI analyzes the unified dataset and extracts common keywords and patterns. For example, it identifies functions and features related to a "plant growing app" (e.g., real-time growth recording, watering notification function, etc.). The output is the analysis results.

[0336] Step 5: Save the analysis results

[0337] The server stores the analysis results from the generated AI in a database. It uses the analysis results obtained in step 4 as input. Specifically, it inserts the analysis results into the appropriate table in the database for quick access. The output is the analysis results stored in the database.

[0338] Step 6: Refresh the dashboard

[0339] The server visualizes the analysis results and updates the dashboard. It uses the analysis results saved in step 5 as input. Specifically, it converts the results into graphs and charts and displays them on the dashboard in a user-friendly format. The output is an updated dashboard with the visualized analysis results.

[0340] Step 7: User Views Dashboard

[0341] The user accesses the dashboard using a device and checks the analysis results. The dashboard updated in step 6 is used as input. Specifically, the user opens a browser, accesses the dashboard URL, and views the latest trend data and market needs related to "plant cultivation apps" (e.g., "real-time growth records," "watering notification function," etc.). The output is the information obtained by the user.

[0342] (Application example 1)

[0343] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0344] Traditional advertising strategies often involve manually collecting and analyzing trend data, making it difficult to quickly respond to market changes. Furthermore, there is a lack of automated systems for aggregating data from multiple social networking services and formulating effective advertising strategies. Therefore, there is a need to quickly deliver advertising messages and campaigns based on the latest trends in real time.

[0345] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0346] In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, an analysis means using generative artificial intelligence to integrate the preprocessed data, a means for saving and displaying the analysis results, and a means for visualizing the generated analysis results and proposing advertising strategies. This makes it possible to automatically collect and analyze trend data from multiple social network services in real time and quickly propose effective advertising messages and campaigns.

[0347] "Data collection instrument" means any device or software that automatically obtains trend data from multiple social networking services.

[0348] "Means for pre-processing collected data" refers to systems and processes for removing irrelevant information and redundant data from collected trend data and standardizing the data format.

[0349] "Analytical means using generative artificial intelligence to integrate pre-processed data" refers to algorithms or programs that integrate pre-processed data and analyze it using AI to extract trends and patterns.

[0350] "Means for storing and displaying analysis results" refers to software or tools for storing the results of AI analysis in a database and displaying them in a visual format such as graphs or charts.

[0351] "Means for visualizing the generated analysis results and proposing advertising strategies" refers to systems or applications that visually display the results to propose ideas and messages for advertising campaigns based on the analysis results generated by AI.

[0352] "Social Network Service" means an online platform that enables users to share content and communicate.

[0353] "Trend Data" refers to data and information on social networking services that reflects user interests and topics within a specific period of time.

[0354] To implement this invention, a server, a data collection mechanism, a data preprocessing mechanism, a generation AI analysis mechanism, a display mechanism, and a user terminal are required.

[0355] Data collection

[0356] The server obtains trend data using APIs that collect data from multiple social networking services. Data related to a specific keyword, such as "plant growing app," is automatically obtained from YouTube and X (formerly Twitter). This data collection process is carried out using YouTube's API key and Twitter's Bearer token.

[0357] Data Preprocessing

[0358] The collected data is cleansed by a data preprocessing mechanism within the server. Specifically, irrelevant information and spam posts are filtered out, and duplicate data is deleted. In addition, data obtained from different social networking services is converted into a standard format (e.g., YouTube video titles are standardized as "title" and Twitter tweet content as "content").

[0359] Generative AI analysis

[0360] The pre-processed data is fed into a generative AI analysis mechanism on the server. An AI model (e.g., GPT-3) is used to analyze the data and extract trends and patterns. The AI ​​uses prompts to generate messages and ideas for advertising campaigns. For example, the analysis can be performed using prompts such as:

[0361] "Analyze the following YouTube video and suggest advertising strategies:\nThis plant care app offers real-time growth recording and watering notifications. What advertising messages would be effective for promoting these features?"

[0362] Saving and displaying results

[0363] The analysis results generated by the generative AI are stored in a database. The stored results are visualized in the form of a dashboard by the server's display mechanism. The dashboard uses Matplotlib or a similar visualization tool to display the analysis results in visual formats such as graphs and charts.

[0364] User device operation

[0365] Users access the dashboard using devices such as smartphones or smart glasses, which displays analyzed advertising campaign suggestions and messages, allowing users to quickly develop advertising strategies suited to their market.

[0366] This allows users to quickly respond to the latest trends and execute effective advertising campaigns. The entire process is automated, eliminating the need for manual data collection and analysis.

[0367] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0368] Step 1:

[0369] Data collection

[0370] The server collects trend data related to specific keywords from social networking services such as YouTube and Twitter. Specifically, it uses YouTube's API key to obtain video information (title, number of views, poster, posting date, etc.), and uses Twitter's Bearer token to obtain tweet information (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0371] Input: Keywords (e.g. "plant growing app"), YouTube API key, Twitter Bearer token

[0372] Output: Trend data (video information, tweet information)

[0373] Step 2:

[0374] Data Preprocessing

[0375] The server preprocesses the collected trend data. First, it filters out irrelevant information (such as advertisements and spam posts) and duplicate data. Second, it standardizes the data format. For example, YouTube video information is converted to "title," "author," "views," and "date," while Twitter tweet information is converted to "content," "username," "likes," and "date."

[0376] Input: Trend data

[0377] Output: Preprocessed data in a standard format

[0378] Step 3:

[0379] Generative AI analysis

[0380] The server then supplies the preprocessed data to a generative AI model (e.g., GPT-3) for analysis. Specifically, the data is integrated and common keywords and patterns are extracted. The generative AI model then uses a prompt to generate analysis results. For example, the prompt could be, "Analyze the following YouTube video and suggest advertising strategies:\nThis plant care app offers real-time growth recording and watering notifications. What advertising messages would be effective for promoting these features?"

[0381] Input: Preprocessed data in standard format, prompt statements

[0382] Output: AI analysis results (advertising strategy proposals)

[0383] Step 4:

[0384] Saving and displaying results

[0385] The server stores the analysis results of the generative AI in a database. When storing the results, they are appropriately categorized by item. The stored data is then used to display the results on a dashboard. On the dashboard, the analysis results are visualized using graphs and charts, allowing users to view the results in an easily understandable format.

[0386] Input: AI analysis results

[0387] Output: Data stored in a database, visualized dashboard

[0388] Step 5:

[0389] User Use

[0390] Users access the dashboard using a smartphone or smart glasses, view the displayed analysis results, and confirm the proposed advertising strategies and messages. By providing data in an easy-to-understand format, users can quickly develop advertising campaigns that are suited to their market.

[0391] Input: Visualized dashboard

[0392] Output: User browsing and advertising strategy development

[0393] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0394] The present invention relates to a system that automatically collects trend data from multiple social networking services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. Additionally, by combining it with an emotion engine that recognizes user emotions, it provides deeper insight into market needs. A specific embodiment for implementing this system is described below.

[0395] 1. Data collection phase:

[0396] The server uses data collection means to collect trend data from multiple social networking services such as YouTube and X (formerly Twitter). Specifically, the server obtains data related to specified keywords (e.g., "plant cultivation app") through the API of each SNS. This data includes video information on YouTube (title, poster, number of views, posting date, etc.) and tweet information on X (formerly Twitter) (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0397] 2. Data preprocessing phase:

[0398] The server stores the collected trend data in a database and performs data cleansing. Specifically, it applies filtering rules to remove advertisements and spam posts, and identifies and deletes or merges duplicates of the same data. The server then converts the preprocessed data into a unified format. It formats video information obtained from YouTube and tweet information obtained from X (formerly Twitter) into entities with common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0399] 3. Analysis phase by generative AI:

[0400] The server provides the unified data to the Generator AI for analysis. The Generator AI integrates the pre-processed trend data and extracts interesting patterns and insights. For example, it analyzes the features of a "plant growing app" and the functions users want (e.g., real-time growth records, watering notifications, etc.).

[0401] 4. Use of Emotion Engine:

[0402] The server collects users' emotional data and uses an emotion engine to preprocess and analyze it. The emotion engine recognizes users' emotions and generates necessary metadata. For example, it collects users' emotional reactions (e.g., joy, sadness, surprise, anger, etc.) to videos and tweets they have watched.

[0403] 5. Analysis and display of integrated data:

[0404] The server integrates the emotion data and trend data and uses generative AI to extract market needs. The analysis results are saved in a database and a template is created for display on a dashboard. For example, based on the emotion data, positive reactions and requests from users regarding a "plant growing app" can be identified and displayed on the dashboard.

[0405] 6. User Use of the Dashboard:

[0406] Users can access the dashboard on their devices to view current trends and market needs, as well as insights based on user sentiment data. For example, the market needs for a "plant growing app" are shown as positive emotional responses to features like real-time growth tracking and watering notifications.

[0407] This system allows companies to perform trend analysis that takes into account user emotional data, enabling them to gain a deeper understanding of the market and plan products with greater precision.

[0408] The processing flow will be explained below.

[0409] Step 1:

[0410] The server uses data collection means to collect trend data from multiple social networking services, such as YouTube and X (formerly Twitter). Specifically, the server obtains data related to designated keywords, such as "plant cultivation app," through the API of each SNS. This data includes YouTube video information (title, poster, number of views, posting date, etc.) and X (formerly Twitter) tweet information (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0411] Step 2:

[0412] The server stores the collected trend data in a database, which makes the data easily accessible for subsequent processing.

[0413] Step 3:

[0414] The server performs data cleansing, applying filtering rules to remove irrelevant information such as advertisements and spam posts, and identifying duplicate data, removing or merging the duplicates.

[0415] Step 4:

[0416] The server converts the preprocessed data into a unified format. It formats the video information obtained from YouTube and the tweet information obtained from X (formerly Twitter) into entities with common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0417] Step 5:

[0418] The server provides the unified data to the generation AI, which then analyzes the pre-processed trend data and extracts interesting patterns and insights from the unified trend data. For example, it analyzes the features of a "plant growing app" and the functions users want (e.g., real-time growth records, watering notifications, etc.).

[0419] Step 6:

[0420] The server uses an emotion engine that recognizes users' emotions to collect emotional data provided by users. For example, it obtains emotional responses (e.g., joy, sadness, surprise, anger, etc.) to videos or tweets that users have watched. This emotional data is collected through users' activities (e.g., comments, likes, shares).

[0421] Step 7:

[0422] The server preprocesses the emotion data, removing irrelevant emotion information and noise data, and converts the emotion data into a unified format, preparing it for feeding to the generative AI.

[0423] Step 8:

[0424] The server integrates the emotion data and trend data and performs a comprehensive analysis using generative AI. This allows for the extraction of deeper insights that reflect user emotions, rather than just trends. For example, it identifies users' positive emotional reactions to a "plant growing app" and their specific requests for specific features.

[0425] Step 9:

[0426] The server stores the analysis results of the generative AI in a database, which includes the integrated results of trend data and emotion data.

[0427] Step 10:

[0428] The server visualizes the analysis results and creates templates for displaying them on a dashboard. For example, it converts the analysis results into graphs and charts and provides them in a format that is easy for users to understand.

[0429] Step 11:

[0430] Users can access the dashboard on their devices to view insights based on current trends and market needs, as well as user sentiment data. For example, market needs for a "plant growing app" are displayed, showing users' positive reactions to features like real-time growth tracking and watering notifications. This information can be used to efficiently develop and plan new products.

[0431] Example 2

[0432] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0433] Conventional market analysis systems have difficulty effectively integrating and analyzing trend data collected from multiple social networking services. In particular, the complexity of data preprocessing, sentiment data analysis, and the extraction of market needs through advanced analysis using generative AI models makes it difficult for companies to obtain fast and accurate insights.

[0434] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, a means for converting the preprocessed data into a unified format, an analysis means using a generative AI model to analyze the data converted into the unified format, and a means for saving and displaying the analysis results. This enables efficient collection, preprocessing, integration, and analysis of trend data from multiple social network services, making it possible to quickly obtain accurate insights into market needs based on user sentiment data.

[0435] "Means for data collection" refers to technical means, such as APIs and scraping technologies, used to obtain trend data based on specified keywords from multiple social networking services.

[0436] "Means for pre-processing collected data" refers to technical means for improving the quality of data by filtering and cleansing the acquired data, removing irrelevant information and duplicate data, etc.

[0437] The "means for converting preprocessed data into a unified format" refers to a technical means for converting data obtained from different social network services into common data items and into a consistent format.

[0438] "Analysis methods using generative AI models" are technical methods that provide data converted into a unified format, perform advanced analysis using generative AI models, and extract interesting patterns and insights.

[0439] "Means for storing and displaying analysis results" refers to the technical means for storing the analysis results of the generative AI model in a database and providing dashboards and templates for visually displaying them.

[0440] A "social network service" is a service that allows users to share information and interact with each other over the Internet, and refers to platforms such as YouTube and X (formerly Twitter).

[0441] This invention relates to a system that automatically collects trend data from multiple social networking services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. In addition, by combining it with an emotion engine that recognizes user emotions, it provides deeper insight into market needs. A specific embodiment for implementing this system is shown below.

[0442] The server collects trend data based on specified keywords via APIs from YouTube, X (formerly Twitter), etc. For example, for the keyword "plant growing app," it collects information such as the video title, poster, number of views, and posting date from YouTube, and information such as tweet content, user name, posting date and time, number of retweets, and number of likes from X (formerly Twitter).

[0443] The collected data is temporarily stored in a database by the server. After that, data cleansing is performed, applying filtering rules to remove advertisements and spam posts and removing or merging duplicate data. Next, the preprocessed data is reformatted into common data items and converted into a unified format. For example, video information from YouTube and tweet information from X (formerly Twitter) are reformatted into entities such as "title," "author," "content," and "username."

[0444] The server then feeds the unified data to a generative AI model for analysis. The generative AI extracts interesting patterns and insights from the integrated trend data. For example, it analyzes the features associated with a "plant growing app" and the features users want (such as real-time growth tracking and watering notifications).

[0445] In addition, the server uses an emotion engine to collect and preprocess users' emotion data to recognize their emotional reactions to the videos and tweets they watch (e.g., joy, sadness, surprise, anger, etc.). This emotion data is also analyzed and integrated with trend data.

[0446] The server then analyzes the integrated data again using a generative AI model to extract market needs. The analysis results are then stored in a database and templates are created for display on a dashboard. For example, the server identifies market needs for a "plant growing app" based on emotional data and displays positive emotional responses to features such as real-time growth records and watering notifications on a dashboard.

[0447] Finally, users can access the dashboard using their devices to view insights based on current trends, market needs, and sentiment data. For example, the market needs for a "plant growing app" are displayed, showing positive reactions to features like real-time growth tracking and watering notifications. This system allows companies to conduct trend analysis incorporating user sentiment data, enabling them to gain a deeper understanding of the market and develop more accurate product plans.

[0448] Prompt Sentence Examples

[0449] To research the market needs for a "plant growing app," please collect social media data using the following keywords. Also, analyze users' emotional responses to identify market needs. Display the results on a dashboard.

[0450] In this way, the server, terminals, and users cooperate to collect, preprocess, analyze, and display data, thereby realizing a system that can grasp market needs efficiently and accurately.

[0451] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0452] Step 1: Data collection

[0453] The server sends a request to the APIs of multiple social networking services, such as YouTube and X (formerly Twitter), using a specified keyword (e.g., "plant growing app"). This request obtains information from YouTube, such as the video title, poster, number of views, and posting date, and information from X (formerly Twitter), such as the tweet content, user name, posting date and time, number of retweets, and number of likes. The input data is the specified keyword, and the output data is detailed information obtained from each SNS.

[0454] Step 2: Storing and Cleansing the Data

[0455] The collected data is temporarily stored in a database. The server then applies filtering rules to remove advertisements and spam posts. It also identifies duplicates of the same data and deletes or merges them. The input data is the collected social media information, and the output data is the filtered, clean data.

[0456] Step 3: Standardize data formatting

[0457] The server converts the preprocessed data into a unified format. Specifically, it formats video information obtained from YouTube and tweet information obtained from X (formerly Twitter) into common data items such as "title," "author," "content," and "username." The input data is cleaned SNS information, and the output data is data converted into a unified format.

[0458] Step 4: Analyze the data with a generative AI model

[0459] The server supplies the data converted into a unified format to the generative AI model. The generative AI model analyzes the data and extracts insights. For example, it extracts the features of a "plant growing app" and the functions desired by users (real-time growth records, watering notification functions, etc.). The input data is SNS data converted into a unified format, and the output data is the insights analyzed by the generative AI model.

[0460] Step 5: Analyze the emotion data with the emotion engine

[0461] The server uses an emotion engine to collect and preprocess user emotion data. Specifically, it obtains reaction data to recognize users' emotional responses (e.g., joy, sadness, surprise, anger, etc.) to videos and tweets they have watched. The input data is the user's reaction data, and the output data is the analyzed emotion data.

[0462] Step 6: Reanalyzing the integrated data

[0463] The server integrates the analysis results from the generative AI model with the sentiment data, and then re-analyzes it using the generative AI model. This allows for deeper insights that integrate trends and sentiment. The input data is the analyzed insights and sentiment data, and the output data is the integrated market needs.

[0464] Step 7: Save and view the analysis results

[0465] The server stores the generated insights and market needs in a database and creates templates for displaying them on a dashboard. The input data is the consolidated market needs, and the output data is the data displayed on the dashboard.

[0466] Step 8: Users interact with the dashboard

[0467] Users access the dashboard using a device and view insights based on trends, market needs, and sentiment data displayed in real time. The input data are the authentication information to access the dashboard, and the output data are the insights visualized on the dashboard.

[0468] In this way, data is processed and analyzed at each step, and the results are finally displayed on a dashboard. This series of processes creates a system that can efficiently and accurately grasp market needs.

[0469] (Application example 2)

[0470] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0471] Conventional advertising analysis systems lack the functionality to comprehensively analyze social media trend data and user emotional data to plan advertising effectiveness and targeting strategies. As a result, it has been difficult for marketers to obtain specific insights to improve the effectiveness of their advertising campaigns. Furthermore, because analysis does not include emotional data, it has been difficult to improve advertising to reflect users' emotional reactions.

[0472] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0473] In this invention, the server includes a means for collecting data, a means for pre-processing the collected data, an analysis means using generative artificial intelligence to integrate the pre-processed data, a means for saving and displaying the analysis results, a means using an emotion engine to collect and analyze emotion data, and a means for extracting market needs and interesting patterns from the analysis results and providing advertising effectiveness and targeting strategies. This makes it possible to comprehensively analyze trend data on social media and user emotion data and provide specific insights to improve the effectiveness of advertising campaigns.

[0474] A "data collection instrument" is a device or system used to collect trend data and sentiment data from multiple social network services.

[0475] "Pre-processing means" refers to devices or systems that filter collected data and remove irrelevant information and duplicate data.

[0476] "Analysis means using generative artificial intelligence" refers to a device or system that integrates pre-processed data and analyzes it using a generative AI model.

[0477] "Means for saving and displaying analysis results" refers to devices or systems that save the analysis results of the generative AI model in a database and display them in a form that can be viewed by users.

[0478] "Means using an emotion engine" refers to a device or system for collecting and analyzing emotion data and identifying a user's emotional response.

[0479] "Means for extracting market needs and interesting patterns" refers to devices and systems that identify market demands and unique patterns based on the analysis results of generative artificial intelligence and emotion engines.

[0480] "Means for providing advertising effectiveness and targeting strategies" refers to devices or systems that propose strategies to increase the effectiveness of advertising campaigns based on analysis results and emotional data.

[0481] The system to realize this application example performs a series of processes: data collection, data preprocessing, analysis using generative AI, use of an emotion engine, analysis and display of the integrated data, and user use of a dashboard.

[0482] 1. Data Collection:

[0483] The server automatically collects trend data related to advertisements through the APIs of various social media services (e.g., video sharing platforms and microblogging services). This data includes the content of posts related to advertisements, user names, posting dates and times, number of reactions (e.g., likes and retweets), number of views, etc. For example, for advertisements related to plant cultivation, data is collected using keywords such as "real-time growth record."

[0484] 2. Data Preprocessing:

[0485] The server stores the collected data in a database and performs data cleansing. Specifically, it uses Python's Pandas library to filter the data, remove irrelevant information and spam posts, and eliminate duplicate data. It then converts the data into a standard format. For example, the post content is formatted as "content," the user name as "username," and the number of reactions as "reaction_count."

[0486] 3. Generative AI analysis:

[0487] The preprocessed data is fed into a generative AI model (e.g., OpenAI GPT-4) for analysis. The generative AI model extracts interesting patterns from the aggregated trend data and analyzes advertising features and user interest points. For example, it identifies features users want (e.g., time-lapse of growth process) from comments about "real-time growth record."

[0488] 4. Use of Emotion Engine:

[0489] The server uses an emotion engine (e.g., IBM Watson Emotion Analysis) to analyze users' emotions regarding the collected data. The emotion engine is used to collect and analyze users' emotional responses to each advertisement (e.g., joy, surprise, anger, sadness, etc.), which helps understand how the advertisement is received.

[0490] 5. Analysis and display of integrated data:

[0491] The server combines the analysis results from the generative AI with those from the emotion engine and stores them in a database. Furthermore, based on these results, it provides predictions of advertising effectiveness and targeting strategies. Using dashboard software (e.g., Plotly Dash), it visualizes these results and displays them in a form that can be used by marketers. For example, if users like an ad about "real-time growth records," it displays that reaction as positive.

[0492] 6. User Use of the Dashboard:

[0493] Users can access the dashboard via their devices (e.g., smartphones or PCs) and view insights based on current trends, market needs, and user sentiment data. This allows them to identify areas for improvement in advertising campaigns and develop effective marketing strategies. For example, the dashboard can display "real-time growth records" showing a high number of positive emotional responses to advertising, allowing them to plan new advertising campaigns based on that information.

[0494] Example prompt sentence:

[0495] "Please share the results of your analysis of the positive comments on the 'Real-time Plant Growth Record' video on a video sharing platform. Please also include data on viewer sentiment, and identify market needs and areas for improvement in advertising."

[0496] As described above, embodiments of the present invention enable marketers to analyze the effectiveness of their advertising and optimize their advertising strategies based on insights derived from emotion data.

[0497] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0498] Step 1:

[0499] The server calls the APIs of multiple social network services to collect trend and sentiment data related to a specified keyword (e.g., "plant cultivation"). The API endpoints and keywords of each SNS are required as input, and the collected raw data (e.g., video information, tweet content, number of reactions, etc.) is obtained as output.

[0500] Step 2:

[0501] The server stores the collected raw data in a database and performs data cleansing. Specifically, it uses Pandas to filter irrelevant information and spam posts and remove duplicate data. The collected raw data is required as input, and the cleansed data is obtained as output.

[0502] Step 3:

[0503] The server converts the cleansed data into a standard format, specifically formatting the data to correspond to data items (e.g., "title", "author", "content", "username", etc.). It takes the cleansed data as input and gets the formatted data as output.

[0504] Step 4:

[0505] The server then supplies the formatted data to a generative AI (e.g., OpenAI GPT-4) for analysis. The inputs are the formatted data and a prompt, and the output is the analysis results (e.g., user interest points and ad features) from the generative AI model. A specific example of a prompt might be, "Please tell me the results of your analysis of the comments that show positive reactions to the 'Real-time Plant Growth Record' video on a video sharing platform. Please extract market needs and areas for improvement in the ad, especially including viewer sentiment data."

[0506] Step 5:

[0507] The server uses an emotion engine (e.g., IBM Watson Emotion Analysis) to analyze the user's emotional response based on the formatted data. As input, the formatted data is required, and as output, the emotion analysis results (e.g., emotion data such as joy, surprise, sadness, etc.) are obtained.

[0508] Step 6:

[0509] The server integrates the analysis results of the generative AI model and the emotion engine, and stores the final analysis results in a database. Specifically, it extracts market needs and interesting patterns, and identifies advertising effectiveness and targeting strategies. The analysis results of the generative AI model and the emotion engine are required as input, and the integrated analysis results are obtained as output.

[0510] Step 7:

[0511] The server visualizes the integrated analysis results in the form of a dashboard. Specifically, it uses dashboard software such as Plotly Dash to display them in a format that can be easily interpreted by marketers. The integrated analysis results are required as input, and the visualized dashboard is obtained as output.

[0512] Step 8:

[0513] Users access the dashboard using their devices to view insights into the effectiveness of their advertising campaigns and market needs. The input is the user's access request, and the output is the analysis results displayed on the dashboard, providing users with concrete data to optimize their advertising strategies.

[0514] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0515] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0516] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0517] [Third embodiment]

[0518] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0519] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0520] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0521] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0522] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0523] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0524] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0525] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0526] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0527] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0528] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0529] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0530] The present invention relates to a system that automatically collects trend data from multiple social network services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. Specific embodiments for implementing this system are described below.

[0531] First, the server uses data collection means to collect trend data from multiple social networking services, such as YouTube and X (formerly Twitter). Specifically, the server obtains data related to a specified keyword (e.g., "plant cultivation app") through the API of each SNS. This data includes video information on YouTube (title, poster, number of views, posting date, etc.) and tweet information on X (formerly Twitter) (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0532] Next, the server preprocesses the collected data. First, data cleansing is performed to remove irrelevant information and duplicate data. Specifically, filtering rules are applied to remove advertisements and spam posts, and duplicate data is identified and deleted or merged. Next, a data format unification procedure is performed to convert data from different social media platforms into entities with a standard format (for example, YouTube title as "title," poster as "author," number of views as "views," tweet content from X (formerly Twitter) as "content," user name as "username," and posting date and time as "date").

[0533] The server then supplies the unified data to the Generator AI, which then integrates and analyzes the preprocessed trend data. For example, it merges data sets related to "plant growing apps" obtained from YouTube and X (formerly Twitter) to extract and analyze common keywords and patterns. The Generator AI then generates insights based on the functions and features desired by users and current trends. For example, it extracts user-desired features such as "real-time growth records" and "plant watering notifications."

[0534] The server also has a means for storing the analysis results of the generative AI in a database and displaying them on a dashboard that can be visually accessed by users. Specifically, the server creates templates for visualizing the analysis results and providing them in formats that are easy for users to understand (graphs, charts, etc.). Users can then access the dashboard using their devices and view information based on current trends and market needs.

[0535] For example, when a user accesses the dashboard, trend data and market needs related to "plant cultivation apps" (such as real-time growth records, watering notification functions, and fertilizer information functions) are displayed. This allows users to efficiently develop and plan new products.

[0536] The processing flow will be explained below.

[0537] Step 1:

[0538] The server begins collecting data. Specifically, it obtains trend data for a specific keyword (e.g., "plant cultivation app") through the APIs of YouTube and X (formerly Twitter). It collects video information (title, poster, number of views, posting date, etc.) from the YouTube API, and tweet information (content, user name, posting date and time, number of retweets, number of likes, etc.) from the X (formerly Twitter) API.

[0539] Step 2:

[0540] The server stores the collected trend data in a database, which makes the data easily accessible for subsequent processing.

[0541] Step 3:

[0542] The server performs data cleansing, applying filtering rules to remove irrelevant information such as advertisements and spam posts, and identifying duplicate data, removing or merging the duplicates.

[0543] Step 4:

[0544] The server converts the preprocessed data into a unified format. It maps video information obtained from YouTube and tweet information obtained from X (formerly Twitter) to common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0545] Step 5:

[0546] The server provides the unified data to the Generator AI, which then analyzes the pre-processed data and extracts interesting patterns and insights from the integrated trend data. For example, it analyzes the features of a "plant growing app" and the functions users want.

[0547] Step 6:

[0548] The server stores the results of the generated AI's analysis in a database, allowing users to access this data later.

[0549] Step 7:

[0550] The server visualizes the analysis results and creates templates for displaying them on a dashboard. For example, it converts the analysis results into graphs and charts and provides them in a format that is easy for users to understand.

[0551] Step 8:

[0552] Users access the dashboard using their devices. On the dashboard, users can view current trends and market needs and use them to develop and plan products. For example, analysis results for a "plant cultivation app" are displayed on the dashboard, and users can check information such as real-time growth records, watering notification functions, and fertilizer information functions.

[0553] Example 1

[0554] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0555] Conventional trend data analysis systems have the drawback of requiring a lot of time and effort to collect, preprocess, and integrate data from multiple online communication platforms. Furthermore, it is difficult to standardize different data formats or visualize data, resulting in analysis results that are often difficult to understand intuitively. This makes it difficult for users to make quick and accurate decisions.

[0556] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0557] In this invention, the server includes a means for collecting data, a means for pre-processing the collected data, a means for unifying the pre-processed data, an analysis means using generative AI to integrate the pre-processed data, a means for saving and displaying the analysis results, and a means for visualizing the analysis results, thereby enabling the efficient collection of trend data from multiple online communication platforms, unifying the data into a standard format, and analyzing and visualizing the data using generative AI, thereby enabling users to quickly and accurately grasp market trends.

[0558] "Data collection instrument" means a combination of software and hardware for collecting data based on designated keywords from online communication platforms.

[0559] A "pre-processing means" is a part of the system that runs algorithms and rules on collected data to cleanse and format it.

[0560] "Data formatting standardization measures" are procedures and programs for converting data collected from different platforms into a common format.

[0561] "Generative AI-based analytical tools" are AI models that analyze collected and pre-processed data to generate common patterns and insights.

[0562] "Means for storing and displaying" refers to the system configuration for storing the analysis results in a database and displaying the results to the user using a visualization template.

[0563] A "visualization tool" is a software component that intuitively displays analysis results in graphs, charts, etc.

[0564] "Multiple online communication platforms" refer to services aimed at sharing information and communicating over the Internet, such as YouTube and X (formerly Twitter).

[0565] The present invention relates to a system that automatically collects trend data from multiple online communication platforms, preprocesses and integrates it, analyzes it using generative artificial intelligence (generative AI), and stores and displays the results in a database. Specific embodiments for implementing the present invention are described below.

[0566] First, the server uses data collection means to collect trend data from multiple online communication platforms, such as YouTube and X (formerly Twitter). To do this, it uses the API of each platform. For example, it uses the YouTube API to collect video information related to "plant growing apps" (title, poster, number of views, posting date), and then uses the X (formerly Twitter) API to obtain tweet information related to the same keyword (tweet content, user name, posting date and time, number of retweets, number of likes).

[0567] Next, the server preprocesses the collected data. This data cleansing process removes irrelevant information and duplicate data. Specifically, it applies filtering rules to remove advertisements and spam posts, and identifies and merges or deletes duplicate data. It then standardizes data from different platforms into a standard format. For example, it converts YouTube video titles to "title," posters to "authors," view counts to "views," tweet content from X (formerly Twitter) to "content," usernames to "username," and posting dates and times to "date."

[0568] The server then supplies the preprocessed data to a generative AI, which analyzes the combined data set and extracts common keywords and patterns. For example, it analyzes data related to "plant-growing apps" and extracts the functions and features desired by users (e.g., "real-time growth records" and "plant watering notifications"). The generative AI performs this analysis using natural language processing and machine learning techniques.

[0569] The server further includes a means for storing the analysis results of the generative AI in a database and displaying them on a dashboard that can be visually accessed by users. Visualization templates such as graphs and charts are used to visualize the analysis results. This allows users to access the dashboard using their terminals and easily check trend data and market needs.

[0570] For example, when a user accesses the dashboard, the latest trend data and market needs for "plant cultivation apps" (e.g., "real-time growth record," "watering notification function," "fertilizer information provision function") are displayed. Based on this information, users can efficiently develop and plan new products.

[0571] Examples of prompts include the following as input to a generative AI model:

[0572] "Collect data related to 'plant growing apps' from YouTube and X (formerly Twitter), preprocess it (data cleansing and formatting), and then feed it to the generative AI to analyze common keywords and market needs. Store the results in a database and visualize them on a dashboard for display to users."

[0573] In this way, a concrete form for carrying out the invention is provided, and it becomes possible to construct a system that allows users to efficiently collect and analyze trend data and visually understand the results.

[0574] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0575] Step 1: Data collection

[0576] The server collects trend data from multiple online communication platforms such as YouTube and X (formerly Twitter). It uses a specified keyword (e.g., "plant cultivation app") as input. Specifically, the server sends a request to the YouTube API to obtain video information (title, poster, number of views, and posting date) that matches the keyword. Similarly, it uses the X (formerly Twitter) API to obtain tweet information (tweet content, user name, posting date and time, number of retweets, and number of likes) that matches the keyword. The output is the collected dataset.

[0577] Step 2: Data cleansing

[0578] The server preprocesses the collected data. It takes as input the dataset collected in step 1. Specifically, it applies filtering rules to remove irrelevant information (advertisements, spam posts), and identifies and removes or merges duplicates of identical data. The output is a cleansed dataset.

[0579] Step 3: Standardize data formats

[0580] The server formats the cleansed data into a standard format. The cleansed dataset from step 2 is used as input. Specifically, it converts YouTube video information and X (formerly Twitter) tweet information into a unified format. For example, the YouTube title is converted to "title," the poster is converted to "author," the number of views is converted to "views," the content of X's tweet is converted to "content," the user name is converted to "username," and the posting date and time is converted to "date." The output is a dataset unified into a standard format.

[0581] Step 4: Data analysis

[0582] The server supplies the preprocessed data to the Generative AI. The unified dataset from step 3 is used as input. Specifically, the Generative AI analyzes the unified dataset and extracts common keywords and patterns. For example, it identifies functions and features related to a "plant growing app" (e.g., real-time growth recording, watering notification function, etc.). The output is the analysis results.

[0583] Step 5: Save the analysis results

[0584] The server stores the analysis results from the generated AI in a database. It uses the analysis results obtained in step 4 as input. Specifically, it inserts the analysis results into the appropriate table in the database for quick access. The output is the analysis results stored in the database.

[0585] Step 6: Refresh the dashboard

[0586] The server visualizes the analysis results and updates the dashboard. It uses the analysis results saved in step 5 as input. Specifically, it converts the results into graphs and charts and displays them on the dashboard in a user-friendly format. The output is an updated dashboard with the visualized analysis results.

[0587] Step 7: User Views Dashboard

[0588] The user accesses the dashboard using a device and checks the analysis results. The dashboard updated in step 6 is used as input. Specifically, the user opens a browser, accesses the dashboard URL, and views the latest trend data and market needs related to "plant cultivation apps" (e.g., "real-time growth records," "watering notification function," etc.). The output is the information obtained by the user.

[0589] (Application example 1)

[0590] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0591] Traditional advertising strategies often involve manually collecting and analyzing trend data, making it difficult to quickly respond to market changes. Furthermore, there is a lack of automated systems for aggregating data from multiple social networking services and formulating effective advertising strategies. Therefore, there is a need to quickly deliver advertising messages and campaigns based on the latest trends in real time.

[0592] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0593] In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, an analysis means using generative artificial intelligence to integrate the preprocessed data, a means for saving and displaying the analysis results, and a means for visualizing the generated analysis results and proposing advertising strategies. This makes it possible to automatically collect and analyze trend data from multiple social network services in real time and quickly propose effective advertising messages and campaigns.

[0594] "Data collection instrument" means any device or software that automatically obtains trend data from multiple social networking services.

[0595] "Means for pre-processing collected data" refers to systems and processes for removing irrelevant information and redundant data from collected trend data and standardizing the data format.

[0596] "Analytical means using generative artificial intelligence to integrate pre-processed data" refers to algorithms or programs that integrate pre-processed data and analyze it using AI to extract trends and patterns.

[0597] "Means for storing and displaying analysis results" refers to software or tools for storing the results of AI analysis in a database and displaying them in a visual format such as graphs or charts.

[0598] "Means for visualizing the generated analysis results and proposing advertising strategies" refers to systems or applications that visually display the results to propose ideas and messages for advertising campaigns based on the analysis results generated by AI.

[0599] "Social Network Service" means an online platform that enables users to share content and communicate.

[0600] "Trend Data" refers to data and information on social networking services that reflects user interests and topics within a specific period of time.

[0601] To implement this invention, a server, a data collection mechanism, a data preprocessing mechanism, a generation AI analysis mechanism, a display mechanism, and a user terminal are required.

[0602] Data collection

[0603] The server obtains trend data using APIs that collect data from multiple social networking services. Data related to a specific keyword, such as "plant growing app," is automatically obtained from YouTube and X (formerly Twitter). This data collection process is carried out using YouTube's API key and Twitter's Bearer token.

[0604] Data Preprocessing

[0605] The collected data is cleansed by a data preprocessing mechanism within the server. Specifically, irrelevant information and spam posts are filtered out, and duplicate data is deleted. In addition, data obtained from different social networking services is converted into a standard format (e.g., YouTube video titles are standardized as "title" and Twitter tweet content as "content").

[0606] Generative AI analysis

[0607] The pre-processed data is fed into a generative AI analysis mechanism on the server. An AI model (e.g., GPT-3) is used to analyze the data and extract trends and patterns. The AI ​​uses prompts to generate messages and ideas for advertising campaigns. For example, the analysis can be performed using prompts such as:

[0608] "Analyze the following YouTube video and suggest advertising strategies:\nThis plant care app offers real-time growth recording and watering notifications. What advertising messages would be effective for promoting these features?"

[0609] Saving and displaying results

[0610] The analysis results generated by the generative AI are stored in a database. The stored results are visualized in the form of a dashboard by the server's display mechanism. The dashboard uses Matplotlib or a similar visualization tool to display the analysis results in visual formats such as graphs and charts.

[0611] User device operation

[0612] Users access the dashboard using devices such as smartphones or smart glasses, which displays analyzed advertising campaign suggestions and messages, allowing users to quickly develop advertising strategies suited to their market.

[0613] This allows users to quickly respond to the latest trends and execute effective advertising campaigns. The entire process is automated, eliminating the need for manual data collection and analysis.

[0614] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0615] Step 1:

[0616] Data collection

[0617] The server collects trend data related to specific keywords from social networking services such as YouTube and Twitter. Specifically, it uses YouTube's API key to obtain video information (title, number of views, poster, posting date, etc.), and uses Twitter's Bearer token to obtain tweet information (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0618] Input: Keywords (e.g. "plant growing app"), YouTube API key, Twitter Bearer token

[0619] Output: Trend data (video information, tweet information)

[0620] Step 2:

[0621] Data Preprocessing

[0622] The server preprocesses the collected trend data. First, it filters out irrelevant information (such as advertisements and spam posts) and duplicate data. Second, it standardizes the data format. For example, YouTube video information is converted to "title," "author," "views," and "date," while Twitter tweet information is converted to "content," "username," "likes," and "date."

[0623] Input: Trend data

[0624] Output: Preprocessed data in a standard format

[0625] Step 3:

[0626] Generative AI analysis

[0627] The server then supplies the preprocessed data to a generative AI model (e.g., GPT-3) for analysis. Specifically, the data is integrated and common keywords and patterns are extracted. The generative AI model then uses a prompt to generate analysis results. For example, the prompt could be, "Analyze the following YouTube video and suggest advertising strategies:\nThis plant care app offers real-time growth recording and watering notifications. What advertising messages would be effective for promoting these features?"

[0628] Input: Preprocessed data in standard format, prompt statements

[0629] Output: AI analysis results (advertising strategy proposals)

[0630] Step 4:

[0631] Saving and displaying results

[0632] The server stores the analysis results of the generative AI in a database. When storing the results, they are appropriately categorized by item. The stored data is then used to display the results on a dashboard. On the dashboard, the analysis results are visualized using graphs and charts, allowing users to view the results in an easily understandable format.

[0633] Input: AI analysis results

[0634] Output: Data stored in a database, visualized dashboard

[0635] Step 5:

[0636] User Use

[0637] Users access the dashboard using a smartphone or smart glasses, view the displayed analysis results, and confirm the proposed advertising strategies and messages. By providing data in an easy-to-understand format, users can quickly develop advertising campaigns that are suited to their market.

[0638] Input: Visualized dashboard

[0639] Output: User browsing and advertising strategy development

[0640] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0641] The present invention relates to a system that automatically collects trend data from multiple social networking services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. Additionally, by combining it with an emotion engine that recognizes user emotions, it provides deeper insight into market needs. A specific embodiment for implementing this system is described below.

[0642] 1. Data collection phase:

[0643] The server uses data collection means to collect trend data from multiple social networking services such as YouTube and X (formerly Twitter). Specifically, the server obtains data related to specified keywords (e.g., "plant cultivation app") through the API of each SNS. This data includes video information on YouTube (title, poster, number of views, posting date, etc.) and tweet information on X (formerly Twitter) (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0644] 2. Data preprocessing phase:

[0645] The server stores the collected trend data in a database and performs data cleansing. Specifically, it applies filtering rules to remove advertisements and spam posts, and identifies and deletes or merges duplicates of the same data. The server then converts the preprocessed data into a unified format. It formats video information obtained from YouTube and tweet information obtained from X (formerly Twitter) into entities with common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0646] 3. Analysis phase by generative AI:

[0647] The server provides the unified data to the Generator AI for analysis. The Generator AI integrates the pre-processed trend data and extracts interesting patterns and insights. For example, it analyzes the features of a "plant growing app" and the functions users want (e.g., real-time growth records, watering notifications, etc.).

[0648] 4. Use of Emotion Engine:

[0649] The server collects users' emotional data and uses an emotion engine to preprocess and analyze it. The emotion engine recognizes users' emotions and generates necessary metadata. For example, it collects users' emotional reactions (e.g., joy, sadness, surprise, anger, etc.) to videos and tweets they have watched.

[0650] 5. Analysis and display of integrated data:

[0651] The server integrates the emotion data and trend data and uses generative AI to extract market needs. The analysis results are saved in a database and a template is created for display on a dashboard. For example, based on the emotion data, positive reactions and requests from users regarding a "plant growing app" can be identified and displayed on the dashboard.

[0652] 6. User Use of the Dashboard:

[0653] Users can access the dashboard on their devices to view current trends and market needs, as well as insights based on user sentiment data. For example, the market needs for a "plant growing app" are shown as positive emotional responses to features like real-time growth tracking and watering notifications.

[0654] This system allows companies to perform trend analysis that takes into account user emotional data, enabling them to gain a deeper understanding of the market and plan products with greater precision.

[0655] The processing flow will be explained below.

[0656] Step 1:

[0657] The server uses data collection means to collect trend data from multiple social networking services, such as YouTube and X (formerly Twitter). Specifically, the server obtains data related to designated keywords, such as "plant cultivation app," through the API of each SNS. This data includes YouTube video information (title, poster, number of views, posting date, etc.) and X (formerly Twitter) tweet information (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0658] Step 2:

[0659] The server stores the collected trend data in a database, which makes the data easily accessible for subsequent processing.

[0660] Step 3:

[0661] The server performs data cleansing, applying filtering rules to remove irrelevant information such as advertisements and spam posts, and identifying duplicate data, removing or merging the duplicates.

[0662] Step 4:

[0663] The server converts the preprocessed data into a unified format. It formats the video information obtained from YouTube and the tweet information obtained from X (formerly Twitter) into entities with common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0664] Step 5:

[0665] The server provides the unified data to the generation AI, which then analyzes the pre-processed trend data and extracts interesting patterns and insights from the unified trend data. For example, it analyzes the features of a "plant growing app" and the functions users want (e.g., real-time growth records, watering notifications, etc.).

[0666] Step 6:

[0667] The server uses an emotion engine that recognizes users' emotions to collect emotional data provided by users. For example, it obtains emotional responses (e.g., joy, sadness, surprise, anger, etc.) to videos or tweets that users have watched. This emotional data is collected through users' activities (e.g., comments, likes, shares).

[0668] Step 7:

[0669] The server preprocesses the emotion data, removing irrelevant emotion information and noise data, and converts the emotion data into a unified format, preparing it for feeding to the generative AI.

[0670] Step 8:

[0671] The server integrates the emotion data and trend data and performs a comprehensive analysis using generative AI. This allows for the extraction of deeper insights that reflect user emotions, rather than just trends. For example, it identifies users' positive emotional reactions to a "plant growing app" and their specific requests for specific features.

[0672] Step 9:

[0673] The server stores the analysis results of the generative AI in a database, which includes the integrated results of trend data and emotion data.

[0674] Step 10:

[0675] The server visualizes the analysis results and creates templates for displaying them on a dashboard. For example, it converts the analysis results into graphs and charts and provides them in a format that is easy for users to understand.

[0676] Step 11:

[0677] Users can access the dashboard on their devices to view insights based on current trends and market needs, as well as user sentiment data. For example, market needs for a "plant growing app" are displayed, showing users' positive reactions to features like real-time growth tracking and watering notifications. This information can be used to efficiently develop and plan new products.

[0678] Example 2

[0679] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0680] Conventional market analysis systems have difficulty effectively integrating and analyzing trend data collected from multiple social networking services. In particular, the complexity of data preprocessing, sentiment data analysis, and the extraction of market needs through advanced analysis using generative AI models makes it difficult for companies to obtain fast and accurate insights.

[0681] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, a means for converting the preprocessed data into a unified format, an analysis means using a generative AI model to analyze the data converted into the unified format, and a means for saving and displaying the analysis results. This enables efficient collection, preprocessing, integration, and analysis of trend data from multiple social network services, making it possible to quickly obtain accurate insights into market needs based on user sentiment data.

[0682] "Means for data collection" refers to technical means, such as APIs and scraping technologies, used to obtain trend data based on specified keywords from multiple social networking services.

[0683] "Means for pre-processing collected data" refers to technical means for improving the quality of data by filtering and cleansing the acquired data, removing irrelevant information and duplicate data, etc.

[0684] The "means for converting preprocessed data into a unified format" refers to a technical means for converting data obtained from different social network services into common data items and into a consistent format.

[0685] "Analysis methods using generative AI models" are technical methods that provide data converted into a unified format, perform advanced analysis using generative AI models, and extract interesting patterns and insights.

[0686] "Means for storing and displaying analysis results" refers to the technical means for storing the analysis results of the generative AI model in a database and providing dashboards and templates for visually displaying them.

[0687] A "social network service" is a service that allows users to share information and interact with each other over the Internet, and refers to platforms such as YouTube and X (formerly Twitter).

[0688] This invention relates to a system that automatically collects trend data from multiple social networking services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. In addition, by combining it with an emotion engine that recognizes user emotions, it provides deeper insight into market needs. A specific embodiment for implementing this system is shown below.

[0689] The server collects trend data based on specified keywords via APIs from YouTube, X (formerly Twitter), etc. For example, for the keyword "plant growing app," it collects information such as the video title, poster, number of views, and posting date from YouTube, and information such as tweet content, user name, posting date and time, number of retweets, and number of likes from X (formerly Twitter).

[0690] The collected data is temporarily stored in a database by the server. After that, data cleansing is performed, applying filtering rules to remove advertisements and spam posts and removing or merging duplicate data. Next, the preprocessed data is reformatted into common data items and converted into a unified format. For example, video information from YouTube and tweet information from X (formerly Twitter) are reformatted into entities such as "title," "author," "content," and "username."

[0691] The server then feeds the unified data to a generative AI model for analysis. The generative AI extracts interesting patterns and insights from the integrated trend data. For example, it analyzes the features associated with a "plant growing app" and the features users want (such as real-time growth tracking and watering notifications).

[0692] In addition, the server uses an emotion engine to collect and preprocess users' emotion data to recognize their emotional reactions to the videos and tweets they watch (e.g., joy, sadness, surprise, anger, etc.). This emotion data is also analyzed and integrated with trend data.

[0693] The server then analyzes the integrated data again using a generative AI model to extract market needs. The analysis results are then stored in a database and templates are created for display on a dashboard. For example, the server identifies market needs for a "plant growing app" based on emotional data and displays positive emotional responses to features such as real-time growth records and watering notifications on a dashboard.

[0694] Finally, users can access the dashboard using their devices to view insights based on current trends, market needs, and sentiment data. For example, the market needs for a "plant growing app" are displayed, showing positive reactions to features like real-time growth tracking and watering notifications. This system allows companies to conduct trend analysis incorporating user sentiment data, enabling them to gain a deeper understanding of the market and develop more accurate product plans.

[0695] Prompt Sentence Examples

[0696] To research the market needs for a "plant growing app," please collect social media data using the following keywords. Also, analyze users' emotional responses to identify market needs. Display the results on a dashboard.

[0697] In this way, the server, terminals, and users cooperate to collect, preprocess, analyze, and display data, thereby realizing a system that can grasp market needs efficiently and accurately.

[0698] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0699] Step 1: Data collection

[0700] The server sends a request to the APIs of multiple social networking services, such as YouTube and X (formerly Twitter), using a specified keyword (e.g., "plant growing app"). This request obtains information from YouTube, such as the video title, poster, number of views, and posting date, and information from X (formerly Twitter), such as the tweet content, user name, posting date and time, number of retweets, and number of likes. The input data is the specified keyword, and the output data is detailed information obtained from each SNS.

[0701] Step 2: Storing and Cleansing the Data

[0702] The collected data is temporarily stored in a database. The server then applies filtering rules to remove advertisements and spam posts. It also identifies duplicates of the same data and deletes or merges them. The input data is the collected social media information, and the output data is the filtered, clean data.

[0703] Step 3: Standardize data formatting

[0704] The server converts the preprocessed data into a unified format. Specifically, it formats video information obtained from YouTube and tweet information obtained from X (formerly Twitter) into common data items such as "title," "author," "content," and "username." The input data is cleaned SNS information, and the output data is data converted into a unified format.

[0705] Step 4: Analyze the data with a generative AI model

[0706] The server supplies the data converted into a unified format to the generative AI model. The generative AI model analyzes the data and extracts insights. For example, it extracts the features of a "plant growing app" and the functions desired by users (real-time growth records, watering notification functions, etc.). The input data is SNS data converted into a unified format, and the output data is the insights analyzed by the generative AI model.

[0707] Step 5: Analyze the emotion data with the emotion engine

[0708] The server uses an emotion engine to collect and preprocess user emotion data. Specifically, it obtains reaction data to recognize users' emotional responses (e.g., joy, sadness, surprise, anger, etc.) to videos and tweets they have watched. The input data is the user's reaction data, and the output data is the analyzed emotion data.

[0709] Step 6: Reanalyzing the integrated data

[0710] The server integrates the analysis results from the generative AI model with the sentiment data, and then re-analyzes it using the generative AI model. This allows for deeper insights that integrate trends and sentiment. The input data is the analyzed insights and sentiment data, and the output data is the integrated market needs.

[0711] Step 7: Save and view the analysis results

[0712] The server stores the generated insights and market needs in a database and creates templates for displaying them on a dashboard. The input data is the consolidated market needs, and the output data is the data displayed on the dashboard.

[0713] Step 8: Users interact with the dashboard

[0714] Users access the dashboard using a device and view insights based on trends, market needs, and sentiment data displayed in real time. The input data are the authentication information to access the dashboard, and the output data are the insights visualized on the dashboard.

[0715] In this way, data is processed and analyzed at each step, and the results are finally displayed on a dashboard. This series of processes creates a system that can efficiently and accurately grasp market needs.

[0716] (Application example 2)

[0717] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0718] Conventional advertising analysis systems lack the functionality to comprehensively analyze social media trend data and user emotional data to plan advertising effectiveness and targeting strategies. As a result, it has been difficult for marketers to obtain specific insights to improve the effectiveness of their advertising campaigns. Furthermore, because analysis does not include emotional data, it has been difficult to improve advertising to reflect users' emotional reactions.

[0719] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0720] In this invention, the server includes a means for collecting data, a means for pre-processing the collected data, an analysis means using generative artificial intelligence to integrate the pre-processed data, a means for saving and displaying the analysis results, a means using an emotion engine to collect and analyze emotion data, and a means for extracting market needs and interesting patterns from the analysis results and providing advertising effectiveness and targeting strategies. This makes it possible to comprehensively analyze trend data on social media and user emotion data and provide specific insights to improve the effectiveness of advertising campaigns.

[0721] A "data collection instrument" is a device or system used to collect trend data and sentiment data from multiple social network services.

[0722] "Pre-processing means" refers to devices or systems that filter collected data and remove irrelevant information and duplicate data.

[0723] "Analysis means using generative artificial intelligence" refers to a device or system that integrates pre-processed data and analyzes it using a generative AI model.

[0724] "Means for saving and displaying analysis results" refers to devices or systems that save the analysis results of the generative AI model in a database and display them in a form that can be viewed by users.

[0725] "Means using an emotion engine" refers to a device or system for collecting and analyzing emotion data and identifying a user's emotional response.

[0726] "Means for extracting market needs and interesting patterns" refers to devices and systems that identify market demands and unique patterns based on the analysis results of generative artificial intelligence and emotion engines.

[0727] "Means for providing advertising effectiveness and targeting strategies" refers to devices or systems that propose strategies to increase the effectiveness of advertising campaigns based on analysis results and emotional data.

[0728] The system to realize this application example performs a series of processes: data collection, data preprocessing, analysis using generative AI, use of an emotion engine, analysis and display of the integrated data, and user use of a dashboard.

[0729] 1. Data Collection:

[0730] The server automatically collects trend data related to advertisements through the APIs of various social media services (e.g., video sharing platforms and microblogging services). This data includes the content of posts related to advertisements, user names, posting dates and times, number of reactions (e.g., likes and retweets), number of views, etc. For example, for advertisements related to plant cultivation, data is collected using keywords such as "real-time growth record."

[0731] 2. Data Preprocessing:

[0732] The server stores the collected data in a database and performs data cleansing. Specifically, it uses Python's Pandas library to filter the data, remove irrelevant information and spam posts, and eliminate duplicate data. It then converts the data into a standard format. For example, the post content is formatted as "content," the user name as "username," and the number of reactions as "reaction_count."

[0733] 3. Generative AI analysis:

[0734] The preprocessed data is fed into a generative AI model (e.g., OpenAI GPT-4) for analysis. The generative AI model extracts interesting patterns from the aggregated trend data and analyzes advertising features and user interest points. For example, it identifies features users want (e.g., time-lapse of growth process) from comments about "real-time growth record."

[0735] 4. Use of Emotion Engine:

[0736] The server uses an emotion engine (e.g., IBM Watson Emotion Analysis) to analyze users' emotions regarding the collected data. The emotion engine is used to collect and analyze users' emotional responses to each advertisement (e.g., joy, surprise, anger, sadness, etc.), which helps understand how the advertisement is received.

[0737] 5. Analysis and display of integrated data:

[0738] The server combines the analysis results from the generative AI with those from the emotion engine and stores them in a database. Furthermore, based on these results, it provides predictions of advertising effectiveness and targeting strategies. Using dashboard software (e.g., Plotly Dash), it visualizes these results and displays them in a form that can be used by marketers. For example, if users like an ad about "real-time growth records," it displays that reaction as positive.

[0739] 6. User Use of the Dashboard:

[0740] Users can access the dashboard via their devices (e.g., smartphones or PCs) and view insights based on current trends, market needs, and user sentiment data. This allows them to identify areas for improvement in advertising campaigns and develop effective marketing strategies. For example, the dashboard can display "real-time growth records" showing a high number of positive emotional responses to advertising, allowing them to plan new advertising campaigns based on that information.

[0741] Example prompt sentence:

[0742] "Please share the results of your analysis of the positive comments on the 'Real-time Plant Growth Record' video on a video sharing platform. Please also include data on viewer sentiment, and identify market needs and areas for improvement in advertising."

[0743] As described above, embodiments of the present invention enable marketers to analyze the effectiveness of their advertising and optimize their advertising strategies based on insights derived from emotion data.

[0744] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0745] Step 1:

[0746] The server calls the APIs of multiple social network services to collect trend and sentiment data related to a specified keyword (e.g., "plant cultivation"). The API endpoints and keywords of each SNS are required as input, and the collected raw data (e.g., video information, tweet content, number of reactions, etc.) is obtained as output.

[0747] Step 2:

[0748] The server stores the collected raw data in a database and performs data cleansing. Specifically, it uses Pandas to filter irrelevant information and spam posts and remove duplicate data. The collected raw data is required as input, and the cleansed data is obtained as output.

[0749] Step 3:

[0750] The server converts the cleansed data into a standard format, specifically formatting the data to correspond to data items (e.g., "title", "author", "content", "username", etc.). It takes the cleansed data as input and gets the formatted data as output.

[0751] Step 4:

[0752] The server then supplies the formatted data to a generative AI (e.g., OpenAI GPT-4) for analysis. The inputs are the formatted data and a prompt, and the output is the analysis results (e.g., user interest points and ad features) from the generative AI model. A specific example of a prompt might be, "Please tell me the results of your analysis of the comments that show positive reactions to the 'Real-time Plant Growth Record' video on a video sharing platform. Please extract market needs and areas for improvement in the ad, especially including viewer sentiment data."

[0753] Step 5:

[0754] The server uses an emotion engine (e.g., IBM Watson Emotion Analysis) to analyze the user's emotional response based on the formatted data. As input, the formatted data is required, and as output, the emotion analysis results (e.g., emotion data such as joy, surprise, sadness, etc.) are obtained.

[0755] Step 6:

[0756] The server integrates the analysis results of the generative AI model and the emotion engine, and stores the final analysis results in a database. Specifically, it extracts market needs and interesting patterns, and identifies advertising effectiveness and targeting strategies. The analysis results of the generative AI model and the emotion engine are required as input, and the integrated analysis results are obtained as output.

[0757] Step 7:

[0758] The server visualizes the integrated analysis results in the form of a dashboard. Specifically, it uses dashboard software such as Plotly Dash to display them in a format that can be easily interpreted by marketers. The integrated analysis results are required as input, and the visualized dashboard is obtained as output.

[0759] Step 8:

[0760] Users access the dashboard using their devices to view insights into the effectiveness of their advertising campaigns and market needs. The input is the user's access request, and the output is the analysis results displayed on the dashboard, providing users with concrete data to optimize their advertising strategies.

[0761] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0762] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0763] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0764] [Fourth embodiment]

[0765] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0766] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0767] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0768] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0769] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0770] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0771] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0772] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0773] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0774] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0775] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0776] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0777] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0778] The present invention relates to a system that automatically collects trend data from multiple social network services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. Specific embodiments for implementing this system are described below.

[0779] First, the server uses data collection means to collect trend data from multiple social networking services, such as YouTube and X (formerly Twitter). Specifically, the server obtains data related to a specified keyword (e.g., "plant cultivation app") through the API of each SNS. This data includes video information on YouTube (title, poster, number of views, posting date, etc.) and tweet information on X (formerly Twitter) (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0780] Next, the server preprocesses the collected data. First, data cleansing is performed to remove irrelevant information and duplicate data. Specifically, filtering rules are applied to remove advertisements and spam posts, and duplicate data is identified and deleted or merged. Next, a data format unification procedure is performed to convert data from different social media platforms into entities with a standard format (for example, YouTube title as "title," poster as "author," number of views as "views," tweet content from X (formerly Twitter) as "content," user name as "username," and posting date and time as "date").

[0781] The server then supplies the unified data to the Generator AI, which then integrates and analyzes the preprocessed trend data. For example, it merges data sets related to "plant growing apps" obtained from YouTube and X (formerly Twitter) to extract and analyze common keywords and patterns. The Generator AI then generates insights based on the functions and features desired by users and current trends. For example, it extracts user-desired features such as "real-time growth records" and "plant watering notifications."

[0782] The server also has a means for storing the analysis results of the generative AI in a database and displaying them on a dashboard that can be visually accessed by users. Specifically, the server creates templates for visualizing the analysis results and providing them in formats that are easy for users to understand (graphs, charts, etc.). Users can then access the dashboard using their devices and view information based on current trends and market needs.

[0783] For example, when a user accesses the dashboard, trend data and market needs related to "plant cultivation apps" (such as real-time growth records, watering notification functions, and fertilizer information functions) are displayed. This allows users to efficiently develop and plan new products.

[0784] The processing flow will be explained below.

[0785] Step 1:

[0786] The server begins collecting data. Specifically, it obtains trend data for a specific keyword (e.g., "plant cultivation app") through the APIs of YouTube and X (formerly Twitter). It collects video information (title, poster, number of views, posting date, etc.) from the YouTube API, and tweet information (content, user name, posting date and time, number of retweets, number of likes, etc.) from the X (formerly Twitter) API.

[0787] Step 2:

[0788] The server stores the collected trend data in a database, which makes the data easily accessible for subsequent processing.

[0789] Step 3:

[0790] The server performs data cleansing, applying filtering rules to remove irrelevant information such as advertisements and spam posts, and identifying duplicate data, removing or merging the duplicates.

[0791] Step 4:

[0792] The server converts the preprocessed data into a unified format. It maps video information obtained from YouTube and tweet information obtained from X (formerly Twitter) to common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0793] Step 5:

[0794] The server provides the unified data to the Generator AI, which then analyzes the pre-processed data and extracts interesting patterns and insights from the integrated trend data. For example, it analyzes the features of a "plant growing app" and the functions users want.

[0795] Step 6:

[0796] The server stores the results of the generated AI's analysis in a database, allowing users to access this data later.

[0797] Step 7:

[0798] The server visualizes the analysis results and creates templates for displaying them on a dashboard. For example, it converts the analysis results into graphs and charts and provides them in a format that is easy for users to understand.

[0799] Step 8:

[0800] Users access the dashboard using their devices. On the dashboard, users can view current trends and market needs and use them to develop and plan products. For example, analysis results for a "plant cultivation app" are displayed on the dashboard, and users can check information such as real-time growth records, watering notification functions, and fertilizer information functions.

[0801] Example 1

[0802] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0803] Conventional trend data analysis systems have the drawback of requiring a lot of time and effort to collect, preprocess, and integrate data from multiple online communication platforms. Furthermore, it is difficult to standardize different data formats or visualize data, resulting in analysis results that are often difficult to understand intuitively. This makes it difficult for users to make quick and accurate decisions.

[0804] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0805] In this invention, the server includes a means for collecting data, a means for pre-processing the collected data, a means for unifying the pre-processed data, an analysis means using generative AI to integrate the pre-processed data, a means for saving and displaying the analysis results, and a means for visualizing the analysis results, thereby enabling the efficient collection of trend data from multiple online communication platforms, unifying the data into a standard format, and analyzing and visualizing the data using generative AI, thereby enabling users to quickly and accurately grasp market trends.

[0806] "Data collection instrument" means a combination of software and hardware for collecting data based on designated keywords from online communication platforms.

[0807] A "pre-processing means" is a part of the system that runs algorithms and rules on collected data to cleanse and format it.

[0808] "Data formatting standardization measures" are procedures and programs for converting data collected from different platforms into a common format.

[0809] "Generative AI-based analytical tools" are AI models that analyze collected and pre-processed data to generate common patterns and insights.

[0810] "Means for storing and displaying" refers to the system configuration for storing the analysis results in a database and displaying the results to the user using a visualization template.

[0811] A "visualization tool" is a software component that intuitively displays analysis results in graphs, charts, etc.

[0812] "Multiple online communication platforms" refer to services aimed at sharing information and communicating over the Internet, such as YouTube and X (formerly Twitter).

[0813] The present invention relates to a system that automatically collects trend data from multiple online communication platforms, preprocesses and integrates it, analyzes it using generative artificial intelligence (generative AI), and stores and displays the results in a database. Specific embodiments for implementing the present invention are described below.

[0814] First, the server uses data collection means to collect trend data from multiple online communication platforms, such as YouTube and X (formerly Twitter). To do this, it uses the API of each platform. For example, it uses the YouTube API to collect video information related to "plant growing apps" (title, poster, number of views, posting date), and then uses the X (formerly Twitter) API to obtain tweet information related to the same keyword (tweet content, user name, posting date and time, number of retweets, number of likes).

[0815] Next, the server preprocesses the collected data. This data cleansing process removes irrelevant information and duplicate data. Specifically, it applies filtering rules to remove advertisements and spam posts, and identifies and merges or deletes duplicate data. It then standardizes data from different platforms into a standard format. For example, it converts YouTube video titles to "title," posters to "authors," view counts to "views," tweet content from X (formerly Twitter) to "content," usernames to "username," and posting dates and times to "date."

[0816] The server then supplies the preprocessed data to a generative AI, which analyzes the combined data set and extracts common keywords and patterns. For example, it analyzes data related to "plant-growing apps" and extracts the functions and features desired by users (e.g., "real-time growth records" and "plant watering notifications"). The generative AI performs this analysis using natural language processing and machine learning techniques.

[0817] The server further includes a means for storing the analysis results of the generative AI in a database and displaying them on a dashboard that can be visually accessed by users. Visualization templates such as graphs and charts are used to visualize the analysis results. This allows users to access the dashboard using their terminals and easily check trend data and market needs.

[0818] For example, when a user accesses the dashboard, the latest trend data and market needs for "plant cultivation apps" (e.g., "real-time growth record," "watering notification function," "fertilizer information provision function") are displayed. Based on this information, users can efficiently develop and plan new products.

[0819] Examples of prompts include the following as input to a generative AI model:

[0820] "Collect data related to 'plant growing apps' from YouTube and X (formerly Twitter), preprocess it (data cleansing and formatting), and then feed it to the generative AI to analyze common keywords and market needs. Store the results in a database and visualize them on a dashboard for display to users."

[0821] In this way, a concrete form for carrying out the invention is provided, and it becomes possible to construct a system that allows users to efficiently collect and analyze trend data and visually understand the results.

[0822] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0823] Step 1: Data collection

[0824] The server collects trend data from multiple online communication platforms such as YouTube and X (formerly Twitter). It uses a specified keyword (e.g., "plant cultivation app") as input. Specifically, the server sends a request to the YouTube API to obtain video information (title, poster, number of views, and posting date) that matches the keyword. Similarly, it uses the X (formerly Twitter) API to obtain tweet information (tweet content, user name, posting date and time, number of retweets, and number of likes) that matches the keyword. The output is the collected dataset.

[0825] Step 2: Data cleansing

[0826] The server preprocesses the collected data. It takes as input the dataset collected in step 1. Specifically, it applies filtering rules to remove irrelevant information (advertisements, spam posts), and identifies and removes or merges duplicates of identical data. The output is a cleansed dataset.

[0827] Step 3: Standardize data formats

[0828] The server formats the cleansed data into a standard format. The cleansed dataset from step 2 is used as input. Specifically, it converts YouTube video information and X (formerly Twitter) tweet information into a unified format. For example, the YouTube title is converted to "title," the poster is converted to "author," the number of views is converted to "views," the content of X's tweet is converted to "content," the user name is converted to "username," and the posting date and time is converted to "date." The output is a dataset unified into a standard format.

[0829] Step 4: Data analysis

[0830] The server supplies the preprocessed data to the Generative AI. The unified dataset from step 3 is used as input. Specifically, the Generative AI analyzes the unified dataset and extracts common keywords and patterns. For example, it identifies functions and features related to a "plant growing app" (e.g., real-time growth recording, watering notification function, etc.). The output is the analysis results.

[0831] Step 5: Save the analysis results

[0832] The server stores the analysis results from the generated AI in a database. It uses the analysis results obtained in step 4 as input. Specifically, it inserts the analysis results into the appropriate table in the database for quick access. The output is the analysis results stored in the database.

[0833] Step 6: Refresh the dashboard

[0834] The server visualizes the analysis results and updates the dashboard. It uses the analysis results saved in step 5 as input. Specifically, it converts the results into graphs and charts and displays them on the dashboard in a user-friendly format. The output is an updated dashboard with the visualized analysis results.

[0835] Step 7: User Views Dashboard

[0836] The user accesses the dashboard using a device and checks the analysis results. The dashboard updated in step 6 is used as input. Specifically, the user opens a browser, accesses the dashboard URL, and views the latest trend data and market needs related to "plant cultivation apps" (e.g., "real-time growth records," "watering notification function," etc.). The output is the information obtained by the user.

[0837] (Application example 1)

[0838] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0839] Traditional advertising strategies often involve manually collecting and analyzing trend data, making it difficult to quickly respond to market changes. Furthermore, there is a lack of automated systems for aggregating data from multiple social networking services and formulating effective advertising strategies. Therefore, there is a need to quickly deliver advertising messages and campaigns based on the latest trends in real time.

[0840] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0841] In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, an analysis means using generative artificial intelligence to integrate the preprocessed data, a means for saving and displaying the analysis results, and a means for visualizing the generated analysis results and proposing advertising strategies. This makes it possible to automatically collect and analyze trend data from multiple social network services in real time and quickly propose effective advertising messages and campaigns.

[0842] "Data collection instrument" means any device or software that automatically obtains trend data from multiple social networking services.

[0843] "Means for pre-processing collected data" refers to systems and processes for removing irrelevant information and redundant data from collected trend data and standardizing the data format.

[0844] "Analytical means using generative artificial intelligence to integrate pre-processed data" refers to algorithms or programs that integrate pre-processed data and analyze it using AI to extract trends and patterns.

[0845] "Means for storing and displaying analysis results" refers to software or tools for storing the results of AI analysis in a database and displaying them in a visual format such as graphs or charts.

[0846] "Means for visualizing the generated analysis results and proposing advertising strategies" refers to systems or applications that visually display the results to propose ideas and messages for advertising campaigns based on the analysis results generated by AI.

[0847] "Social Network Service" means an online platform that enables users to share content and communicate.

[0848] "Trend Data" refers to data and information on social networking services that reflects user interests and topics within a specific period of time.

[0849] To implement this invention, a server, a data collection mechanism, a data preprocessing mechanism, a generation AI analysis mechanism, a display mechanism, and a user terminal are required.

[0850] Data collection

[0851] The server obtains trend data using APIs that collect data from multiple social networking services. Data related to a specific keyword, such as "plant growing app," is automatically obtained from YouTube and X (formerly Twitter). This data collection process is carried out using YouTube's API key and Twitter's Bearer token.

[0852] Data Preprocessing

[0853] The collected data is cleansed by a data preprocessing mechanism within the server. Specifically, irrelevant information and spam posts are filtered out, and duplicate data is deleted. In addition, data obtained from different social networking services is converted into a standard format (e.g., YouTube video titles are standardized as "title" and Twitter tweet content as "content").

[0854] Generative AI analysis

[0855] The pre-processed data is fed into a generative AI analysis mechanism on the server. An AI model (e.g., GPT-3) is used to analyze the data and extract trends and patterns. The AI ​​uses prompts to generate messages and ideas for advertising campaigns. For example, the analysis can be performed using prompts such as:

[0856] "Analyze the following YouTube video and suggest advertising strategies:\nThis plant care app offers real-time growth recording and watering notifications. What advertising messages would be effective for promoting these features?"

[0857] Saving and displaying results

[0858] The analysis results generated by the generative AI are stored in a database. The stored results are visualized in the form of a dashboard by the server's display mechanism. The dashboard uses Matplotlib or a similar visualization tool to display the analysis results in visual formats such as graphs and charts.

[0859] User device operation

[0860] Users access the dashboard using devices such as smartphones or smart glasses, which displays analyzed advertising campaign suggestions and messages, allowing users to quickly develop advertising strategies suited to their market.

[0861] This allows users to quickly respond to the latest trends and execute effective advertising campaigns. The entire process is automated, eliminating the need for manual data collection and analysis.

[0862] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0863] Step 1:

[0864] Data collection

[0865] The server collects trend data related to specific keywords from social networking services such as YouTube and Twitter. Specifically, it uses YouTube's API key to obtain video information (title, number of views, poster, posting date, etc.), and uses Twitter's Bearer token to obtain tweet information (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0866] Input: Keywords (e.g. "plant growing app"), YouTube API key, Twitter Bearer token

[0867] Output: Trend data (video information, tweet information)

[0868] Step 2:

[0869] Data Preprocessing

[0870] The server preprocesses the collected trend data. First, it filters out irrelevant information (such as advertisements and spam posts) and duplicate data. Second, it standardizes the data format. For example, YouTube video information is converted to "title," "author," "views," and "date," while Twitter tweet information is converted to "content," "username," "likes," and "date."

[0871] Input: Trend data

[0872] Output: Preprocessed data in a standard format

[0873] Step 3:

[0874] Generative AI analysis

[0875] The server then supplies the preprocessed data to a generative AI model (e.g., GPT-3) for analysis. Specifically, the data is integrated and common keywords and patterns are extracted. The generative AI model then uses a prompt to generate analysis results. For example, the prompt could be, "Analyze the following YouTube video and suggest advertising strategies:\nThis plant care app offers real-time growth recording and watering notifications. What advertising messages would be effective for promoting these features?"

[0876] Input: Preprocessed data in standard format, prompt statements

[0877] Output: AI analysis results (advertising strategy proposals)

[0878] Step 4:

[0879] Saving and displaying results

[0880] The server stores the analysis results of the generative AI in a database. When storing the results, they are appropriately categorized by item. The stored data is then used to display the results on a dashboard. On the dashboard, the analysis results are visualized using graphs and charts, allowing users to view the results in an easily understandable format.

[0881] Input: AI analysis results

[0882] Output: Data stored in a database, visualized dashboard

[0883] Step 5:

[0884] User Use

[0885] Users access the dashboard using a smartphone or smart glasses, view the displayed analysis results, and confirm the proposed advertising strategies and messages. By providing data in an easy-to-understand format, users can quickly develop advertising campaigns that are suited to their market.

[0886] Input: Visualized dashboard

[0887] Output: User browsing and advertising strategy development

[0888] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0889] The present invention relates to a system that automatically collects trend data from multiple social networking services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. Additionally, by combining it with an emotion engine that recognizes user emotions, it provides deeper insight into market needs. A specific embodiment for implementing this system is described below.

[0890] 1. Data collection phase:

[0891] The server uses data collection means to collect trend data from multiple social networking services such as YouTube and X (formerly Twitter). Specifically, the server obtains data related to specified keywords (e.g., "plant cultivation app") through the API of each SNS. This data includes video information on YouTube (title, poster, number of views, posting date, etc.) and tweet information on X (formerly Twitter) (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0892] 2. Data preprocessing phase:

[0893] The server stores the collected trend data in a database and performs data cleansing. Specifically, it applies filtering rules to remove advertisements and spam posts, and identifies and deletes or merges duplicates of the same data. The server then converts the preprocessed data into a unified format. It formats video information obtained from YouTube and tweet information obtained from X (formerly Twitter) into entities with common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0894] 3. Analysis phase by generative AI:

[0895] The server provides the unified data to the Generator AI for analysis. The Generator AI integrates the pre-processed trend data and extracts interesting patterns and insights. For example, it analyzes the features of a "plant growing app" and the functions users want (e.g., real-time growth records, watering notifications, etc.).

[0896] 4. Use of Emotion Engine:

[0897] The server collects users' emotional data and uses an emotion engine to preprocess and analyze it. The emotion engine recognizes users' emotions and generates necessary metadata. For example, it collects users' emotional reactions (e.g., joy, sadness, surprise, anger, etc.) to videos and tweets they have watched.

[0898] 5. Analysis and display of integrated data:

[0899] The server integrates the emotion data and trend data and uses generative AI to extract market needs. The analysis results are saved in a database and a template is created for display on a dashboard. For example, based on the emotion data, positive reactions and requests from users regarding a "plant growing app" can be identified and displayed on the dashboard.

[0900] 6. User Use of the Dashboard:

[0901] Users can access the dashboard on their devices to view current trends and market needs, as well as insights based on user sentiment data. For example, the market needs for a "plant growing app" are shown as positive emotional responses to features like real-time growth tracking and watering notifications.

[0902] This system allows companies to perform trend analysis that takes into account user emotional data, enabling them to gain a deeper understanding of the market and plan products with greater precision.

[0903] The processing flow will be explained below.

[0904] Step 1:

[0905] The server uses data collection means to collect trend data from multiple social networking services, such as YouTube and X (formerly Twitter). Specifically, the server obtains data related to designated keywords, such as "plant cultivation app," through the API of each SNS. This data includes YouTube video information (title, poster, number of views, posting date, etc.) and X (formerly Twitter) tweet information (tweet content, user name, posting date and time, number of retweets, number of likes, etc.).

[0906] Step 2:

[0907] The server stores the collected trend data in a database, which makes the data easily accessible for subsequent processing.

[0908] Step 3:

[0909] The server performs data cleansing, applying filtering rules to remove irrelevant information such as advertisements and spam posts, and identifying duplicate data, removing or merging the duplicates.

[0910] Step 4:

[0911] The server converts the preprocessed data into a unified format. It formats the video information obtained from YouTube and the tweet information obtained from X (formerly Twitter) into entities with common data items (e.g., title as "title," poster as "author," content as "content," username as "username," etc.).

[0912] Step 5:

[0913] The server provides the unified data to the generation AI, which then analyzes the pre-processed trend data and extracts interesting patterns and insights from the unified trend data. For example, it analyzes the features of a "plant growing app" and the functions users want (e.g., real-time growth records, watering notifications, etc.).

[0914] Step 6:

[0915] The server uses an emotion engine that recognizes users' emotions to collect emotional data provided by users. For example, it obtains emotional responses (e.g., joy, sadness, surprise, anger, etc.) to videos or tweets that users have watched. This emotional data is collected through users' activities (e.g., comments, likes, shares).

[0916] Step 7:

[0917] The server preprocesses the emotion data, removing irrelevant emotion information and noise data, and converts the emotion data into a unified format, preparing it for feeding to the generative AI.

[0918] Step 8:

[0919] The server integrates the emotion data and trend data and performs a comprehensive analysis using generative AI. This allows for the extraction of deeper insights that reflect user emotions, rather than just trends. For example, it identifies users' positive emotional reactions to a "plant growing app" and their specific requests for specific features.

[0920] Step 9:

[0921] The server stores the analysis results of the generative AI in a database, which includes the integrated results of trend data and emotion data.

[0922] Step 10:

[0923] The server visualizes the analysis results and creates templates for displaying them on a dashboard. For example, it converts the analysis results into graphs and charts and provides them in a format that is easy for users to understand.

[0924] Step 11:

[0925] Users can access the dashboard on their devices to view insights based on current trends and market needs, as well as user sentiment data. For example, market needs for a "plant growing app" are displayed, showing users' positive reactions to features like real-time growth tracking and watering notifications. This information can be used to efficiently develop and plan new products.

[0926] Example 2

[0927] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0928] Conventional market analysis systems have difficulty effectively integrating and analyzing trend data collected from multiple social networking services. In particular, the complexity of data preprocessing, sentiment data analysis, and the extraction of market needs through advanced analysis using generative AI models makes it difficult for companies to obtain fast and accurate insights.

[0929] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for collecting data, a means for preprocessing the collected data, a means for converting the preprocessed data into a unified format, an analysis means using a generative AI model to analyze the data converted into the unified format, and a means for saving and displaying the analysis results. This enables efficient collection, preprocessing, integration, and analysis of trend data from multiple social network services, making it possible to quickly obtain accurate insights into market needs based on user sentiment data.

[0930] "Means for data collection" refers to technical means, such as APIs and scraping technologies, used to obtain trend data based on specified keywords from multiple social networking services.

[0931] "Means for pre-processing collected data" refers to technical means for improving the quality of data by filtering and cleansing the acquired data, removing irrelevant information and duplicate data, etc.

[0932] The "means for converting preprocessed data into a unified format" refers to a technical means for converting data obtained from different social network services into common data items and into a consistent format.

[0933] "Analysis methods using generative AI models" are technical methods that provide data converted into a unified format, perform advanced analysis using generative AI models, and extract interesting patterns and insights.

[0934] "Means for storing and displaying analysis results" refers to the technical means for storing the analysis results of the generative AI model in a database and providing dashboards and templates for visually displaying them.

[0935] A "social network service" is a service that allows users to share information and interact with each other over the Internet, and refers to platforms such as YouTube and X (formerly Twitter).

[0936] This invention relates to a system that automatically collects trend data from multiple social networking services, preprocesses and integrates it, analyzes it using generative artificial intelligence (AI), and stores and displays the results in a database. In addition, by combining it with an emotion engine that recognizes user emotions, it provides deeper insight into market needs. A specific embodiment for implementing this system is shown below.

[0937] The server collects trend data based on specified keywords via APIs from YouTube, X (formerly Twitter), etc. For example, for the keyword "plant growing app," it collects information such as the video title, poster, number of views, and posting date from YouTube, and information such as tweet content, user name, posting date and time, number of retweets, and number of likes from X (formerly Twitter).

[0938] The collected data is temporarily stored in a database by the server. After that, data cleansing is performed, applying filtering rules to remove advertisements and spam posts and removing or merging duplicate data. Next, the preprocessed data is reformatted into common data items and converted into a unified format. For example, video information from YouTube and tweet information from X (formerly Twitter) are reformatted into entities such as "title," "author," "content," and "username."

[0939] The server then feeds the unified data to a generative AI model for analysis. The generative AI extracts interesting patterns and insights from the integrated trend data. For example, it analyzes the features associated with a "plant growing app" and the features users want (such as real-time growth tracking and watering notifications).

[0940] In addition, the server uses an emotion engine to collect and preprocess users' emotion data to recognize their emotional reactions to the videos and tweets they watch (e.g., joy, sadness, surprise, anger, etc.). This emotion data is also analyzed and integrated with trend data.

[0941] The server then analyzes the integrated data again using a generative AI model to extract market needs. The analysis results are then stored in a database and templates are created for display on a dashboard. For example, the server identifies market needs for a "plant growing app" based on emotional data and displays positive emotional responses to features such as real-time growth records and watering notifications on a dashboard.

[0942] Finally, users can access the dashboard using their devices to view insights based on current trends, market needs, and sentiment data. For example, the market needs for a "plant growing app" are displayed, showing positive reactions to features like real-time growth tracking and watering notifications. This system allows companies to conduct trend analysis incorporating user sentiment data, enabling them to gain a deeper understanding of the market and develop more accurate product plans.

[0943] Prompt Sentence Examples

[0944] To research the market needs for a "plant growing app," please collect social media data using the following keywords. Also, analyze users' emotional responses to identify market needs. Display the results on a dashboard.

[0945] In this way, the server, terminals, and users cooperate to collect, preprocess, analyze, and display data, thereby realizing a system that can grasp market needs efficiently and accurately.

[0946] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0947] Step 1: Data collection

[0948] The server sends a request to the APIs of multiple social networking services, such as YouTube and X (formerly Twitter), using a specified keyword (e.g., "plant growing app"). This request obtains information from YouTube, such as the video title, poster, number of views, and posting date, and information from X (formerly Twitter), such as the tweet content, user name, posting date and time, number of retweets, and number of likes. The input data is the specified keyword, and the output data is detailed information obtained from each SNS.

[0949] Step 2: Storing and Cleansing the Data

[0950] The collected data is temporarily stored in a database. The server then applies filtering rules to remove advertisements and spam posts. It also identifies duplicates of the same data and deletes or merges them. The input data is the collected social media information, and the output data is the filtered, clean data.

[0951] Step 3: Standardize data formatting

[0952] The server converts the preprocessed data into a unified format. Specifically, it formats video information obtained from YouTube and tweet information obtained from X (formerly Twitter) into common data items such as "title," "author," "content," and "username." The input data is cleaned SNS information, and the output data is data converted into a unified format.

[0953] Step 4: Analyze the data with a generative AI model

[0954] The server supplies the data converted into a unified format to the generative AI model. The generative AI model analyzes the data and extracts insights. For example, it extracts the features of a "plant growing app" and the functions desired by users (real-time growth records, watering notification functions, etc.). The input data is SNS data converted into a unified format, and the output data is the insights analyzed by the generative AI model.

[0955] Step 5: Analyze the emotion data with the emotion engine

[0956] The server uses an emotion engine to collect and preprocess user emotion data. Specifically, it obtains reaction data to recognize users' emotional responses (e.g., joy, sadness, surprise, anger, etc.) to videos and tweets they have watched. The input data is the user's reaction data, and the output data is the analyzed emotion data.

[0957] Step 6: Reanalyzing the integrated data

[0958] The server integrates the analysis results from the generative AI model with the sentiment data, and then re-analyzes it using the generative AI model. This allows for deeper insights that integrate trends and sentiment. The input data is the analyzed insights and sentiment data, and the output data is the integrated market needs.

[0959] Step 7: Save and view the analysis results

[0960] The server stores the generated insights and market needs in a database and creates templates for displaying them on a dashboard. The input data is the consolidated market needs, and the output data is the data displayed on the dashboard.

[0961] Step 8: Users interact with the dashboard

[0962] Users access the dashboard using a device and view insights based on trends, market needs, and sentiment data displayed in real time. The input data are the authentication information to access the dashboard, and the output data are the insights visualized on the dashboard.

[0963] In this way, data is processed and analyzed at each step, and the results are finally displayed on a dashboard. This series of processes creates a system that can efficiently and accurately grasp market needs.

[0964] (Application example 2)

[0965] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0966] Conventional advertising analysis systems lack the functionality to comprehensively analyze social media trend data and user emotional data to plan advertising effectiveness and targeting strategies. As a result, it has been difficult for marketers to obtain specific insights to improve the effectiveness of their advertising campaigns. Furthermore, because analysis does not include emotional data, it has been difficult to improve advertising to reflect users' emotional reactions.

[0967] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0968] In this invention, the server includes a means for collecting data, a means for pre-processing the collected data, an analysis means using generative artificial intelligence to integrate the pre-processed data, a means for saving and displaying the analysis results, a means using an emotion engine to collect and analyze emotion data, and a means for extracting market needs and interesting patterns from the analysis results and providing advertising effectiveness and targeting strategies. This makes it possible to comprehensively analyze trend data on social media and user emotion data and provide specific insights to improve the effectiveness of advertising campaigns.

[0969] A "data collection instrument" is a device or system used to collect trend data and sentiment data from multiple social network services.

[0970] "Pre-processing means" refers to devices or systems that filter collected data and remove irrelevant information and duplicate data.

[0971] "Analysis means using generative artificial intelligence" refers to a device or system that integrates pre-processed data and analyzes it using a generative AI model.

[0972] "Means for saving and displaying analysis results" refers to devices or systems that save the analysis results of the generative AI model in a database and display them in a form that can be viewed by users.

[0973] "Means using an emotion engine" refers to a device or system for collecting and analyzing emotion data and identifying a user's emotional response.

[0974] "Means for extracting market needs and interesting patterns" refers to devices and systems that identify market demands and unique patterns based on the analysis results of generative artificial intelligence and emotion engines.

[0975] "Means for providing advertising effectiveness and targeting strategies" refers to devices or systems that propose strategies to increase the effectiveness of advertising campaigns based on analysis results and emotional data.

[0976] The system to realize this application example performs a series of processes: data collection, data preprocessing, analysis using generative AI, use of an emotion engine, analysis and display of the integrated data, and user use of a dashboard.

[0977] 1. Data Collection:

[0978] The server automatically collects trend data related to advertisements through the APIs of various social media services (e.g., video sharing platforms and microblogging services). This data includes the content of posts related to advertisements, user names, posting dates and times, number of reactions (e.g., likes and retweets), number of views, etc. For example, for advertisements related to plant cultivation, data is collected using keywords such as "real-time growth record."

[0979] 2. Data Preprocessing:

[0980] The server stores the collected data in a database and performs data cleansing. Specifically, it uses Python's Pandas library to filter the data, remove irrelevant information and spam posts, and eliminate duplicate data. It then converts the data into a standard format. For example, the post content is formatted as "content," the user name as "username," and the number of reactions as "reaction_count."

[0981] 3. Generative AI analysis:

[0982] The preprocessed data is fed into a generative AI model (e.g., OpenAI GPT-4) for analysis. The generative AI model extracts interesting patterns from the aggregated trend data and analyzes advertising features and user interest points. For example, it identifies features users want (e.g., time-lapse of growth process) from comments about "real-time growth record."

[0983] 4. Use of Emotion Engine:

[0984] The server uses an emotion engine (e.g., IBM Watson Emotion Analysis) to analyze users' emotions regarding the collected data. The emotion engine is used to collect and analyze users' emotional responses to each advertisement (e.g., joy, surprise, anger, sadness, etc.), which helps understand how the advertisement is received.

[0985] 5. Analysis and display of integrated data:

[0986] The server combines the analysis results from the generative AI with those from the emotion engine and stores them in a database. Furthermore, based on these results, it provides predictions of advertising effectiveness and targeting strategies. Using dashboard software (e.g., Plotly Dash), it visualizes these results and displays them in a form that can be used by marketers. For example, if users like an ad about "real-time growth records," it displays that reaction as positive.

[0987] 6. User Use of the Dashboard:

[0988] Users can access the dashboard via their devices (e.g., smartphones or PCs) and view insights based on current trends, market needs, and user sentiment data. This allows them to identify areas for improvement in advertising campaigns and develop effective marketing strategies. For example, the dashboard can display "real-time growth records" showing a high number of positive emotional responses to advertising, allowing them to plan new advertising campaigns based on that information.

[0989] Example prompt sentence:

[0990] "Please share the results of your analysis of the positive comments on the 'Real-time Plant Growth Record' video on a video sharing platform. Please also include data on viewer sentiment, and identify market needs and areas for improvement in advertising."

[0991] As described above, embodiments of the present invention enable marketers to analyze the effectiveness of their advertising and optimize their advertising strategies based on insights derived from emotion data.

[0992] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0993] Step 1:

[0994] The server calls the APIs of multiple social network services to collect trend and sentiment data related to a specified keyword (e.g., "plant cultivation"). The API endpoints and keywords of each SNS are required as input, and the collected raw data (e.g., video information, tweet content, number of reactions, etc.) is obtained as output.

[0995] Step 2:

[0996] The server stores the collected raw data in a database and performs data cleansing. Specifically, it uses Pandas to filter irrelevant information and spam posts and remove duplicate data. The collected raw data is required as input, and the cleansed data is obtained as output.

[0997] Step 3:

[0998] The server converts the cleansed data into a standard format, specifically formatting the data to correspond to data items (e.g., "title", "author", "content", "username", etc.). It takes the cleansed data as input and gets the formatted data as output.

[0999] Step 4:

[1000] The server then supplies the formatted data to a generative AI (e.g., OpenAI GPT-4) for analysis. The inputs are the formatted data and a prompt, and the output is the analysis results (e.g., user interest points and ad features) from the generative AI model. A specific example of a prompt might be, "Please tell me the results of your analysis of the comments that show positive reactions to the 'Real-time Plant Growth Record' video on a video sharing platform. Please extract market needs and areas for improvement in the ad, especially including viewer sentiment data."

[1001] Step 5:

[1002] The server uses an emotion engine (e.g., IBM Watson Emotion Analysis) to analyze the user's emotional response based on the formatted data. As input, the formatted data is required, and as output, the emotion analysis results (e.g., emotion data such as joy, surprise, sadness, etc.) are obtained.

[1003] Step 6:

[1004] The server integrates the analysis results of the generative AI model and the emotion engine, and stores the final analysis results in a database. Specifically, it extracts market needs and interesting patterns, and identifies advertising effectiveness and targeting strategies. The analysis results of the generative AI model and the emotion engine are required as input, and the integrated analysis results are obtained as output.

[1005] Step 7:

[1006] The server visualizes the integrated analysis results in the form of a dashboard. Specifically, it uses dashboard software such as Plotly Dash to display them in a format that can be easily interpreted by marketers. The integrated analysis results are required as input, and the visualized dashboard is obtained as output.

[1007] Step 8:

[1008] Users access the dashboard using their devices to view insights into the effectiveness of their advertising campaigns and market needs. The input is the user's access request, and the output is the analysis results displayed on the dashboard, providing users with concrete data to optimize their advertising strategies.

[1009] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1010] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1011] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1012] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1013] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1014] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1015] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1016] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1017] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1018] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1019] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1020] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1021] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1022] 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.

[1023] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1024] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1025] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1026] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1027] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1028] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1029] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1030] The following is further disclosed regarding the above embodiment.

[1031] (Claim 1)

[1032] a means for collecting data;

[1033] means for pre-processing the collected data;

[1034] an analytical means using generative artificial intelligence to integrate the pre-processed data;

[1035] A means to store and display the analysis results

[1036] A system including:

[1037] (Claim 2)

[1038] 10. The system of claim 1, further comprising: means for collecting trend data from a plurality of social network services.

[1039] (Claim 3)

[1040] 10. The system of claim 1, further comprising means for filtering the collected data to remove irrelevant information and redundant data.

[1041] (Claim 4)

[1042] 10. The system of claim 1, further comprising means for standardizing the preprocessed data into a standard format.

[1043] (Claim 5)

[1044] The system according to claim 1, further comprising means for extracting market needs from the analyzed trend data and displaying them on a dashboard.

[1045] "Example 1"

[1046] (Claim 1)

[1047] a means for collecting data;

[1048] means for pre-processing the collected data;

[1049] an analytical means using generative artificial intelligence to integrate the pre-processed data;

[1050] means for storing and displaying the analysis results;

[1051] A means of standardizing the format of collected data;

[1052] A means of visualizing analysis results

[1053] A system including:

[1054] (Claim 2)

[1055] 10. The system of claim 1, further comprising means for collecting trend data from a plurality of online communication platforms.

[1056] (Claim 3)

[1057] 10. The system of claim 1, further comprising means for filtering the collected data to remove irrelevant information and redundant data, and means for converting the collected data into a standard format.

[1058] "Application Example 1"

[1059] (Claim 1)

[1060] a means for collecting data;

[1061] means for pre-processing the collected data;

[1062] an analytical means using generative artificial intelligence to integrate the pre-processed data;

[1063] means for storing and displaying the analysis results;

[1064] A means for visualizing the generated analysis results and proposing an advertising strategy;

[1065] A system including:

[1066] (Claim 2)

[1067] 10. The system of claim 1, further comprising: means for collecting trend data from a plurality of social network services.

[1068] (Claim 3)

[1069] 10. The system of claim 1, further comprising means for filtering the collected data to remove irrelevant information and redundant data.

[1070] "Example 2: Combining Emotion Engines"

[1071] (Claim 1)

[1072] a means for collecting data;

[1073] means for pre-processing the collected data;

[1074] means for converting the preprocessed data into a unified format;

[1075] An analysis means using a generative AI model to analyze the data converted into the unified format;

[1076] means for storing and displaying the analysis results;

[1077] A system including:

[1078] (Claim 2)

[1079] 10. The system of claim 1, further comprising means for collecting trend data from a plurality of social network services.

[1080] (Claim 3)

[1081] 10. The system of claim 1, further comprising means for filtering the collected data to remove irrelevant information and redundant data.

[1082] "Application example 2 when combining emotion engines"

[1083] (Claim 1)

[1084] a means for collecting data;

[1085] means for pre-processing the collected data;

[1086] an analytical means using generative artificial intelligence to integrate the pre-processed data;

[1087] means for storing and displaying the analysis results;

[1088] a means using an emotion engine for collecting and analyzing emotion data;

[1089] A means to extract market needs and interesting patterns from the analysis results and provide advertising effectiveness and targeting strategies.

[1090] A system including:

[1091] (Claim 2)

[1092] 10. The system of claim 1, further comprising: means for collecting trend data and sentiment data from a plurality of social network services.

[1093] (Claim 3)

[1094] 10. The system of claim 1, further comprising means for filtering the collected data to remove irrelevant information and redundant data. [Explanation of symbols]

[1095] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting data; means for pre-processing the collected data; an analytical means using generative artificial intelligence to integrate the pre-processed data; A means to store and display the analysis results A system including:

2. The system of claim 1 , further comprising means for collecting trend data from a plurality of social network services.

3. 10. The system of claim 1, further comprising means for filtering the collected data to remove irrelevant information and redundant data.

4. 2. The system of claim 1, further comprising means for standardizing the preprocessed data into a standard format.

5. The system according to claim 1, further comprising means for extracting market needs from the analyzed trend data and displaying them on a dashboard.

Images