system

Abstract

Provide a system. The method includes: automatically collecting posts related to a specified keyword from multiple online platforms; a means for storing the collected posts in a database; A way to filter out spam and noise from saved posts, and means for analyzing the sentiment and topic of posts using natural language processing techniques; A means of converting analytical results into visualization formats such as graphs and charts; means for automatically generating a report including the visualized data; a means for distributing the generated reports to interested parties; A system that includes a means to periodically update aggregate data and display it in real time.

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] When a company launches a new device or service, it needs to quickly and accurately collect and analyze consumer feedback and ratings. However, traditional methods require a significant amount of time and effort to manually collect and analyze each consumer's posts and opinions. Furthermore, there is a lack of automation for multiple steps, such as spam and noise removal, sentiment analysis and topic extraction using natural language processing, and the creation and distribution of visualized data reports. This makes it difficult to respond to market changes quickly, hindering efforts to improve customer satisfaction and NPS. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means: a system including means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualized format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, and means for periodically updating and displaying aggregated data in real time. This system enables fast and accurate collection and analysis of consumer feedback, enabling companies to quickly respond to market demands.

[0006] "Specified Keywords" are pre-defined words or phrases that identify posts or feedback to be collected.

[0007] A "post" is content, including text, images, and videos, such as comments, opinions, ratings, and reviews, that a user provides to a social networking site or online platform.

[0008] "Online platform" is a general term for services and sites on the Internet such as Twitter, Facebook, and Instagram where users can post, share, and view information.

[0009] "Collection methods" are processes, tools, or algorithms used to automatically retrieve posts containing specified keywords from multiple online platforms.

[0010] "Storage means" refers to the process or tools used to temporarily or permanently store collected submission data in a database.

[0011] "Spam and noise removal methods" are processes and tools used to filter and remove unwanted information and harmful content from collected posts.

[0012] "Natural language processing technology" is a technology that uses computers to analyze, understand, and generate human language, and includes analytical methods such as sentiment analysis and topic extraction.

[0013] "Sentiment analysis" is a technology that determines whether emotions are positive, negative, or neutral based on the content of a post.

[0014] "Topic extraction" is a technique for identifying frequently occurring keywords and major topics from posted content.

[0015] A "visualization format" is a method of displaying collected and analyzed data in the form of graphs, charts, etc., to make the data intuitively easier to understand.

[0016] A "report" is a document, including documents, graphs, and charts, created based on collected and analyzed data to provide information to stakeholders.

[0017] "Delivery methods" are processes and tools that automatically send generated reports to relevant parties via email or chat tools.

[0018] "Means for regularly updating aggregated data" refers to processes or tools for recalculating collected and analyzed data at regular intervals and updating it as the latest data.

[0019] "Means of displaying in real time" refers to processes and tools that instantly display aggregated data and analysis results on a dashboard or similar, making them available for relevant parties to check at any time. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to stakeholders. This system is implemented through the following steps.

[0042] First, the server uses the APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords, and then automatically collects comments and ratings posted by users about new devices and services.

[0043] The server then stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used, allowing for efficient subsequent analysis and filtering processes.

[0044] Next, the server removes spam and noise from the posted data stored in the database. In this step, spam is identified based on specific keyword lists and blacklists, and inappropriate data is filtered out. This process improves the accuracy of analysis and produces reliable data.

[0045] The server then uses natural language processing technology to analyze the sentiment and topics of the posts. This analysis classifies each post as positive, negative, or neutral, and extracts key topics and frequently occurring keywords. This provides a concrete understanding of users' opinions and sentiments.

[0046] The server then converts the analysis results into visualizations such as graphs and charts, such as pie charts showing sentiment percentages or word clouds displaying frequently occurring keywords, providing data in an intuitive and easy-to-understand format.

[0047] The server then automatically generates a report with visualized data, including the percentage of positive vs. negative sentiment, major topics and trends, and specific feedback from users.

[0048] The generated reports are distributed to relevant parties by the server automatically via email or chat tools (e.g., Slack, MICROSOFT® TEAMS®, ​​etc.), allowing relevant parties to quickly grasp the voice of the market and take any necessary action immediately.

[0049] Finally, the server periodically updates the aggregated data and provides a means for displaying it in real time. This dashboard allows stakeholders to check the latest market evaluations and customer satisfaction at any time. In this way, the present invention enables quick and accurate market responses, contributing to improving a company's competitiveness and customer satisfaction.

[0050] The above is an embodiment of the present invention. This embodiment allows each step to work together, enabling efficient and effective collection and analysis of market feedback. For example, if a user posts on social media immediately after the release of a new device, saying, "The battery life of the new device is poor," this system instantly collects the post and determines through sentiment analysis that it is a negative evaluation. It then classifies the post as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. This allows developers to quickly identify the problem and take measures to improve it.

[0051] In this way, the system of the present invention becomes a powerful tool for companies to take advantage of real-time feedback from the market and respond quickly.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The server periodically searches and collects posts containing specified keywords using the APIs of multiple online platforms (Twitter, Facebook, Instagram, etc.), sends API requests, and retrieves the relevant post data.

[0055] Step 2:

[0056] The server stores the collected post data in a database, specifically metadata such as the post content, user ID, posting date and time, and used hashtags and mentions, based on an appropriate schema.

[0057] Step 3:

[0058] The server filters out spam and noise from the submissions stored in the database, using specific keyword lists and blacklists to filter out spam submissions and inappropriate data, eliminating unnecessary data.

[0059] Step 4:

[0060] The server then analyzes the cleansed post data using natural language processing (NLP) technology. This involves performing sentiment analysis on each post to determine whether it is classified as positive, negative, or neutral, and extracting key topics and frequently occurring keywords.

[0061] Step 5:

[0062] The server visualizes the analysis results, converting the sentiment interpretations and keyword frequencies obtained through text mining into graphs, charts, word clouds, and other diagrams to visually display the data.

[0063] Step 6:

[0064] The server automatically generates reports based on the visualized data, including analysis results such as sentiment ratings, key topics, and user feedback, and presents this information in an intuitive format for stakeholders.

[0065] Step 7:

[0066] The server distributes the generated reports to the relevant parties. The reports are automatically sent via email or chat tools (Slack, Microsoft Teams, etc.). It also manages distribution logs and monitors whether the distribution was successful.

[0067] Step 8:

[0068] The server runs a process that periodically updates the aggregated data and displays it on the dashboard in real time, allowing stakeholders to always check the latest market evaluations and customer satisfaction. Data is updated at specified time intervals, and the dashboard display is updated accordingly.

[0069] Example 1

[0070] 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."

[0071] If market feedback is not collected quickly and effectively after the release of a new device or service, companies will be unable to respond appropriately to customer opinions and sentiments, resulting in a decline in competitiveness and customer satisfaction. Furthermore, if collected data is left unorganized, unreliable analysis results may result. In such situations, it becomes difficult to respond to the market in real time, requiring companies to make quick decisions and take action.

[0072] 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.

[0073] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, and means for periodically updating the aggregated data and displaying it in real time. This makes it possible to quickly and accurately grasp market feedback about new devices and new services and take appropriate measures.

[0074] "Specified keywords" refer to words or phrases that a user has specified to gather specific information.

[0075] "Post" means a message, comment or review posted publicly by a User on an Online Platform.

[0076] "Online Platform" refers to web-based services that enable users to publish and share information, such as social networking services, blogs, and forums.

[0077] An "application program interface (API)" refers to a set of rules or protocols that allow different software applications to communicate with each other.

[0078] A "database" refers to a system that stores data in a structured manner that allows it to be efficiently managed, queried, and manipulated.

[0079] "Spam" refers to unsolicited messages or irrelevant postings sent in large quantities over the Internet.

[0080] "Noise" refers to unnecessary information or inaccurate data contained in the data being analyzed.

[0081] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[0082] "Sentiment analysis" refers to the technology of classifying emotional states (positive, negative, neutral, etc.) from text data.

[0083] "Topic extraction" refers to the technique of identifying key concepts or themes from text data.

[0084] "Visualization format" refers to the way data is visually represented in the form of graphs and charts.

[0085] "Report" refers to a document summarizing the analysis results and providing them to relevant parties.

[0086] "Aggregated Data" refers to data that compiles multiple data points into statistical information.

[0087] "Real-time display" means that data is displayed immediately as soon as it is updated.

[0088] The system of the present invention aims to collect and analyze real-time feedback from the market after the release of a new terminal or new service, visualize the results, and provide them to the relevant parties. This system is implemented as follows.

[0089] Hardware and software used

[0090] First, the main hardware and software used in this system are listed below.

[0091] Hardware

[0092] Server: Primarily responsible for collecting, storing, analyzing, visualizing, and distributing data. For example, an EC2 instance from Amazon Web Services (AWS (registered trademark)) is used.

[0093] Database server: Stores and manages collected data. For example, AWS RDS or MySQL (registered trademark) is used.

[0094] software

[0095] Social media platform APIs: Used to collect data. Examples include Twitter API and Facebook Graph API.

[0096] Database management systems: Examples include MySQL and PostgreSQL.

[0097] Natural language processing libraries: Mainly use NLTK and spaCy.

[0098] Data visualization tools: Matplotlib and D3.js are used.

[0099] Communication tools: Slack API and Microsoft Teams API are used for report distribution.

[0100] Specific operation of the system

[0101] The server first automatically collects posts related to the specified keywords from multiple online platforms. To do this, it uses the APIs of the social media platforms. For example, it uses the Twitter API to search for and retrieve posts using the keyword "new device." The collected post data is then saved in a database. The data is received in JSON format, parsed, and stored in the database as structured data.

[0102] After the collected submission data is saved, it is extracted from the database and filtered for spam and noise. Specific keyword lists and blacklists are used to identify spam, and the data is converted into a data frame using the Python pandas library to remove inappropriate data.

[0103] The server then uses natural language processing techniques to analyze the sentiment and topics of the collected posts. Specifically, it uses the NLTK library to perform sentiment analysis of the text and classify it as positive, negative, or neutral. It also uses TF-IDF (Term Frequency-Inverse Document Frequency) scores to extract major topics and frequently occurring keywords.

[0104] The analysis results are converted into an intuitively understandable visualization format. The server uses Matplotlib to generate pie charts showing the percentage of each sentiment, and the wordcloud library to generate word clouds of frequently occurring keywords. This allows users to visually grasp the overall trends and main opinions of the collected data.

[0105] Additionally, the server automatically generates reports containing visualized data in HTML format using the Jinja2 template engine, which are then distributed to interested parties via email using the SMTP protocol, allowing for quick sharing of market opinions and assessments.

[0106] Finally, the server periodically refreshes the data and provides a dashboard that displays it in real time. Using the Flask web framework, we expose a real-time dashboard, allowing users to see the latest status of the aggregated data at any time.

[0107] Examples of concrete examples and prompts

[0108] For example, if a user posts on social media immediately after a new device is released that "the battery life of the new device is poor," the system instantly collects the post and determines that it is a negative evaluation through sentiment analysis. It then classifies it as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. This allows developers to quickly identify the problem and take measures to improve it.

[0109] Prompt Sentence Examples

[0110] "Please explain the steps in your system to collect posts from social media and perform sentiment analysis and topic extraction. Please be specific about how your system collects data, analyzes it using natural language processing techniques, and visualizes the results."

[0111] By utilizing this system, companies will have a powerful tool to quickly analyze real-time feedback from the market and take appropriate countermeasures.

[0112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0113] Step 1:

[0114] The server automatically collects posts related to a specified keyword from multiple online platforms. The input is a specific keyword (e.g., "new device") and the API credentials of the online platform. It uses the Python tweepy library to send a search query to the Twitter API and retrieves related post data. The output is the retrieved post data in JSON format.

[0115] Specific working example:

[0116] The server sends a request to the Twitter API with a pre-defined keyword.

[0117] The JSON data returned from the API contains information such as the content of each post, the user ID, and the posting date and time.

[0118] Step 2:

[0119] The server saves the collected post data in a database. The input is the JSON format post data obtained in step 1. It connects to the database using Python's MySQL-connector library, parses the JSON data, and inserts each field into the corresponding table. The output is structured data saved in the database.

[0120] Specific working example:

[0121] The server establishes a database connection and parses each field of the JSON data to generate an SQL INSERT statement.

[0122] The generated SQL statement is executed and the collected post data is stored in a database.

[0123] Step 3:

[0124] The server reads collected submission data from the database and removes spam and noise. The input is the raw data read from the database. The data is converted into a data frame using the Python pandas library and filtered based on a specific keyword list or blacklist. The output is clean data with spam and noise removed.

[0125] Specific working example:

[0126] The server fetches the data from the database and converts it into a pandas dataframe.

[0127] Apply criteria to filter out inappropriate data using keyword lists and blacklists.

[0128] Step 4:

[0129] The server uses natural language processing technology to analyze the sentiment and topics of the collected post data. The input is the clean data obtained in step 3. It performs sentiment analysis of the text using Python's NLTK library and classifies it as positive, negative, or neutral. It also uses the TF-IDF method to extract major topics and frequently occurring keywords. The output is the sentiment classification results and topic analysis results.

[0130] Specific working example:

[0131] The server applies the nltk.sentiment.vader.SentimentIntensityAnalyzer to calculate a sentiment score for each post.

[0132] Calculate the TF-IDF score and list the important topics.

[0133] Step 5:

[0134] The server converts the analysis results into visualization formats such as graphs and charts that are easy to understand intuitively. The input is the sentiment classification and topic analysis results obtained in Step 4. The Python Matplotlib library is used to generate a pie chart showing the proportion of each sentiment, and the wordcloud library is used to create a word cloud of frequently occurring keywords. The output is the visualized data.

[0135] Specific working example:

[0136] The server generates a pie chart based on the sentiment results and displays frequently occurring keywords in a word cloud format.

[0137] Step 6:

[0138] The server automatically generates a report containing the visualized data. The input is the visualization data created in step 5. It creates the report in HTML format using the Jinja2 template engine and delivers it via email using the SMTP protocol. The output is the generated report and the delivery status.

[0139] Specific working example:

[0140] The server generates an HTML report using Jinja2 templates, embedding the visualization data.

[0141] Generated reports are sent via email using the smtplib library.

[0142] Step 7:

[0143] The server periodically updates the data and provides a dashboard that displays it in real time. The input is the latest aggregated data. The real-time dashboard is built using the Flask web framework and the APScheduler library to update the data periodically. The output is the dashboard updated in real time.

[0144] Specific working example:

[0145] The server uses Flask to build a web dashboard that displays the latest data.

[0146] Use APScheduler to run data refresh jobs periodically to ensure your dashboard always reflects the latest information.

[0147] (Application example 1)

[0148] 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."

[0149] There is a need to quickly and efficiently collect real-time feedback from the market for newly released autonomous vehicles, analyze it, and provide visualized data to stakeholders in order to quickly improve vehicle performance and add new functions.Since such a feedback system requires real-time performance, it has been difficult to achieve this using conventional methods.

[0150] 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.

[0151] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, means for accessing a specific online platform that collects feedback via an API, means for displaying the analysis results in real time on a smartphone and an in-vehicle display, and means for periodically updating aggregated data and displaying it in real time, thereby enabling the system to quickly understand user feedback and improve performance or add new functions.

[0152] "Means for automatically collecting posts related to specified keywords from multiple online platforms" refers to a function that automatically collects posts related to specific keywords from multiple online platforms, such as Twitter, Facebook, and Instagram, via API.

[0153] "Means for storing collected posts in a database" refers to a function for safely and efficiently storing the content and metadata of collected posts in a database.

[0154] "Means to remove spam and noise from saved posts" refers to a function that filters inappropriate content and irrelevant information from collected posting data.

[0155] "Means for analyzing the sentiment and topics of posts using natural language processing technology" refers to technology that analyzes the collected content of posts and extracts sentiment classifications such as positive, negative, and neutral, as well as major topics.

[0156] "Means for converting analysis results into visualization formats such as graphs and charts" refers to a function that converts the data obtained from the analysis into formats such as pie charts, bar graphs, and word clouds in order to display them graphically.

[0157] The "means for automatically generating a report including visualized data" is a function for automatically creating a report based on visualized data and providing it to a user.

[0158] The "means for distributing the generated report to the relevant parties" is a function for quickly distributing the generated report to the relevant parties via email or chat tools.

[0159] "Means of accessing specific online platforms that collect feedback via API" refers to a function that obtains posting data using the API of designated online platforms such as Twitter, Facebook, and Instagram.

[0160] "Means for displaying analysis results in real time on a smartphone and in-vehicle display" refers to a function that displays the results of analysis of posts in real time on a smartphone or the in-vehicle display of an autonomous vehicle.

[0161] The "means for periodically updating the aggregated data and displaying it in real time" is a function for periodically updating the collected data and displaying the latest information in real time.

[0162] This invention is a system that efficiently collects, analyzes, and provides real-time feedback from the autonomous vehicle market to stakeholders. This system is configured as follows.

[0163] The server automatically collects posts related to the specified keywords from multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) via API. The collected data is stored in a database, including the post content, user ID, and posting date and time.

[0164] The server then filters out spam and noise from the stored submissions using filtering based on specific keyword lists and blacklists.

[0165] The server then uses natural language processing techniques (specifically, NLP libraries such as SpaCy and NLTK) to analyze the sentiment and topics of the posts, classifying each post as positive, negative, or neutral, and extracting major topics and frequently occurring keywords.

[0166] The analysis results are converted into visualization formats such as graphs and charts by the server. Graph drawing libraries such as D3.js are used for this visualization. Reports are automatically generated based on the visualized data and distributed to relevant parties via email or chat tools. This allows stakeholders to quickly grasp market feedback and respond immediately.

[0167] Furthermore, the system has the ability to access specific online platforms that collect feedback via API and display the analysis results in real time on a smartphone and in-car display, allowing drivers to check important feedback at the appropriate time while driving.

[0168] A dashboard is also provided that regularly updates aggregated data and displays it in real time, allowing stakeholders to always check the latest market valuations and user sentiment.

[0169] For example, if a user posts on social media that a new self-driving vehicle is too slow immediately after its release, the system will instantly collect the post, analyze it as a negative evaluation, classify it as a problem with the self-braking function, visualize it, and deliver it to the development team as a report.

[0170] An example prompt is:

[0171] "Collect social media posts about new autonomous vehicles and analyze them for sentiment and key topics. Visualize the results and generate a word cloud showing the percentage of positive and negative feedback, as well as key issues."

[0172] In this way, the system of the present invention can quickly and efficiently collect and analyze market feedback on autonomous vehicles and provide it in real time, thereby contributing to improved user satisfaction and product quality.

[0173] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0174] Step 1:

[0175] Data collection

[0176] Subject: Server

[0177] Input: the specified keyword

[0178] How it works: The server collects posts related to specified keywords via APIs of online platforms such as Twitter, Facebook, and Instagram.

[0179] Output: Collected submission data

[0180] Step 2:

[0181] Data storage

[0182] Subject: Server

[0183] Input: Collected submission data

[0184] How it works: The server stores the collected post data in a database, which includes metadata such as the post content, user ID, post date and time, and hashtags and mentions used.

[0185] Output: Post data saved in the database

[0186] Step 3:

[0187] Spam and noise removal

[0188] Subject: Server

[0189] Input: Post data stored in the database

[0190] How it works: The server filters submissions based on specific keyword lists and blacklists to remove spam and noise.

[0191] Output: Filtered post data

[0192] Step 4:

[0193] Sentiment and topic analysis

[0194] Subject: Server

[0195] Input: Filtered post data

[0196] How it works: The server uses natural language processing techniques to analyze posts for sentiment (positive, negative, neutral), main topics, and frequently occurring keywords. Specifically, it uses NLP libraries (e.g., SpaCy, NLTK).

[0197] Output: Parsed sentiment and topic data

[0198] Step 5:

[0199] Data visualization

[0200] Subject: Server

[0201] Input: Parsed sentiment and topic data

[0202] How it works: The server converts the analysis results into visualizations such as graphs and charts (e.g., pie charts, word clouds), using a graph drawing library such as D3.js.

[0203] Output: Visualized data

[0204] Step 6:

[0205] Report Generation

[0206] Subject: Server

[0207] Input: Visualized data

[0208] How it works: The server automatically generates reports based on the visualized data, including the ratio of positive vs. negative sentiment, major topics and trends, and specific feedback from users.

[0209] Output: Generated report

[0210] Step 7:

[0211] Report Distribution

[0212] Subject: Server

[0213] Input: Generated report

[0214] How it works: The server delivers automatically generated reports to relevant parties via email or chat tools (e.g., Slack, Microsoft Teams).

[0215] Output: Delivered report

[0216] Step 8:

[0217] Real-time display

[0218] Subject: Server

[0219] Input: Aggregate data

[0220] How it works: The server periodically updates the aggregated data and provides real-time display, allowing users to check the latest market valuation and sentiment data on their smartphone or in-car display.

[0221] Output: Data displayed in real time

[0222] Step 9:

[0223] Feedback collection

[0224] Subject: Server

[0225] Input: API of a specific online platform

[0226] Operation: The server accesses a specific online platform via API and collects feedback.

[0227] Output: Collected feedback data

[0228] 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.

[0229] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to stakeholders. Furthermore, by combining it with an emotion engine that recognizes user emotions, more detailed and accurate feedback analysis is possible. This system is implemented through the following steps:

[0230] First, the server uses the APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords. In this step, comments and ratings about new devices and services posted by users on SNS are automatically acquired and stored in a database.

[0231] The server then stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used, allowing for efficient subsequent analysis and filtering processes.

[0232] The server then filters out spam and noise from the submissions stored in the database. This filtering step removes spam submissions and inappropriate data based on specific keyword lists and blacklists, resulting in reliable, cleansed data.

[0233] The server then analyzes the cleansed post data using natural language processing technology and an emotion engine. The emotion engine recognizes the user's emotions expressed in each post and determines whether the post is positive, negative, or neutral. It also extracts major topics and frequently occurring keywords. This emotion analysis provides a clear understanding of the user's specific emotional state.

[0234] The server converts the analysis results into visualizations such as graphs and charts. For example, it generates a pie chart showing the percentage of emotions or a word cloud showing frequently occurring keywords. Furthermore, the analysis results of the emotion engine are also visualized, allowing users to intuitively understand the detailed data.

[0235] The server then automatically generates a report based on the visualized data, including the ratio of positive vs. negative sentiment, key topics, user feedback, and sentiment analysis results from the sentiment engine, all in a visually easy-to-understand format, allowing stakeholders to easily understand the market situation.

[0236] The generated reports are distributed to relevant parties by the server automatically via email or chat tools (such as Slack or Microsoft Teams), allowing relevant parties to quickly grasp the voice of the market and take any necessary action immediately.

[0237] Finally, the server periodically updates the aggregated data and provides a means to display it in real time. This dashboard allows stakeholders to check the latest market valuation and customer satisfaction at any time. Furthermore, the emotion engine generates alerts to notify stakeholders of specific emotional states (e.g., extreme dissatisfaction).

[0238] For example, if a user posts on social media immediately after the release of a new device that "the battery life of the new device is poor," the system immediately collects the post and uses sentiment analysis to determine that it is a negative evaluation. Next, it uses natural language processing to classify it as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. The sentiment engine detects strong user dissatisfaction and generates an alert to immediately notify relevant parties. This series of processes allows developers to quickly identify the problem and take measures to improve it.

[0239] This concludes the description of the embodiment of the present invention. This embodiment allows each step to work together, efficiently and effectively collecting and analyzing market feedback, and enabling rapid market response. The combination of emotion engines allows for a detailed understanding of the user's emotional state, enabling appropriate responses to be taken promptly.

[0240] The processing flow will be explained below.

[0241] Step 1:

[0242] The server uses APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords, thereby automatically obtaining comments and ratings about new devices and new services posted by users on SNS.

[0243] Step 2:

[0244] The server stores the collected post data in a database, where metadata such as the post content, user ID, posting date and time, and used hashtags and mentions are stored based on a schema.

[0245] Step 3:

[0246] The server filters spam and noise from the submissions stored in the database, using specific keyword lists and blacklists to filter out spam submissions and inappropriate data, resulting in reliable, cleansed data.

[0247] Step 4:

[0248] The server analyzes the cleansed post data using natural language processing technology and an emotion engine. The emotion engine recognizes the user's emotions expressed in each post and determines whether the post is positive, negative, or neutral. It also extracts major topics and frequently occurring keywords.

[0249] Step 5:

[0250] The server visualizes the analysis results, generating graphs, charts, and word clouds based on the sentiment analysis results and keyword frequencies obtained through text mining, and creating diagrams to visually display the data.

[0251] Step 6:

[0252] The server automatically generates reports based on the visualized data, including sentiment ratios, major topics, user feedback, and detailed sentiment analysis results from the sentiment engine.

[0253] Step 7:

[0254] The server distributes the generated reports to the relevant parties, automatically sending the reports via email or chat tools (e.g., Slack, Microsoft Teams, etc.), and managing the distribution logs.

[0255] Step 8:

[0256] The server runs a calculation process that periodically updates the aggregated data and displays it on the dashboard in real time, allowing stakeholders to always see the latest market evaluations and customer satisfaction figures.

[0257] Step 9:

[0258] The server generates alerts for specific emotional states (e.g., extreme dissatisfaction) recognized by the emotion engine, allowing relevant parties to be notified immediately and respond quickly.

[0259] Example 2

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

[0261] With conventional systems, it was difficult to efficiently collect, analyze, visualize, and quickly provide real-time feedback from the market after the release of new devices or services. Furthermore, the analytical technology required to grasp user sentiment in detail was insufficient, making it difficult to quickly take appropriate action.

[0262] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0263] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology and an emotion engine, means for converting the analysis results into a visualized format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to interested parties via email or a chat tool, means for periodically updating the aggregated data and displaying it in real time, and means for detecting specific emotional states using the emotion engine and generating alerts. This makes it possible to quickly and precisely collect, analyze, visualize, and provide relevant parties with feedback from the market after the release of a new device or service.

[0264] "Specified Keywords" are specific words or phrases used to collect targeted posts.

[0265] An "online platform" is a system that provides services over the Internet and allows users to post and share content. Examples include social networking platforms.

[0266] A "post" is any content such as a comment, rating, photo, or video posted by a user on an online platform.

[0267] "Collection methods" refers to technologies or methods for automatically obtaining posts related to designated keywords from online platforms.

[0268] A "database" is a storage device for systematically storing and managing collected submission data.

[0269] "Spam" and "noise" refer to information that is inappropriate or irrelevant for analysis. Spam is irrelevant posts sent in large quantities, while noise is unnecessary data that reduces the accuracy of analysis.

[0270] "Natural language processing technology" refers to the technology that uses computers to analyze, understand, and generate human language.

[0271] An "emotion engine" is software or algorithms used to identify and classify user emotions contained in posts.

[0272] A "visualization format" is a method of converting analytical results into graphics such as graphs and charts so that they can be understood at a glance.

[0273] A "report" is a document or file that summarizes the results of analysis and visualization and provides them to stakeholders.

[0274] "Email and chat tools" refers to applications for sending generated reports to relevant parties via communication means.

[0275] "Means of displaying in real time" refers to a system that regularly updates the latest data so that relevant parties can check it immediately.

[0276] An "alert" is a notification function that alerts relevant parties when a specific condition is met.

[0277] This invention is a system that collects real-time feedback from the market when a new device or service is released, analyzes it, and provides visualized data to stakeholders. Furthermore, by combining it with an emotion engine, detailed and accurate feedback analysis is achieved. This system is mainly composed of a server, a device, and a user.

[0278] server

[0279] The server first uses APIs from multiple online platforms (Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords. It authenticates with each platform using an API key and obtains data in JSON format. The collected post data is then stored in a NoSQL database such as MongoDB. The stored data includes metadata such as the post content, user ID, posting date and time, and used hashtags and mentions.

[0280] The server then filters the collected submission data to remove spam and noise. This involves filtering the data using specific keyword lists and blacklists. By removing spam submissions and eliminating noise data, the server obtains reliable, cleansed data.

[0281] The server then analyzes the cleansed post data using natural language processing techniques (NLP libraries, e.g., SpaCy, NLTK) and a sentiment engine (e.g., Hugging Face sentiment analysis model). The sentiment engine identifies user sentiment expressed in each post and classifies it as positive, negative, or neutral. It also extracts major topics and frequently occurring keywords.

[0282] The analysis results are converted by the server into visualization formats such as graphs and charts (using Matplotlib, D3.js, Plotly, and Chart.js), with pie charts showing sentiment percentages and word clouds showing frequent keywords.

[0283] Finally, the server automatically generates reports based on the visualized data and distributes them to relevant parties via email or chat tools (Slack, Microsoft Teams, etc.). Furthermore, it provides a dashboard that periodically aggregates data and displays it in real time. It also has a function that generates alerts to relevant parties when a specific emotional state (such as extreme dissatisfaction) is detected by the emotion engine.

[0284] Terminal

[0285] The terminals display reports and real-time evaluation data delivered from the server, allowing participants to quickly grasp market conditions and take any necessary action immediately.

[0286] User

[0287] Users provide feedback on new devices and services on the online platform, which allows the system to collect and analyze specific market evaluations and sentiments.

[0288] Specific examples

[0289] For example, if a user posts on social media that "my new device's battery life is poor," the server collects the post via the Twitter API and stores it in MongoDB. It then uses a blacklist to filter out spam posts, and the content is saved as cleansed data. The server then uses natural language processing technology and an emotion engine to analyze the negative emotions, including dissatisfaction with the "battery." The results are then distributed to relevant parties in a visualized format (pie chart or word cloud). Additionally, if a specific emotional state is detected, an immediate alert is sent via Slack or other means.

[0290] Prompt Sentence Examples

[0291] "Describe a system that instantly analyzes market reactions after the release of a new device, categorizes user feedback with an emotion engine, and generates real-time visualizations."

[0292] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0293] Step 1: Data collection

[0294] The server uses APIs of online platforms such as Twitter, Facebook, and Instagram to collect posts containing specified keywords related to new devices and new services. It requires an API key and keywords as input, and sends a request to each platform to retrieve the posted data in JSON format. The output is the collected posted data.

[0295] As a specific example of how this works, the server uses the Twitter API to collect tweets containing the keyword "new device."

[0296] Step 2: Save data

[0297] The server stores the collected post data in a NoSQL database such as MongoDB. The input is the collected post data in JSON format, and the output is the data stored in the database.

[0298] As a specific example of how this works, the server stores the acquired post data as a document in MongoDB, including metadata such as the post content, user ID, posting date and time, and hashtags.

[0299] Step 3: Data cleansing

[0300] The server filters out spam and noise from the stored data. The input is the submitted data stored in the database, and the output is the cleansed data.

[0301] In particular, the server may use specific keyword lists or blacklists to filter out irrelevant or spam posts and remove them.

[0302] Step 4: Data analysis

[0303] The server analyzes the cleansed data using natural language processing technology and an emotion engine. The input is the cleansed posted data, and the output is the analysis results.

[0304] For example, the server analyzes posts using an NLP library (e.g., SpaCy) to extract topics, and then uses an emotion engine (e.g., the Hugging Face model) to classify emotions into positive, negative, and neutral.

[0305] Step 5: Data visualization

[0306] The server converts the analysis results into a visualization format: the input is the analysis results and the output is the visualized graphs and charts.

[0307] As a specific example of how it works, the server uses Matplotlib and D3.js to create pie charts showing the percentage of sentiment analysis and word clouds showing frequently occurring keywords.

[0308] Step 6: Report generation and delivery

[0309] The server generates reports based on the visualized data and distributes them to relevant parties via email or chat tools. The input is the visualized data, and the output is the generated report and the distribution completion status.

[0310] For example, the server generates a report in PDF format and emails it to interested parties via an SMTP server, and also sends a message containing the visualization data using the Slack API.

[0311] Step 7: Real-time updates and alerts

[0312] The server periodically aggregates data and provides a dashboard that displays it in real time. Furthermore, an emotion engine detects specific emotional states and generates alerts. The input is newly collected post data and analysis results, and the output is an updated dashboard and alert notifications.

[0313] For example, the server uses Node.js and Socket.IO to update the dashboard in real time, and when it detects certain emotional states, such as extreme dissatisfaction, it sends alerts to relevant parties via SMS or push notifications.

[0314] (Application example 2)

[0315] 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."

[0316] After the release of a new device or service, there is a need to collect, analyze, and visualize customer feedback in real time so that quick and specific responses can be taken. However, traditional feedback collection methods have problems with incomplete spam and noise removal and low sentiment analysis accuracy, making it difficult to accurately grasp market trends. In addition, the inability to generate notifications or alerts in real time makes it difficult to take quick action.

[0317] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, means for periodically updating and displaying aggregated data in real time, means for notifying customer feedback in real time, means for generating and distributing alerts based on specific sentiment results, and means for viewing the visualized data on a dashboard. This allows relevant parties to grasp the market's voice in real time and respond promptly and appropriately.

[0318] "Post" means a message or comment written by a User on an Online Platform.

[0319] "Online platform" refers to an internet service that provides social networking services such as Twitter, Facebook, and Instagram.

[0320] A "database" is a storage medium for structuring and storing collected data.

[0321] "Spam and noise" refers to unnecessary advertising and irrelevant, meaningless data.

[0322] "Natural language processing technology" is a technology that analyzes human language and converts it into a format that a computer can understand and process.

[0323] "Sentiment analysis" is the use of natural language processing technology to classify users' emotions into positive, negative, or neutral based on the content of their posts.

[0324] "Topic" refers to a recurring theme or subject matter within a post.

[0325] A "visualization format" is a method of presenting analytical results in a visually easy-to-understand format, such as a graph or chart.

[0326] A "report" is a document that summarizes visualized data and analysis results.

[0327] "Real-time notification" means instantly informing relevant parties of analysis results and feedback.

[0328] An "alert" refers to issuing a warning to relevant parties when a specific condition or emotional outcome is detected.

[0329] A "dashboard" is an interface for visually and centrally managing analysis results and feedback.

[0330] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to relevant parties. In particular, it provides a mechanism that allows quick confirmation of customer feedback and immediate response as needed.

[0331] The system includes the following components:

[0332] 1. Data Collection

[0333] The server automatically collects relevant posts from multiple online platforms (e.g., social networking services) and retrieves posts based on specified keywords using the API of each platform.

[0334] 2. Data storage

[0335] The server stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used.

[0336] 3. Data Cleansing

[0337] The server filters out spam and noise from the submission data stored in the database, and filters out inappropriate data based on specific keyword lists and blacklists.

[0338] 4. Sentiment Analysis and Topic Extraction

[0339] The server analyzes the cleansed post data using natural language processing technology and an emotion engine, which classifies the sentiment of posts into positive, negative, and neutral, and extracts major topics and frequently occurring keywords.

[0340] 5. Data Visualization

[0341] The server then converts the analysis results into visualizations such as graphs and charts, including pie charts showing sentiment percentages and word clouds showing major topics.

[0342] 6. Report Generation and Delivery

[0343] The server automatically generates reports based on the visualized data and distributes them to relevant parties via email or chat tools.

[0344] 7. Real-time notifications and dashboard display

[0345] The server periodically updates the data, providing a dashboard with real-time display, and also provides real-time customer feedback and generates alerts based on specific sentiment results.

[0346] Program processing explanation

[0347] The hardware used includes servers and devices such as smartphones and tablets, while the software used includes APIs from each online platform, the Python requests library, the NLTK library for natural language processing, a sentiment analysis engine, and the matplotlib library for visualization.

[0348] Data collection:

[0349] Post data is obtained from each platform via API and stored in a database.

[0350] Data cleansing:

[0351] Filter out spam and noise to create a clean dataset.

[0352] Sentiment analysis and topic extraction:

[0353] We use the NLTK library and a sentiment analysis engine to classify and extract the sentiment and main topics of each post.

[0354] Data Visualization:

[0355] The matplotlib library is used to convert the analysis results into visually understandable formats such as pie charts and word clouds.

[0356] Report generation and delivery:

[0357] Reports are automatically created based on the generated visualization data and distributed to relevant parties via email or chat tools.

[0358] Real-time notifications and dashboard views:

[0359] It regularly updates the data, providing a dashboard with up-to-date feedback, and provides real-time alerts when specific sentiment results are detected.

[0360] Specific examples

[0361] For example, if a store launches a new service and a customer posts on social media, "This new service is so convenient!", this positive feedback will be immediately notified to the store manager. Similarly, if there is a negative post such as "The wait time for service is long," the store manager will be notified in the same way, so that they can take immediate action.

[0362] Prompt sentence for generative AI model

[0363] We will design a smartphone application that collects real-time social media feedback after the release of a new service or device, and analyzes and visualizes positive and negative sentiment. This application uses Python's requests library to collect data from social media APIs, combines natural language processing and an emotion engine to analyze the feedback, and visualizes it using matplotlib. As a concrete example, if a customer posts on social media that "the wait time for service is long," this negative feedback will be immediately notified to the store manager.

[0364] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0365] Step 1: Data collection

[0366] The server collects posts based on the specified keywords using APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram).

[0367] Input: the specified keyword

[0368] Data processing: Acquiring posts through API, analyzing JSON format data

[0369] Output: Retrieved post data (metadata such as post content, user ID, post date and time)

[0370] Step 2: Save data

[0371] The server stores the collected posting data in a database.

[0372] Input: Collected submission data

[0373] Data processing: Inserting data into the database

[0374] Output: Post data saved in the database

[0375] Step 3: Remove spam noise

[0376] The server filters out spam and noise from posts stored in a database.

[0377] Input: Post data read from the database

[0378] Data processing: filtering based on specific keyword lists or blacklists

[0379] Output: Cleansed post data

[0380] Step 4: Sentiment analysis and topic extraction

[0381] The server uses natural language processing technology and an emotion engine to analyze the sentiment and topic of posts.

[0382] Input: Cleansed post data

[0383] Data processing: Sentiment determination and topic extraction using natural language processing techniques

[0384] Output: Analysis data with sentiment and topic annotations

[0385] Step 5: Data visualization

[0386] The server converts the analysis results into visualization formats such as graphs and charts.

[0387] Input: Analysis data with sentiment and topic annotations

[0388] Data processing: Graph generation using visualization libraries (e.g., matplotlib)

[0389] Output: Visualized graphs and charts

[0390] Step 6: Report generation and distribution

[0391] The server automatically generates reports based on the visualized data and distributes them to relevant parties.

[0392] Input: Data for visualizations of graphs and charts

[0393] Data processing: Report generation and distribution via email or chat tools

[0394] Output: Report sent to stakeholders

[0395] Step 7: Real-time notifications and dashboard display

[0396] The server provides a dashboard that periodically updates and displays the data in real time, and also generates alerts based on specific sentiment results.

[0397] Input: Real-time collected analytics data

[0398] Data processing: Display on dashboard and generate alerts

[0399] Output: Latest data displayed in the dashboard and delivered alerts

[0400] 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.

[0401] 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.

[0402] 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.

[0403] [Second embodiment]

[0404] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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).

[0410] 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. 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.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] In the smart glasses 214, 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.

[0415] 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."

[0416] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to stakeholders. This system is implemented through the following steps.

[0417] First, the server uses the APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords, and then automatically collects comments and ratings posted by users about new devices and services.

[0418] The server then stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used, allowing for efficient subsequent analysis and filtering processes.

[0419] Next, the server removes spam and noise from the posted data stored in the database. In this step, spam is identified based on specific keyword lists and blacklists, and inappropriate data is filtered out. This process improves the accuracy of analysis and produces reliable data.

[0420] The server then uses natural language processing technology to analyze the sentiment and topics of the posts. This analysis classifies each post as positive, negative, or neutral, and extracts key topics and frequently occurring keywords. This provides a concrete understanding of users' opinions and sentiments.

[0421] The server then converts the analysis results into visualizations such as graphs and charts, such as pie charts showing sentiment percentages or word clouds displaying frequently occurring keywords, providing data in an intuitive and easy-to-understand format.

[0422] The server then automatically generates a report with visualized data, including the percentage of positive vs. negative sentiment, major topics and trends, and specific feedback from users.

[0423] The generated reports are distributed to relevant parties by the server automatically via email or chat tools (such as Slack or Microsoft Teams), allowing relevant parties to quickly grasp the voice of the market and take any necessary action immediately.

[0424] Finally, the server periodically updates the aggregated data and provides a means for displaying it in real time. This dashboard allows stakeholders to check the latest market evaluations and customer satisfaction at any time. In this way, the present invention enables quick and accurate market responses, contributing to improving a company's competitiveness and customer satisfaction.

[0425] The above is an embodiment of the present invention. This embodiment allows each step to work together, enabling efficient and effective collection and analysis of market feedback. For example, if a user posts on social media immediately after the release of a new device, saying, "The battery life of the new device is poor," this system instantly collects the post and determines through sentiment analysis that it is a negative evaluation. It then classifies the post as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. This allows developers to quickly identify the problem and take measures to improve it.

[0426] In this way, the system of the present invention becomes a powerful tool for companies to take advantage of real-time feedback from the market and respond quickly.

[0427] The processing flow will be explained below.

[0428] Step 1:

[0429] The server periodically searches and collects posts containing specified keywords using the APIs of multiple online platforms (Twitter, Facebook, Instagram, etc.), sends API requests, and retrieves the relevant post data.

[0430] Step 2:

[0431] The server stores the collected post data in a database, specifically metadata such as the post content, user ID, posting date and time, and used hashtags and mentions, based on an appropriate schema.

[0432] Step 3:

[0433] The server filters out spam and noise from the submissions stored in the database, using specific keyword lists and blacklists to filter out spam submissions and inappropriate data, eliminating unnecessary data.

[0434] Step 4:

[0435] The server then analyzes the cleansed post data using natural language processing (NLP) technology. This involves performing sentiment analysis on each post to determine whether it is classified as positive, negative, or neutral, and extracting key topics and frequently occurring keywords.

[0436] Step 5:

[0437] The server visualizes the analysis results, converting the sentiment interpretations and keyword frequencies obtained through text mining into graphs, charts, word clouds, and other diagrams to visually display the data.

[0438] Step 6:

[0439] The server automatically generates reports based on the visualized data, including analysis results such as sentiment ratings, key topics, and user feedback, and presents this information in an intuitive format for stakeholders.

[0440] Step 7:

[0441] The server distributes the generated reports to the relevant parties. The reports are automatically sent via email or chat tools (Slack, Microsoft Teams, etc.). It also manages distribution logs and monitors whether the distribution was successful.

[0442] Step 8:

[0443] The server runs a process that periodically updates the aggregated data and displays it on the dashboard in real time, allowing stakeholders to always check the latest market evaluations and customer satisfaction. Data is updated at specified time intervals, and the dashboard display is updated accordingly.

[0444] Example 1

[0445] 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."

[0446] If market feedback is not collected quickly and effectively after the release of a new device or service, companies will be unable to respond appropriately to customer opinions and sentiments, resulting in a decline in competitiveness and customer satisfaction. Furthermore, if collected data is left unorganized, unreliable analysis results may result. In such situations, it becomes difficult to respond to the market in real time, requiring companies to make quick decisions and take action.

[0447] 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.

[0448] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, and means for periodically updating the aggregated data and displaying it in real time. This makes it possible to quickly and accurately grasp market feedback about new devices and new services and take appropriate measures.

[0449] "Specified keywords" refer to words or phrases that a user has specified to gather specific information.

[0450] "Post" means a message, comment or review posted publicly by a User on an Online Platform.

[0451] "Online Platform" refers to web-based services that enable users to publish and share information, such as social networking services, blogs, and forums.

[0452] An "application program interface (API)" refers to a set of rules or protocols that allow different software applications to communicate with each other.

[0453] A "database" refers to a system that stores data in a structured manner that allows it to be efficiently managed, queried, and manipulated.

[0454] "Spam" refers to unsolicited messages or irrelevant postings sent in large quantities over the Internet.

[0455] "Noise" refers to unnecessary information or inaccurate data contained in the data being analyzed.

[0456] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[0457] "Sentiment analysis" refers to the technology of classifying emotional states (positive, negative, neutral, etc.) from text data.

[0458] "Topic extraction" refers to the technique of identifying key concepts or themes from text data.

[0459] "Visualization format" refers to the way data is visually represented in the form of graphs and charts.

[0460] "Report" refers to a document summarizing the analysis results and providing them to relevant parties.

[0461] "Aggregated Data" refers to data that compiles multiple data points into statistical information.

[0462] "Real-time display" means that data is displayed immediately as soon as it is updated.

[0463] The system of the present invention aims to collect and analyze real-time feedback from the market after the release of a new terminal or new service, visualize the results, and provide them to the relevant parties. This system is implemented as follows.

[0464] Hardware and software used

[0465] First, the main hardware and software used in this system are listed below.

[0466] Hardware

[0467] Server: Primarily responsible for collecting, storing, analyzing, visualizing, and distributing data. For example, an EC2 instance from Amazon Web Services (AWS) is used.

[0468] Database server: Stores and manages collected data. For example, AWS RDS or MySQL is used.

[0469] software

[0470] Social media platform APIs: Used to collect data. Examples include Twitter API and Facebook Graph API.

[0471] Database management systems: Examples include MySQL and PostgreSQL.

[0472] Natural language processing libraries: Mainly use NLTK and spaCy.

[0473] Data visualization tools: Matplotlib and D3.js are used.

[0474] Communication tools: Slack API and Microsoft Teams API are used for report distribution.

[0475] Specific operation of the system

[0476] The server first automatically collects posts related to the specified keywords from multiple online platforms. To do this, it uses the APIs of the social media platforms. For example, it uses the Twitter API to search for and retrieve posts using the keyword "new device." The collected post data is then saved in a database. The data is received in JSON format, parsed, and stored in the database as structured data.

[0477] After the collected submission data is saved, it is extracted from the database and filtered for spam and noise. Specific keyword lists and blacklists are used to identify spam, and the data is converted into a data frame using the Python pandas library to remove inappropriate data.

[0478] The server then uses natural language processing techniques to analyze the sentiment and topics of the collected posts. Specifically, it uses the NLTK library to perform sentiment analysis of the text and classify it as positive, negative, or neutral. It also uses TF-IDF (Term Frequency-Inverse Document Frequency) scores to extract major topics and frequently occurring keywords.

[0479] The analysis results are converted into an intuitively understandable visualization format. The server uses Matplotlib to generate pie charts showing the percentage of each sentiment, and the wordcloud library to generate word clouds of frequently occurring keywords. This allows users to visually grasp the overall trends and main opinions of the collected data.

[0480] Additionally, the server automatically generates reports containing visualized data in HTML format using the Jinja2 template engine, which are then distributed to interested parties via email using the SMTP protocol, allowing for quick sharing of market opinions and assessments.

[0481] Finally, the server periodically refreshes the data and provides a dashboard that displays it in real time. Using the Flask web framework, we expose a real-time dashboard, allowing users to see the latest status of the aggregated data at any time.

[0482] Examples of concrete examples and prompts

[0483] For example, if a user posts on social media immediately after a new device is released that "the battery life of the new device is poor," the system instantly collects the post and determines that it is a negative evaluation through sentiment analysis. It then classifies it as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. This allows developers to quickly identify the problem and take measures to improve it.

[0484] Prompt Sentence Examples

[0485] "Please explain the steps in your system to collect posts from social media and perform sentiment analysis and topic extraction. Please be specific about how your system collects data, analyzes it using natural language processing techniques, and visualizes the results."

[0486] By utilizing this system, companies will have a powerful tool to quickly analyze real-time feedback from the market and take appropriate countermeasures.

[0487] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0488] Step 1:

[0489] The server automatically collects posts related to a specified keyword from multiple online platforms. The input is a specific keyword (e.g., "new device") and the API credentials of the online platform. It uses the Python tweepy library to send a search query to the Twitter API and retrieves related post data. The output is the retrieved post data in JSON format.

[0490] Specific working example:

[0491] The server sends a request to the Twitter API with a pre-defined keyword.

[0492] The JSON data returned from the API contains information such as the content of each post, the user ID, and the posting date and time.

[0493] Step 2:

[0494] The server saves the collected post data in a database. The input is the JSON format post data obtained in step 1. It connects to the database using Python's MySQL-connector library, parses the JSON data, and inserts each field into the corresponding table. The output is structured data saved in the database.

[0495] Specific working example:

[0496] The server establishes a database connection and parses each field of the JSON data to generate an SQL INSERT statement.

[0497] The generated SQL statement is executed and the collected post data is stored in a database.

[0498] Step 3:

[0499] The server reads collected submission data from the database and removes spam and noise. The input is the raw data read from the database. The data is converted into a data frame using the Python pandas library and filtered based on a specific keyword list or blacklist. The output is clean data with spam and noise removed.

[0500] Specific working example:

[0501] The server fetches the data from the database and converts it into a pandas dataframe.

[0502] Apply criteria to filter out inappropriate data using keyword lists and blacklists.

[0503] Step 4:

[0504] The server uses natural language processing technology to analyze the sentiment and topics of the collected post data. The input is the clean data obtained in step 3. It performs sentiment analysis of the text using Python's NLTK library and classifies it as positive, negative, or neutral. It also uses the TF-IDF method to extract major topics and frequently occurring keywords. The output is the sentiment classification results and topic analysis results.

[0505] Specific working example:

[0506] The server applies the nltk.sentiment.vader.SentimentIntensityAnalyzer to calculate a sentiment score for each post.

[0507] Calculate the TF-IDF score and list the important topics.

[0508] Step 5:

[0509] The server converts the analysis results into visualization formats such as graphs and charts that are easy to understand intuitively. The input is the sentiment classification and topic analysis results obtained in Step 4. The Python Matplotlib library is used to generate a pie chart showing the proportion of each sentiment, and the wordcloud library is used to create a word cloud of frequently occurring keywords. The output is the visualized data.

[0510] Specific working example:

[0511] The server generates a pie chart based on the sentiment results and displays frequently occurring keywords in a word cloud format.

[0512] Step 6:

[0513] The server automatically generates a report containing the visualized data. The input is the visualization data created in step 5. It creates the report in HTML format using the Jinja2 template engine and delivers it via email using the SMTP protocol. The output is the generated report and the delivery status.

[0514] Specific working example:

[0515] The server generates an HTML report using Jinja2 templates, embedding the visualization data.

[0516] Generated reports are sent via email using the smtplib library.

[0517] Step 7:

[0518] The server periodically updates the data and provides a dashboard that displays it in real time. The input is the latest aggregated data. The real-time dashboard is built using the Flask web framework and the APScheduler library to update the data periodically. The output is the dashboard updated in real time.

[0519] Specific working example:

[0520] The server uses Flask to build a web dashboard that displays the latest data.

[0521] Use APScheduler to run data refresh jobs periodically to ensure your dashboard always reflects the latest information.

[0522] (Application example 1)

[0523] 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."

[0524] There is a need to quickly and efficiently collect real-time feedback from the market for newly released autonomous vehicles, analyze it, and provide visualized data to stakeholders in order to quickly improve vehicle performance and add new functions.Since such a feedback system requires real-time performance, it has been difficult to achieve this using conventional methods.

[0525] 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.

[0526] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, means for accessing a specific online platform that collects feedback via an API, means for displaying the analysis results in real time on a smartphone and an in-vehicle display, and means for periodically updating aggregated data and displaying it in real time, thereby enabling the system to quickly understand user feedback and improve performance or add new functions.

[0527] "Means for automatically collecting posts related to specified keywords from multiple online platforms" refers to a function that automatically collects posts related to specific keywords from multiple online platforms, such as Twitter, Facebook, and Instagram, via API.

[0528] "Means for storing collected posts in a database" refers to a function for safely and efficiently storing the content and metadata of collected posts in a database.

[0529] "Means to remove spam and noise from saved posts" refers to a function that filters inappropriate content and irrelevant information from collected posting data.

[0530] "Means for analyzing the sentiment and topics of posts using natural language processing technology" refers to technology that analyzes the collected content of posts and extracts sentiment classifications such as positive, negative, and neutral, as well as major topics.

[0531] "Means for converting analysis results into visualization formats such as graphs and charts" refers to a function that converts the data obtained from the analysis into formats such as pie charts, bar graphs, and word clouds in order to display them graphically.

[0532] The "means for automatically generating a report including visualized data" is a function for automatically creating a report based on visualized data and providing it to a user.

[0533] The "means for distributing the generated report to the relevant parties" is a function for quickly distributing the generated report to the relevant parties via email or chat tools.

[0534] "Means of accessing specific online platforms that collect feedback via API" refers to a function that obtains posting data using the API of designated online platforms such as Twitter, Facebook, and Instagram.

[0535] "Means for displaying analysis results in real time on a smartphone and in-vehicle display" refers to a function that displays the results of analysis of posts in real time on a smartphone or the in-vehicle display of an autonomous vehicle.

[0536] The "means for periodically updating the aggregated data and displaying it in real time" is a function for periodically updating the collected data and displaying the latest information in real time.

[0537] This invention is a system that efficiently collects, analyzes, and provides real-time feedback from the autonomous vehicle market to stakeholders. This system is configured as follows.

[0538] The server automatically collects posts related to the specified keywords from multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) via API. The collected data is stored in a database, including the post content, user ID, and posting date and time.

[0539] The server then filters out spam and noise from the stored submissions using filtering based on specific keyword lists and blacklists.

[0540] The server then uses natural language processing techniques (specifically, NLP libraries such as SpaCy and NLTK) to analyze the sentiment and topics of the posts, classifying each post as positive, negative, or neutral, and extracting major topics and frequently occurring keywords.

[0541] The analysis results are converted into visualization formats such as graphs and charts by the server. Graph drawing libraries such as D3.js are used for this visualization. Reports are automatically generated based on the visualized data and distributed to relevant parties via email or chat tools. This allows stakeholders to quickly grasp market feedback and respond immediately.

[0542] Furthermore, the system has the ability to access specific online platforms that collect feedback via API and display the analysis results in real time on a smartphone and in-car display, allowing drivers to check important feedback at the appropriate time while driving.

[0543] A dashboard is also provided that regularly updates aggregated data and displays it in real time, allowing stakeholders to always check the latest market valuations and user sentiment.

[0544] For example, if a user posts on social media that a new self-driving vehicle is too slow immediately after its release, the system will instantly collect the post, analyze it as a negative evaluation, classify it as a problem with the self-braking function, visualize it, and deliver it to the development team as a report.

[0545] An example prompt is:

[0546] "Collect social media posts about new autonomous vehicles and analyze them for sentiment and key topics. Visualize the results and generate a word cloud showing the percentage of positive and negative feedback, as well as key issues."

[0547] In this way, the system of the present invention can quickly and efficiently collect and analyze market feedback on autonomous vehicles and provide it in real time, thereby contributing to improved user satisfaction and product quality.

[0548] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0549] Step 1:

[0550] Data collection

[0551] Subject: Server

[0552] Input: the specified keyword

[0553] How it works: The server collects posts related to specified keywords via APIs of online platforms such as Twitter, Facebook, and Instagram.

[0554] Output: Collected submission data

[0555] Step 2:

[0556] Data storage

[0557] Subject: Server

[0558] Input: Collected submission data

[0559] How it works: The server stores the collected post data in a database, which includes metadata such as the post content, user ID, post date and time, and hashtags and mentions used.

[0560] Output: Post data saved in the database

[0561] Step 3:

[0562] Spam and noise removal

[0563] Subject: Server

[0564] Input: Post data stored in the database

[0565] How it works: The server filters submissions based on specific keyword lists and blacklists to remove spam and noise.

[0566] Output: Filtered post data

[0567] Step 4:

[0568] Sentiment and topic analysis

[0569] Subject: Server

[0570] Input: Filtered post data

[0571] How it works: The server uses natural language processing techniques to analyze posts for sentiment (positive, negative, neutral), main topics, and frequently occurring keywords. Specifically, it uses NLP libraries (e.g., SpaCy, NLTK).

[0572] Output: Parsed sentiment and topic data

[0573] Step 5:

[0574] Data visualization

[0575] Subject: Server

[0576] Input: Parsed sentiment and topic data

[0577] How it works: The server converts the analysis results into visualizations such as graphs and charts (e.g., pie charts, word clouds), using a graph drawing library such as D3.js.

[0578] Output: Visualized data

[0579] Step 6:

[0580] Report Generation

[0581] Subject: Server

[0582] Input: Visualized data

[0583] How it works: The server automatically generates reports based on the visualized data, including the ratio of positive vs. negative sentiment, major topics and trends, and specific feedback from users.

[0584] Output: Generated report

[0585] Step 7:

[0586] Report Distribution

[0587] Subject: Server

[0588] Input: Generated report

[0589] How it works: The server delivers automatically generated reports to relevant parties via email or chat tools (e.g., Slack, Microsoft Teams).

[0590] Output: Delivered report

[0591] Step 8:

[0592] Real-time display

[0593] Subject: Server

[0594] Input: Aggregate data

[0595] How it works: The server periodically updates the aggregated data and provides real-time display, allowing users to check the latest market valuation and sentiment data on their smartphone or in-car display.

[0596] Output: Data displayed in real time

[0597] Step 9:

[0598] Feedback collection

[0599] Subject: Server

[0600] Input: API of a specific online platform

[0601] Operation: The server accesses a specific online platform via API and collects feedback.

[0602] Output: Collected feedback data

[0603] 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.

[0604] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to stakeholders. Furthermore, by combining it with an emotion engine that recognizes user emotions, more detailed and accurate feedback analysis is possible. This system is implemented through the following steps:

[0605] First, the server uses the APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords. In this step, comments and ratings about new devices and services posted by users on SNS are automatically acquired and stored in a database.

[0606] The server then stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used, allowing for efficient subsequent analysis and filtering processes.

[0607] The server then filters out spam and noise from the submissions stored in the database. This filtering step removes spam submissions and inappropriate data based on specific keyword lists and blacklists, resulting in reliable, cleansed data.

[0608] The server then analyzes the cleansed post data using natural language processing technology and an emotion engine. The emotion engine recognizes the user's emotions expressed in each post and determines whether the post is positive, negative, or neutral. It also extracts major topics and frequently occurring keywords. This emotion analysis provides a clear understanding of the user's specific emotional state.

[0609] The server converts the analysis results into visualizations such as graphs and charts. For example, it generates a pie chart showing the percentage of emotions or a word cloud showing frequently occurring keywords. Furthermore, the analysis results of the emotion engine are also visualized, allowing users to intuitively understand the detailed data.

[0610] The server then automatically generates a report based on the visualized data, including the ratio of positive vs. negative sentiment, key topics, user feedback, and sentiment analysis results from the sentiment engine, all in a visually easy-to-understand format, allowing stakeholders to easily understand the market situation.

[0611] The generated reports are distributed to relevant parties by the server automatically via email or chat tools (such as Slack or Microsoft Teams), allowing relevant parties to quickly grasp the voice of the market and take any necessary action immediately.

[0612] Finally, the server periodically updates the aggregated data and provides a means to display it in real time. This dashboard allows stakeholders to check the latest market valuation and customer satisfaction at any time. Furthermore, the emotion engine generates alerts to notify stakeholders of specific emotional states (e.g., extreme dissatisfaction).

[0613] For example, if a user posts on social media immediately after the release of a new device that "the battery life of the new device is poor," the system immediately collects the post and uses sentiment analysis to determine that it is a negative evaluation. Next, it uses natural language processing to classify it as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. The sentiment engine detects strong user dissatisfaction and generates an alert to immediately notify relevant parties. This series of processes allows developers to quickly identify the problem and take measures to improve it.

[0614] This concludes the description of the embodiment of the present invention. This embodiment allows each step to work together, efficiently and effectively collecting and analyzing market feedback, and enabling rapid market response. The combination of emotion engines allows for a detailed understanding of the user's emotional state, enabling appropriate responses to be taken promptly.

[0615] The processing flow will be explained below.

[0616] Step 1:

[0617] The server uses APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords, thereby automatically obtaining comments and ratings about new devices and new services posted by users on SNS.

[0618] Step 2:

[0619] The server stores the collected post data in a database, where metadata such as the post content, user ID, posting date and time, and used hashtags and mentions are stored based on a schema.

[0620] Step 3:

[0621] The server filters spam and noise from the submissions stored in the database, using specific keyword lists and blacklists to filter out spam submissions and inappropriate data, resulting in reliable, cleansed data.

[0622] Step 4:

[0623] The server analyzes the cleansed post data using natural language processing technology and an emotion engine. The emotion engine recognizes the user's emotions expressed in each post and determines whether the post is positive, negative, or neutral. It also extracts major topics and frequently occurring keywords.

[0624] Step 5:

[0625] The server visualizes the analysis results, generating graphs, charts, and word clouds based on the sentiment analysis results and keyword frequencies obtained through text mining, and creating diagrams to visually display the data.

[0626] Step 6:

[0627] The server automatically generates reports based on the visualized data, including sentiment ratios, major topics, user feedback, and detailed sentiment analysis results from the sentiment engine.

[0628] Step 7:

[0629] The server distributes the generated reports to the relevant parties, automatically sending the reports via email or chat tools (e.g., Slack, Microsoft Teams, etc.), and managing the distribution logs.

[0630] Step 8:

[0631] The server runs a calculation process that periodically updates the aggregated data and displays it on the dashboard in real time, allowing stakeholders to always see the latest market evaluations and customer satisfaction figures.

[0632] Step 9:

[0633] The server generates alerts for specific emotional states (e.g., extreme dissatisfaction) recognized by the emotion engine, allowing relevant parties to be notified immediately and respond quickly.

[0634] Example 2

[0635] 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."

[0636] With conventional systems, it was difficult to efficiently collect, analyze, visualize, and quickly provide real-time feedback from the market after the release of new devices or services. Furthermore, the analytical technology required to grasp user sentiment in detail was insufficient, making it difficult to quickly take appropriate action.

[0637] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0638] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology and an emotion engine, means for converting the analysis results into a visualized format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to interested parties via email or a chat tool, means for periodically updating the aggregated data and displaying it in real time, and means for detecting specific emotional states using the emotion engine and generating alerts. This makes it possible to quickly and precisely collect, analyze, visualize, and provide relevant parties with feedback from the market after the release of a new device or service.

[0639] "Specified Keywords" are specific words or phrases used to collect targeted posts.

[0640] An "online platform" is a system that provides services over the Internet and allows users to post and share content. Examples include social networking platforms.

[0641] A "post" is any content such as a comment, rating, photo, or video posted by a user on an online platform.

[0642] "Collection methods" refers to technologies or methods for automatically obtaining posts related to designated keywords from online platforms.

[0643] A "database" is a storage device for systematically storing and managing collected submission data.

[0644] "Spam" and "noise" refer to information that is inappropriate or irrelevant for analysis. Spam is irrelevant posts sent in large quantities, while noise is unnecessary data that reduces the accuracy of analysis.

[0645] "Natural language processing technology" refers to the technology that uses computers to analyze, understand, and generate human language.

[0646] An "emotion engine" is software or algorithms used to identify and classify user emotions contained in posts.

[0647] A "visualization format" is a method of converting analytical results into graphics such as graphs and charts so that they can be understood at a glance.

[0648] A "report" is a document or file that summarizes the results of analysis and visualization and provides them to stakeholders.

[0649] "Email and chat tools" refers to applications for sending generated reports to relevant parties via communication means.

[0650] "Means of displaying in real time" refers to a system that regularly updates the latest data so that relevant parties can check it immediately.

[0651] An "alert" is a notification function that alerts relevant parties when a specific condition is met.

[0652] This invention is a system that collects real-time feedback from the market when a new device or service is released, analyzes it, and provides visualized data to stakeholders. Furthermore, by combining it with an emotion engine, detailed and accurate feedback analysis is achieved. This system is mainly composed of a server, a device, and a user.

[0653] server

[0654] The server first uses APIs from multiple online platforms (Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords. It authenticates with each platform using an API key and obtains data in JSON format. The collected post data is then stored in a NoSQL database such as MongoDB. The stored data includes metadata such as the post content, user ID, posting date and time, and used hashtags and mentions.

[0655] The server then filters the collected submission data to remove spam and noise. This involves filtering the data using specific keyword lists and blacklists. By removing spam submissions and eliminating noise data, the server obtains reliable, cleansed data.

[0656] The server then analyzes the cleansed post data using natural language processing techniques (NLP libraries, e.g., SpaCy, NLTK) and a sentiment engine (e.g., Hugging Face sentiment analysis model). The sentiment engine identifies user sentiment expressed in each post and classifies it as positive, negative, or neutral. It also extracts major topics and frequently occurring keywords.

[0657] The analysis results are converted by the server into visualization formats such as graphs and charts (using Matplotlib, D3.js, Plotly, and Chart.js), with pie charts showing sentiment percentages and word clouds showing frequent keywords.

[0658] Finally, the server automatically generates reports based on the visualized data and distributes them to relevant parties via email or chat tools (Slack, Microsoft Teams, etc.). Furthermore, it provides a dashboard that periodically aggregates data and displays it in real time. It also has a function that generates alerts to relevant parties when a specific emotional state (such as extreme dissatisfaction) is detected by the emotion engine.

[0659] Terminal

[0660] The terminals display reports and real-time evaluation data delivered from the server, allowing participants to quickly grasp market conditions and take any necessary action immediately.

[0661] User

[0662] Users provide feedback on new devices and services on the online platform, which allows the system to collect and analyze specific market evaluations and sentiments.

[0663] Specific examples

[0664] For example, if a user posts on social media that "my new device's battery life is poor," the server collects the post via the Twitter API and stores it in MongoDB. It then uses a blacklist to filter out spam posts, and the content is saved as cleansed data. The server then uses natural language processing technology and an emotion engine to analyze the negative emotions, including dissatisfaction with the "battery." The results are then distributed to relevant parties in a visualized format (pie chart or word cloud). Additionally, if a specific emotional state is detected, an immediate alert is sent via Slack or other means.

[0665] Prompt Sentence Examples

[0666] "Describe a system that instantly analyzes market reactions after the release of a new device, categorizes user feedback with an emotion engine, and generates real-time visualizations."

[0667] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0668] Step 1: Data collection

[0669] The server uses APIs of online platforms such as Twitter, Facebook, and Instagram to collect posts containing specified keywords related to new devices and new services. It requires an API key and keywords as input, and sends a request to each platform to retrieve the posted data in JSON format. The output is the collected posted data.

[0670] As a specific example of how this works, the server uses the Twitter API to collect tweets containing the keyword "new device."

[0671] Step 2: Save data

[0672] The server stores the collected post data in a NoSQL database such as MongoDB. The input is the collected post data in JSON format, and the output is the data stored in the database.

[0673] As a specific example of how this works, the server stores the acquired post data as a document in MongoDB, including metadata such as the post content, user ID, posting date and time, and hashtags.

[0674] Step 3: Data cleansing

[0675] The server filters out spam and noise from the stored data. The input is the submitted data stored in the database, and the output is the cleansed data.

[0676] In particular, the server may use specific keyword lists or blacklists to filter out irrelevant or spam posts and remove them.

[0677] Step 4: Data analysis

[0678] The server analyzes the cleansed data using natural language processing technology and an emotion engine. The input is the cleansed posted data, and the output is the analysis results.

[0679] For example, the server analyzes posts using an NLP library (e.g., SpaCy) to extract topics, and then uses an emotion engine (e.g., the Hugging Face model) to classify emotions into positive, negative, and neutral.

[0680] Step 5: Data visualization

[0681] The server converts the analysis results into a visualization format: the input is the analysis results and the output is the visualized graphs and charts.

[0682] As a specific example of how it works, the server uses Matplotlib and D3.js to create pie charts showing the percentage of sentiment analysis and word clouds showing frequently occurring keywords.

[0683] Step 6: Report generation and delivery

[0684] The server generates reports based on the visualized data and distributes them to relevant parties via email or chat tools. The input is the visualized data, and the output is the generated report and the distribution completion status.

[0685] For example, the server generates a report in PDF format and emails it to interested parties via an SMTP server, and also sends a message containing the visualization data using the Slack API.

[0686] Step 7: Real-time updates and alerts

[0687] The server periodically aggregates data and provides a dashboard that displays it in real time. Furthermore, an emotion engine detects specific emotional states and generates alerts. The input is newly collected post data and analysis results, and the output is an updated dashboard and alert notifications.

[0688] For example, the server uses Node.js and Socket.IO to update the dashboard in real time, and when it detects certain emotional states, such as extreme dissatisfaction, it sends alerts to relevant parties via SMS or push notifications.

[0689] (Application example 2)

[0690] 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."

[0691] After the release of a new device or service, there is a need to collect, analyze, and visualize customer feedback in real time so that quick and specific responses can be taken. However, traditional feedback collection methods have problems with incomplete spam and noise removal and low sentiment analysis accuracy, making it difficult to accurately grasp market trends. In addition, the inability to generate notifications or alerts in real time makes it difficult to take quick action.

[0692] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, means for periodically updating and displaying aggregated data in real time, means for notifying customer feedback in real time, means for generating and distributing alerts based on specific sentiment results, and means for viewing the visualized data on a dashboard. This allows relevant parties to grasp the market's voice in real time and respond promptly and appropriately.

[0693] "Post" means a message or comment written by a User on an Online Platform.

[0694] "Online platform" refers to an internet service that provides social networking services such as Twitter, Facebook, and Instagram.

[0695] A "database" is a storage medium for structuring and storing collected data.

[0696] "Spam and noise" refers to unnecessary advertising and irrelevant, meaningless data.

[0697] "Natural language processing technology" is a technology that analyzes human language and converts it into a format that a computer can understand and process.

[0698] "Sentiment analysis" is the use of natural language processing technology to classify users' emotions into positive, negative, or neutral based on the content of their posts.

[0699] "Topic" refers to a recurring theme or subject matter within a post.

[0700] A "visualization format" is a method of presenting analytical results in a visually easy-to-understand format, such as a graph or chart.

[0701] A "report" is a document that summarizes visualized data and analysis results.

[0702] "Real-time notification" means instantly informing relevant parties of analysis results and feedback.

[0703] An "alert" refers to issuing a warning to relevant parties when a specific condition or emotional outcome is detected.

[0704] A "dashboard" is an interface for visually and centrally managing analysis results and feedback.

[0705] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to relevant parties. In particular, it provides a mechanism that allows quick confirmation of customer feedback and immediate response as needed.

[0706] The system includes the following components:

[0707] 1. Data Collection

[0708] The server automatically collects relevant posts from multiple online platforms (e.g., social networking services) and retrieves posts based on specified keywords using the API of each platform.

[0709] 2. Data storage

[0710] The server stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used.

[0711] 3. Data Cleansing

[0712] The server filters out spam and noise from the submission data stored in the database, and filters out inappropriate data based on specific keyword lists and blacklists.

[0713] 4. Sentiment Analysis and Topic Extraction

[0714] The server analyzes the cleansed post data using natural language processing technology and an emotion engine, which classifies the sentiment of posts into positive, negative, and neutral, and extracts major topics and frequently occurring keywords.

[0715] 5. Data Visualization

[0716] The server then converts the analysis results into visualizations such as graphs and charts, including pie charts showing sentiment percentages and word clouds showing major topics.

[0717] 6. Report Generation and Delivery

[0718] The server automatically generates reports based on the visualized data and distributes them to relevant parties via email or chat tools.

[0719] 7. Real-time notifications and dashboard display

[0720] The server periodically updates the data, providing a dashboard with real-time display, and also provides real-time customer feedback and generates alerts based on specific sentiment results.

[0721] Program processing explanation

[0722] The hardware used includes servers and devices such as smartphones and tablets, while the software used includes APIs from each online platform, the Python requests library, the NLTK library for natural language processing, a sentiment analysis engine, and the matplotlib library for visualization.

[0723] Data collection:

[0724] Post data is obtained from each platform via API and stored in a database.

[0725] Data cleansing:

[0726] Filter out spam and noise to create a clean dataset.

[0727] Sentiment analysis and topic extraction:

[0728] We use the NLTK library and a sentiment analysis engine to classify and extract the sentiment and main topics of each post.

[0729] Data Visualization:

[0730] The matplotlib library is used to convert the analysis results into visually understandable formats such as pie charts and word clouds.

[0731] Report generation and delivery:

[0732] Reports are automatically created based on the generated visualization data and distributed to relevant parties via email or chat tools.

[0733] Real-time notifications and dashboard views:

[0734] It regularly updates the data, providing a dashboard with up-to-date feedback, and provides real-time alerts when specific sentiment results are detected.

[0735] Specific examples

[0736] For example, if a store launches a new service and a customer posts on social media, "This new service is so convenient!", this positive feedback will be immediately notified to the store manager. Similarly, if there is a negative post such as "The wait time for service is long," the store manager will be notified in the same way, so that they can take immediate action.

[0737] Prompt sentence for generative AI model

[0738] We will design a smartphone application that collects real-time social media feedback after the release of a new service or device, and analyzes and visualizes positive and negative sentiment. This application uses Python's requests library to collect data from social media APIs, combines natural language processing and an emotion engine to analyze the feedback, and visualizes it using matplotlib. As a concrete example, if a customer posts on social media that "the wait time for service is long," this negative feedback will be immediately notified to the store manager.

[0739] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0740] Step 1: Data collection

[0741] The server collects posts based on the specified keywords using APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram).

[0742] Input: the specified keyword

[0743] Data processing: Acquiring posts through API, analyzing JSON format data

[0744] Output: Retrieved post data (metadata such as post content, user ID, post date and time)

[0745] Step 2: Save data

[0746] The server stores the collected posting data in a database.

[0747] Input: Collected submission data

[0748] Data processing: Inserting data into the database

[0749] Output: Post data saved in the database

[0750] Step 3: Remove spam noise

[0751] The server filters out spam and noise from posts stored in a database.

[0752] Input: Post data read from the database

[0753] Data processing: filtering based on specific keyword lists or blacklists

[0754] Output: Cleansed post data

[0755] Step 4: Sentiment analysis and topic extraction

[0756] The server uses natural language processing technology and an emotion engine to analyze the sentiment and topic of posts.

[0757] Input: Cleansed post data

[0758] Data processing: Sentiment determination and topic extraction using natural language processing techniques

[0759] Output: Analysis data with sentiment and topic annotations

[0760] Step 5: Data visualization

[0761] The server converts the analysis results into visualization formats such as graphs and charts.

[0762] Input: Analysis data with sentiment and topic annotations

[0763] Data processing: Graph generation using visualization libraries (e.g., matplotlib)

[0764] Output: Visualized graphs and charts

[0765] Step 6: Report generation and distribution

[0766] The server automatically generates reports based on the visualized data and distributes them to relevant parties.

[0767] Input: Data for visualizations of graphs and charts

[0768] Data processing: Report generation and distribution via email or chat tools

[0769] Output: Report sent to stakeholders

[0770] Step 7: Real-time notifications and dashboard display

[0771] The server provides a dashboard that periodically updates and displays the data in real time, and also generates alerts based on specific sentiment results.

[0772] Input: Real-time collected analytics data

[0773] Data processing: Display on dashboard and generate alerts

[0774] Output: Latest data displayed in the dashboard and delivered alerts

[0775] 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.

[0776] 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.

[0777] 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.

[0778] [Third embodiment]

[0779] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0780] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0781] 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).

[0782] 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.

[0783] 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.

[0784] 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).

[0785] 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. 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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."

[0791] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to stakeholders. This system is implemented through the following steps.

[0792] First, the server uses the APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords, and then automatically collects comments and ratings posted by users about new devices and services.

[0793] The server then stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used, allowing for efficient subsequent analysis and filtering processes.

[0794] Next, the server removes spam and noise from the posted data stored in the database. In this step, spam is identified based on specific keyword lists and blacklists, and inappropriate data is filtered out. This process improves the accuracy of analysis and produces reliable data.

[0795] The server then uses natural language processing technology to analyze the sentiment and topics of the posts. This analysis classifies each post as positive, negative, or neutral, and extracts key topics and frequently occurring keywords. This provides a concrete understanding of users' opinions and sentiments.

[0796] The server then converts the analysis results into visualizations such as graphs and charts, such as pie charts showing sentiment percentages or word clouds displaying frequently occurring keywords, providing data in an intuitive and easy-to-understand format.

[0797] The server then automatically generates a report with visualized data, including the percentage of positive vs. negative sentiment, major topics and trends, and specific feedback from users.

[0798] The generated reports are distributed to relevant parties by the server automatically via email or chat tools (such as Slack or Microsoft Teams), allowing relevant parties to quickly grasp the voice of the market and take any necessary action immediately.

[0799] Finally, the server periodically updates the aggregated data and provides a means for displaying it in real time. This dashboard allows stakeholders to check the latest market evaluations and customer satisfaction at any time. In this way, the present invention enables quick and accurate market responses, contributing to improving a company's competitiveness and customer satisfaction.

[0800] The above is an embodiment of the present invention. This embodiment allows each step to work together, enabling efficient and effective collection and analysis of market feedback. For example, if a user posts on social media immediately after the release of a new device, saying, "The battery life of the new device is poor," this system instantly collects the post and determines through sentiment analysis that it is a negative evaluation. It then classifies the post as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. This allows developers to quickly identify the problem and take measures to improve it.

[0801] In this way, the system of the present invention becomes a powerful tool for companies to take advantage of real-time feedback from the market and respond quickly.

[0802] The processing flow will be explained below.

[0803] Step 1:

[0804] The server periodically searches and collects posts containing specified keywords using the APIs of multiple online platforms (Twitter, Facebook, Instagram, etc.), sends API requests, and retrieves the relevant post data.

[0805] Step 2:

[0806] The server stores the collected post data in a database, specifically metadata such as the post content, user ID, posting date and time, and used hashtags and mentions, based on an appropriate schema.

[0807] Step 3:

[0808] The server filters out spam and noise from the submissions stored in the database, using specific keyword lists and blacklists to filter out spam submissions and inappropriate data, eliminating unnecessary data.

[0809] Step 4:

[0810] The server then analyzes the cleansed post data using natural language processing (NLP) technology. This involves performing sentiment analysis on each post to determine whether it is classified as positive, negative, or neutral, and extracting key topics and frequently occurring keywords.

[0811] Step 5:

[0812] The server visualizes the analysis results, converting the sentiment interpretations and keyword frequencies obtained through text mining into graphs, charts, word clouds, and other diagrams to visually display the data.

[0813] Step 6:

[0814] The server automatically generates reports based on the visualized data, including analysis results such as sentiment ratings, key topics, and user feedback, and presents this information in an intuitive format for stakeholders.

[0815] Step 7:

[0816] The server distributes the generated reports to the relevant parties. The reports are automatically sent via email or chat tools (Slack, Microsoft Teams, etc.). It also manages distribution logs and monitors whether the distribution was successful.

[0817] Step 8:

[0818] The server runs a process that periodically updates the aggregated data and displays it on the dashboard in real time, allowing stakeholders to always check the latest market evaluations and customer satisfaction. Data is updated at specified time intervals, and the dashboard display is updated accordingly.

[0819] Example 1

[0820] 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."

[0821] If market feedback is not collected quickly and effectively after the release of a new device or service, companies will be unable to respond appropriately to customer opinions and sentiments, resulting in a decline in competitiveness and customer satisfaction. Furthermore, if collected data is left unorganized, unreliable analysis results may result. In such situations, it becomes difficult to respond to the market in real time, requiring companies to make quick decisions and take action.

[0822] 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.

[0823] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, and means for periodically updating the aggregated data and displaying it in real time. This makes it possible to quickly and accurately grasp market feedback about new devices and new services and take appropriate measures.

[0824] "Specified keywords" refer to words or phrases that a user has specified to gather specific information.

[0825] "Post" means a message, comment or review posted publicly by a User on an Online Platform.

[0826] "Online Platform" refers to web-based services that enable users to publish and share information, such as social networking services, blogs, and forums.

[0827] An "application program interface (API)" refers to a set of rules or protocols that allow different software applications to communicate with each other.

[0828] A "database" refers to a system that stores data in a structured manner that allows it to be efficiently managed, queried, and manipulated.

[0829] "Spam" refers to unsolicited messages or irrelevant postings sent in large quantities over the Internet.

[0830] "Noise" refers to unnecessary information or inaccurate data contained in the data being analyzed.

[0831] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[0832] "Sentiment analysis" refers to the technology of classifying emotional states (positive, negative, neutral, etc.) from text data.

[0833] "Topic extraction" refers to the technique of identifying key concepts or themes from text data.

[0834] "Visualization format" refers to the way data is visually represented in the form of graphs and charts.

[0835] "Report" refers to a document summarizing the analysis results and providing them to relevant parties.

[0836] "Aggregated Data" refers to data that compiles multiple data points into statistical information.

[0837] "Real-time display" means that data is displayed immediately as soon as it is updated.

[0838] The system of the present invention aims to collect and analyze real-time feedback from the market after the release of a new terminal or new service, visualize the results, and provide them to the relevant parties. This system is implemented as follows.

[0839] Hardware and software used

[0840] First, the main hardware and software used in this system are listed below.

[0841] Hardware

[0842] Server: Primarily responsible for collecting, storing, analyzing, visualizing, and distributing data. For example, an EC2 instance from Amazon Web Services (AWS) is used.

[0843] Database server: Stores and manages collected data. For example, AWS RDS or MySQL is used.

[0844] software

[0845] Social media platform APIs: Used to collect data. Examples include Twitter API and Facebook Graph API.

[0846] Database management systems: Examples include MySQL and PostgreSQL.

[0847] Natural language processing libraries: Mainly use NLTK and spaCy.

[0848] Data visualization tools: Matplotlib and D3.js are used.

[0849] Communication tools: Slack API and Microsoft Teams API are used for report distribution.

[0850] Specific operation of the system

[0851] The server first automatically collects posts related to the specified keywords from multiple online platforms. To do this, it uses the APIs of the social media platforms. For example, it uses the Twitter API to search for and retrieve posts using the keyword "new device." The collected post data is then saved in a database. The data is received in JSON format, parsed, and stored in the database as structured data.

[0852] After the collected submission data is saved, it is extracted from the database and filtered for spam and noise. Specific keyword lists and blacklists are used to identify spam, and the data is converted into a data frame using the Python pandas library to remove inappropriate data.

[0853] The server then uses natural language processing techniques to analyze the sentiment and topics of the collected posts. Specifically, it uses the NLTK library to perform sentiment analysis of the text and classify it as positive, negative, or neutral. It also uses TF-IDF (Term Frequency-Inverse Document Frequency) scores to extract major topics and frequently occurring keywords.

[0854] The analysis results are converted into an intuitively understandable visualization format. The server uses Matplotlib to generate pie charts showing the percentage of each sentiment, and the wordcloud library to generate word clouds of frequently occurring keywords. This allows users to visually grasp the overall trends and main opinions of the collected data.

[0855] Additionally, the server automatically generates reports containing visualized data in HTML format using the Jinja2 template engine, which are then distributed to interested parties via email using the SMTP protocol, allowing for quick sharing of market opinions and assessments.

[0856] Finally, the server periodically refreshes the data and provides a dashboard that displays it in real time. Using the Flask web framework, we expose a real-time dashboard, allowing users to see the latest status of the aggregated data at any time.

[0857] Examples of concrete examples and prompts

[0858] For example, if a user posts on social media immediately after a new device is released that "the battery life of the new device is poor," the system instantly collects the post and determines that it is a negative evaluation through sentiment analysis. It then classifies it as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. This allows developers to quickly identify the problem and take measures to improve it.

[0859] Prompt Sentence Examples

[0860] "Please explain the steps in your system to collect posts from social media and perform sentiment analysis and topic extraction. Please be specific about how your system collects data, analyzes it using natural language processing techniques, and visualizes the results."

[0861] By utilizing this system, companies will have a powerful tool to quickly analyze real-time feedback from the market and take appropriate countermeasures.

[0862] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0863] Step 1:

[0864] The server automatically collects posts related to a specified keyword from multiple online platforms. The input is a specific keyword (e.g., "new device") and the API credentials of the online platform. It uses the Python tweepy library to send a search query to the Twitter API and retrieves related post data. The output is the retrieved post data in JSON format.

[0865] Specific working example:

[0866] The server sends a request to the Twitter API with a pre-defined keyword.

[0867] The JSON data returned from the API contains information such as the content of each post, the user ID, and the posting date and time.

[0868] Step 2:

[0869] The server saves the collected post data in a database. The input is the JSON format post data obtained in step 1. It connects to the database using Python's MySQL-connector library, parses the JSON data, and inserts each field into the corresponding table. The output is structured data saved in the database.

[0870] Specific working example:

[0871] The server establishes a database connection and parses each field of the JSON data to generate an SQL INSERT statement.

[0872] The generated SQL statement is executed and the collected post data is stored in a database.

[0873] Step 3:

[0874] The server reads collected submission data from the database and removes spam and noise. The input is the raw data read from the database. The data is converted into a data frame using the Python pandas library and filtered based on a specific keyword list or blacklist. The output is clean data with spam and noise removed.

[0875] Specific working example:

[0876] The server fetches the data from the database and converts it into a pandas dataframe.

[0877] Apply criteria to filter out inappropriate data using keyword lists and blacklists.

[0878] Step 4:

[0879] The server uses natural language processing technology to analyze the sentiment and topics of the collected post data. The input is the clean data obtained in step 3. It performs sentiment analysis of the text using Python's NLTK library and classifies it as positive, negative, or neutral. It also uses the TF-IDF method to extract major topics and frequently occurring keywords. The output is the sentiment classification results and topic analysis results.

[0880] Specific working example:

[0881] The server applies the nltk.sentiment.vader.SentimentIntensityAnalyzer to calculate a sentiment score for each post.

[0882] Calculate the TF-IDF score and list the important topics.

[0883] Step 5:

[0884] The server converts the analysis results into visualization formats such as graphs and charts that are easy to understand intuitively. The input is the sentiment classification and topic analysis results obtained in Step 4. The Python Matplotlib library is used to generate a pie chart showing the proportion of each sentiment, and the wordcloud library is used to create a word cloud of frequently occurring keywords. The output is the visualized data.

[0885] Specific working example:

[0886] The server generates a pie chart based on the sentiment results and displays frequently occurring keywords in a word cloud format.

[0887] Step 6:

[0888] The server automatically generates a report containing the visualized data. The input is the visualization data created in step 5. It creates the report in HTML format using the Jinja2 template engine and delivers it via email using the SMTP protocol. The output is the generated report and the delivery status.

[0889] Specific working example:

[0890] The server generates an HTML report using Jinja2 templates, embedding the visualization data.

[0891] Generated reports are sent via email using the smtplib library.

[0892] Step 7:

[0893] The server periodically updates the data and provides a dashboard that displays it in real time. The input is the latest aggregated data. The real-time dashboard is built using the Flask web framework and the APScheduler library to update the data periodically. The output is the dashboard updated in real time.

[0894] Specific working example:

[0895] The server uses Flask to build a web dashboard that displays the latest data.

[0896] Use APScheduler to run data refresh jobs periodically to ensure your dashboard always reflects the latest information.

[0897] (Application example 1)

[0898] 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."

[0899] There is a need to quickly and efficiently collect real-time feedback from the market for newly released autonomous vehicles, analyze it, and provide visualized data to stakeholders in order to quickly improve vehicle performance and add new functions.Since such a feedback system requires real-time performance, it has been difficult to achieve this using conventional methods.

[0900] 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.

[0901] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, means for accessing a specific online platform that collects feedback via an API, means for displaying the analysis results in real time on a smartphone and an in-vehicle display, and means for periodically updating aggregated data and displaying it in real time, thereby enabling the system to quickly understand user feedback and improve performance or add new functions.

[0902] "Means for automatically collecting posts related to specified keywords from multiple online platforms" refers to a function that automatically collects posts related to specific keywords from multiple online platforms, such as Twitter, Facebook, and Instagram, via API.

[0903] "Means for storing collected posts in a database" refers to a function for safely and efficiently storing the content and metadata of collected posts in a database.

[0904] "Means to remove spam and noise from saved posts" refers to a function that filters inappropriate content and irrelevant information from collected posting data.

[0905] "Means for analyzing the sentiment and topics of posts using natural language processing technology" refers to technology that analyzes the collected content of posts and extracts sentiment classifications such as positive, negative, and neutral, as well as major topics.

[0906] "Means for converting analysis results into visualization formats such as graphs and charts" refers to a function that converts the data obtained from the analysis into formats such as pie charts, bar graphs, and word clouds in order to display them graphically.

[0907] The "means for automatically generating a report including visualized data" is a function for automatically creating a report based on visualized data and providing it to a user.

[0908] The "means for distributing the generated report to the relevant parties" is a function for quickly distributing the generated report to the relevant parties via email or chat tools.

[0909] "Means of accessing specific online platforms that collect feedback via API" refers to a function that obtains posting data using the API of designated online platforms such as Twitter, Facebook, and Instagram.

[0910] "Means for displaying analysis results in real time on a smartphone and in-vehicle display" refers to a function that displays the results of analysis of posts in real time on a smartphone or the in-vehicle display of an autonomous vehicle.

[0911] The "means for periodically updating the aggregated data and displaying it in real time" is a function for periodically updating the collected data and displaying the latest information in real time.

[0912] This invention is a system that efficiently collects, analyzes, and provides real-time feedback from the autonomous vehicle market to stakeholders. This system is configured as follows.

[0913] The server automatically collects posts related to the specified keywords from multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) via API. The collected data is stored in a database, including the post content, user ID, and posting date and time.

[0914] The server then filters out spam and noise from the stored submissions using filtering based on specific keyword lists and blacklists.

[0915] The server then uses natural language processing techniques (specifically, NLP libraries such as SpaCy and NLTK) to analyze the sentiment and topics of the posts, classifying each post as positive, negative, or neutral, and extracting major topics and frequently occurring keywords.

[0916] The analysis results are converted into visualization formats such as graphs and charts by the server. Graph drawing libraries such as D3.js are used for this visualization. Reports are automatically generated based on the visualized data and distributed to relevant parties via email or chat tools. This allows stakeholders to quickly grasp market feedback and respond immediately.

[0917] Furthermore, the system has the ability to access specific online platforms that collect feedback via API and display the analysis results in real time on a smartphone and in-car display, allowing drivers to check important feedback at the appropriate time while driving.

[0918] A dashboard is also provided that regularly updates aggregated data and displays it in real time, allowing stakeholders to always check the latest market valuations and user sentiment.

[0919] For example, if a user posts on social media that a new self-driving vehicle is too slow immediately after its release, the system will instantly collect the post, analyze it as a negative evaluation, classify it as a problem with the self-braking function, visualize it, and deliver it to the development team as a report.

[0920] An example prompt is:

[0921] "Collect social media posts about new autonomous vehicles and analyze them for sentiment and key topics. Visualize the results and generate a word cloud showing the percentage of positive and negative feedback, as well as key issues."

[0922] In this way, the system of the present invention can quickly and efficiently collect and analyze market feedback on autonomous vehicles and provide it in real time, thereby contributing to improved user satisfaction and product quality.

[0923] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0924] Step 1:

[0925] Data collection

[0926] Subject: Server

[0927] Input: the specified keyword

[0928] How it works: The server collects posts related to specified keywords via APIs of online platforms such as Twitter, Facebook, and Instagram.

[0929] Output: Collected submission data

[0930] Step 2:

[0931] Data storage

[0932] Subject: Server

[0933] Input: Collected submission data

[0934] How it works: The server stores the collected post data in a database, which includes metadata such as the post content, user ID, post date and time, and hashtags and mentions used.

[0935] Output: Post data saved in the database

[0936] Step 3:

[0937] Spam and noise removal

[0938] Subject: Server

[0939] Input: Post data stored in the database

[0940] How it works: The server filters submissions based on specific keyword lists and blacklists to remove spam and noise.

[0941] Output: Filtered post data

[0942] Step 4:

[0943] Sentiment and topic analysis

[0944] Subject: Server

[0945] Input: Filtered post data

[0946] How it works: The server uses natural language processing techniques to analyze posts for sentiment (positive, negative, neutral), main topics, and frequently occurring keywords. Specifically, it uses NLP libraries (e.g., SpaCy, NLTK).

[0947] Output: Parsed sentiment and topic data

[0948] Step 5:

[0949] Data visualization

[0950] Subject: Server

[0951] Input: Parsed sentiment and topic data

[0952] How it works: The server converts the analysis results into visualizations such as graphs and charts (e.g., pie charts, word clouds), using a graph drawing library such as D3.js.

[0953] Output: Visualized data

[0954] Step 6:

[0955] Report Generation

[0956] Subject: Server

[0957] Input: Visualized data

[0958] How it works: The server automatically generates reports based on the visualized data, including the ratio of positive vs. negative sentiment, major topics and trends, and specific feedback from users.

[0959] Output: Generated report

[0960] Step 7:

[0961] Report Distribution

[0962] Subject: Server

[0963] Input: Generated report

[0964] How it works: The server delivers automatically generated reports to relevant parties via email or chat tools (e.g., Slack, Microsoft Teams).

[0965] Output: Delivered report

[0966] Step 8:

[0967] Real-time display

[0968] Subject: Server

[0969] Input: Aggregate data

[0970] How it works: The server periodically updates the aggregated data and provides real-time display, allowing users to check the latest market valuation and sentiment data on their smartphone or in-car display.

[0971] Output: Data displayed in real time

[0972] Step 9:

[0973] Feedback collection

[0974] Subject: Server

[0975] Input: API of a specific online platform

[0976] Operation: The server accesses a specific online platform via API and collects feedback.

[0977] Output: Collected feedback data

[0978] 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.

[0979] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to stakeholders. Furthermore, by combining it with an emotion engine that recognizes user emotions, more detailed and accurate feedback analysis is possible. This system is implemented through the following steps:

[0980] First, the server uses the APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords. In this step, comments and ratings about new devices and services posted by users on SNS are automatically acquired and stored in a database.

[0981] The server then stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used, allowing for efficient subsequent analysis and filtering processes.

[0982] The server then filters out spam and noise from the submissions stored in the database. This filtering step removes spam submissions and inappropriate data based on specific keyword lists and blacklists, resulting in reliable, cleansed data.

[0983] The server then analyzes the cleansed post data using natural language processing technology and an emotion engine. The emotion engine recognizes the user's emotions expressed in each post and determines whether the post is positive, negative, or neutral. It also extracts major topics and frequently occurring keywords. This emotion analysis provides a clear understanding of the user's specific emotional state.

[0984] The server converts the analysis results into visualizations such as graphs and charts. For example, it generates a pie chart showing the percentage of emotions or a word cloud showing frequently occurring keywords. Furthermore, the analysis results of the emotion engine are also visualized, allowing users to intuitively understand the detailed data.

[0985] The server then automatically generates a report based on the visualized data, including the ratio of positive vs. negative sentiment, key topics, user feedback, and sentiment analysis results from the sentiment engine, all in a visually easy-to-understand format, allowing stakeholders to easily understand the market situation.

[0986] The generated reports are distributed to relevant parties by the server automatically via email or chat tools (such as Slack or Microsoft Teams), allowing relevant parties to quickly grasp the voice of the market and take any necessary action immediately.

[0987] Finally, the server periodically updates the aggregated data and provides a means to display it in real time. This dashboard allows stakeholders to check the latest market valuation and customer satisfaction at any time. Furthermore, the emotion engine generates alerts to notify stakeholders of specific emotional states (e.g., extreme dissatisfaction).

[0988] For example, if a user posts on social media immediately after the release of a new device that "the battery life of the new device is poor," the system immediately collects the post and uses sentiment analysis to determine that it is a negative evaluation. Next, it uses natural language processing to classify it as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. The sentiment engine detects strong user dissatisfaction and generates an alert to immediately notify relevant parties. This series of processes allows developers to quickly identify the problem and take measures to improve it.

[0989] This concludes the description of the embodiment of the present invention. This embodiment allows each step to work together, efficiently and effectively collecting and analyzing market feedback, and enabling rapid market response. The combination of emotion engines allows for a detailed understanding of the user's emotional state, enabling appropriate responses to be taken promptly.

[0990] The processing flow will be explained below.

[0991] Step 1:

[0992] The server uses APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords, thereby automatically obtaining comments and ratings about new devices and new services posted by users on SNS.

[0993] Step 2:

[0994] The server stores the collected post data in a database, where metadata such as the post content, user ID, posting date and time, and used hashtags and mentions are stored based on a schema.

[0995] Step 3:

[0996] The server filters spam and noise from the submissions stored in the database, using specific keyword lists and blacklists to filter out spam submissions and inappropriate data, resulting in reliable, cleansed data.

[0997] Step 4:

[0998] The server analyzes the cleansed post data using natural language processing technology and an emotion engine. The emotion engine recognizes the user's emotions expressed in each post and determines whether the post is positive, negative, or neutral. It also extracts major topics and frequently occurring keywords.

[0999] Step 5:

[1000] The server visualizes the analysis results, generating graphs, charts, and word clouds based on the sentiment analysis results and keyword frequencies obtained through text mining, and creating diagrams to visually display the data.

[1001] Step 6:

[1002] The server automatically generates reports based on the visualized data, including sentiment ratios, major topics, user feedback, and detailed sentiment analysis results from the sentiment engine.

[1003] Step 7:

[1004] The server distributes the generated reports to the relevant parties, automatically sending the reports via email or chat tools (e.g., Slack, Microsoft Teams, etc.), and managing the distribution logs.

[1005] Step 8:

[1006] The server runs a calculation process that periodically updates the aggregated data and displays it on the dashboard in real time, allowing stakeholders to always see the latest market evaluations and customer satisfaction figures.

[1007] Step 9:

[1008] The server generates alerts for specific emotional states (e.g., extreme dissatisfaction) recognized by the emotion engine, allowing relevant parties to be notified immediately and respond quickly.

[1009] Example 2

[1010] 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."

[1011] With conventional systems, it was difficult to efficiently collect, analyze, visualize, and quickly provide real-time feedback from the market after the release of new devices or services. Furthermore, the analytical technology required to grasp user sentiment in detail was insufficient, making it difficult to quickly take appropriate action.

[1012] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1013] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology and an emotion engine, means for converting the analysis results into a visualized format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to interested parties via email or a chat tool, means for periodically updating the aggregated data and displaying it in real time, and means for detecting specific emotional states using the emotion engine and generating alerts. This makes it possible to quickly and precisely collect, analyze, visualize, and provide relevant parties with feedback from the market after the release of a new device or service.

[1014] "Specified Keywords" are specific words or phrases used to collect targeted posts.

[1015] An "online platform" is a system that provides services over the Internet and allows users to post and share content. Examples include social networking platforms.

[1016] A "post" is any content such as a comment, rating, photo, or video posted by a user on an online platform.

[1017] "Collection methods" refers to technologies or methods for automatically obtaining posts related to designated keywords from online platforms.

[1018] A "database" is a storage device for systematically storing and managing collected submission data.

[1019] "Spam" and "noise" refer to information that is inappropriate or irrelevant for analysis. Spam is irrelevant posts sent in large quantities, while noise is unnecessary data that reduces the accuracy of analysis.

[1020] "Natural language processing technology" refers to the technology that uses computers to analyze, understand, and generate human language.

[1021] An "emotion engine" is software or algorithms used to identify and classify user emotions contained in posts.

[1022] A "visualization format" is a method of converting analytical results into graphics such as graphs and charts so that they can be understood at a glance.

[1023] A "report" is a document or file that summarizes the results of analysis and visualization and provides them to stakeholders.

[1024] "Email and chat tools" refers to applications for sending generated reports to relevant parties via communication means.

[1025] "Means of displaying in real time" refers to a system that regularly updates the latest data so that relevant parties can check it immediately.

[1026] An "alert" is a notification function that alerts relevant parties when a specific condition is met.

[1027] This invention is a system that collects real-time feedback from the market when a new device or service is released, analyzes it, and provides visualized data to stakeholders. Furthermore, by combining it with an emotion engine, detailed and accurate feedback analysis is achieved. This system is mainly composed of a server, a device, and a user.

[1028] server

[1029] The server first uses APIs from multiple online platforms (Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords. It authenticates with each platform using an API key and obtains data in JSON format. The collected post data is then stored in a NoSQL database such as MongoDB. The stored data includes metadata such as the post content, user ID, posting date and time, and used hashtags and mentions.

[1030] The server then filters the collected submission data to remove spam and noise. This involves filtering the data using specific keyword lists and blacklists. By removing spam submissions and eliminating noise data, the server obtains reliable, cleansed data.

[1031] The server then analyzes the cleansed post data using natural language processing techniques (NLP libraries, e.g., SpaCy, NLTK) and a sentiment engine (e.g., Hugging Face sentiment analysis model). The sentiment engine identifies user sentiment expressed in each post and classifies it as positive, negative, or neutral. It also extracts major topics and frequently occurring keywords.

[1032] The analysis results are converted by the server into visualization formats such as graphs and charts (using Matplotlib, D3.js, Plotly, and Chart.js), with pie charts showing sentiment percentages and word clouds showing frequent keywords.

[1033] Finally, the server automatically generates reports based on the visualized data and distributes them to relevant parties via email or chat tools (Slack, Microsoft Teams, etc.). Furthermore, it provides a dashboard that periodically aggregates data and displays it in real time. It also has a function that generates alerts to relevant parties when a specific emotional state (such as extreme dissatisfaction) is detected by the emotion engine.

[1034] Terminal

[1035] The terminals display reports and real-time evaluation data delivered from the server, allowing participants to quickly grasp market conditions and take any necessary action immediately.

[1036] User

[1037] Users provide feedback on new devices and services on the online platform, which allows the system to collect and analyze specific market evaluations and sentiments.

[1038] Specific examples

[1039] For example, if a user posts on social media that "my new device's battery life is poor," the server collects the post via the Twitter API and stores it in MongoDB. It then uses a blacklist to filter out spam posts, and the content is saved as cleansed data. The server then uses natural language processing technology and an emotion engine to analyze the negative emotions, including dissatisfaction with the "battery." The results are then distributed to relevant parties in a visualized format (pie chart or word cloud). Additionally, if a specific emotional state is detected, an immediate alert is sent via Slack or other means.

[1040] Prompt Sentence Examples

[1041] "Describe a system that instantly analyzes market reactions after the release of a new device, categorizes user feedback with an emotion engine, and generates real-time visualizations."

[1042] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1043] Step 1: Data collection

[1044] The server uses APIs of online platforms such as Twitter, Facebook, and Instagram to collect posts containing specified keywords related to new devices and new services. It requires an API key and keywords as input, and sends a request to each platform to retrieve the posted data in JSON format. The output is the collected posted data.

[1045] As a specific example of how this works, the server uses the Twitter API to collect tweets containing the keyword "new device."

[1046] Step 2: Save data

[1047] The server stores the collected post data in a NoSQL database such as MongoDB. The input is the collected post data in JSON format, and the output is the data stored in the database.

[1048] As a specific example of how this works, the server stores the acquired post data as a document in MongoDB, including metadata such as the post content, user ID, posting date and time, and hashtags.

[1049] Step 3: Data cleansing

[1050] The server filters out spam and noise from the stored data. The input is the submitted data stored in the database, and the output is the cleansed data.

[1051] In particular, the server may use specific keyword lists or blacklists to filter out irrelevant or spam posts and remove them.

[1052] Step 4: Data analysis

[1053] The server analyzes the cleansed data using natural language processing technology and an emotion engine. The input is the cleansed posted data, and the output is the analysis results.

[1054] For example, the server analyzes posts using an NLP library (e.g., SpaCy) to extract topics, and then uses an emotion engine (e.g., the Hugging Face model) to classify emotions into positive, negative, and neutral.

[1055] Step 5: Data visualization

[1056] The server converts the analysis results into a visualization format: the input is the analysis results and the output is the visualized graphs and charts.

[1057] As a specific example of how it works, the server uses Matplotlib and D3.js to create pie charts showing the percentage of sentiment analysis and word clouds showing frequently occurring keywords.

[1058] Step 6: Report generation and delivery

[1059] The server generates reports based on the visualized data and distributes them to relevant parties via email or chat tools. The input is the visualized data, and the output is the generated report and the distribution completion status.

[1060] For example, the server generates a report in PDF format and emails it to interested parties via an SMTP server, and also sends a message containing the visualization data using the Slack API.

[1061] Step 7: Real-time updates and alerts

[1062] The server periodically aggregates data and provides a dashboard that displays it in real time. Furthermore, an emotion engine detects specific emotional states and generates alerts. The input is newly collected post data and analysis results, and the output is an updated dashboard and alert notifications.

[1063] For example, the server uses Node.js and Socket.IO to update the dashboard in real time, and when it detects certain emotional states, such as extreme dissatisfaction, it sends alerts to relevant parties via SMS or push notifications.

[1064] (Application example 2)

[1065] 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."

[1066] After the release of a new device or service, there is a need to collect, analyze, and visualize customer feedback in real time so that quick and specific responses can be taken. However, traditional feedback collection methods have problems with incomplete spam and noise removal and low sentiment analysis accuracy, making it difficult to accurately grasp market trends. In addition, the inability to generate notifications or alerts in real time makes it difficult to take quick action.

[1067] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, means for periodically updating and displaying aggregated data in real time, means for notifying customer feedback in real time, means for generating and distributing alerts based on specific sentiment results, and means for viewing the visualized data on a dashboard. This allows relevant parties to grasp the market's voice in real time and respond promptly and appropriately.

[1068] "Post" means a message or comment written by a User on an Online Platform.

[1069] "Online platform" refers to an internet service that provides social networking services such as Twitter, Facebook, and Instagram.

[1070] A "database" is a storage medium for structuring and storing collected data.

[1071] "Spam and noise" refers to unnecessary advertising and irrelevant, meaningless data.

[1072] "Natural language processing technology" is a technology that analyzes human language and converts it into a format that a computer can understand and process.

[1073] "Sentiment analysis" is the use of natural language processing technology to classify users' emotions into positive, negative, or neutral based on the content of their posts.

[1074] "Topic" refers to a recurring theme or subject matter within a post.

[1075] A "visualization format" is a method of presenting analytical results in a visually easy-to-understand format, such as a graph or chart.

[1076] A "report" is a document that summarizes visualized data and analysis results.

[1077] "Real-time notification" means instantly informing relevant parties of analysis results and feedback.

[1078] An "alert" refers to issuing a warning to relevant parties when a specific condition or emotional outcome is detected.

[1079] A "dashboard" is an interface for visually and centrally managing analysis results and feedback.

[1080] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to relevant parties. In particular, it provides a mechanism that allows quick confirmation of customer feedback and immediate response as needed.

[1081] The system includes the following components:

[1082] 1. Data Collection

[1083] The server automatically collects relevant posts from multiple online platforms (e.g., social networking services) and retrieves posts based on specified keywords using the API of each platform.

[1084] 2. Data storage

[1085] The server stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used.

[1086] 3. Data Cleansing

[1087] The server filters out spam and noise from the submission data stored in the database, and filters out inappropriate data based on specific keyword lists and blacklists.

[1088] 4. Sentiment Analysis and Topic Extraction

[1089] The server analyzes the cleansed post data using natural language processing technology and an emotion engine, which classifies the sentiment of posts into positive, negative, and neutral, and extracts major topics and frequently occurring keywords.

[1090] 5. Data Visualization

[1091] The server then converts the analysis results into visualizations such as graphs and charts, including pie charts showing sentiment percentages and word clouds showing major topics.

[1092] 6. Report Generation and Delivery

[1093] The server automatically generates reports based on the visualized data and distributes them to relevant parties via email or chat tools.

[1094] 7. Real-time notifications and dashboard display

[1095] The server periodically updates the data, providing a dashboard with real-time display, and also provides real-time customer feedback and generates alerts based on specific sentiment results.

[1096] Program processing explanation

[1097] The hardware used includes servers and devices such as smartphones and tablets, while the software used includes APIs from each online platform, the Python requests library, the NLTK library for natural language processing, a sentiment analysis engine, and the matplotlib library for visualization.

[1098] Data collection:

[1099] Post data is obtained from each platform via API and stored in a database.

[1100] Data cleansing:

[1101] Filter out spam and noise to create a clean dataset.

[1102] Sentiment analysis and topic extraction:

[1103] We use the NLTK library and a sentiment analysis engine to classify and extract the sentiment and main topics of each post.

[1104] Data Visualization:

[1105] The matplotlib library is used to convert the analysis results into visually understandable formats such as pie charts and word clouds.

[1106] Report generation and delivery:

[1107] Reports are automatically created based on the generated visualization data and distributed to relevant parties via email or chat tools.

[1108] Real-time notifications and dashboard views:

[1109] It regularly updates the data, providing a dashboard with up-to-date feedback, and provides real-time alerts when specific sentiment results are detected.

[1110] Specific examples

[1111] For example, if a store launches a new service and a customer posts on social media, "This new service is so convenient!", this positive feedback will be immediately notified to the store manager. Similarly, if there is a negative post such as "The wait time for service is long," the store manager will be notified in the same way, so that they can take immediate action.

[1112] Prompt sentence for generative AI model

[1113] We will design a smartphone application that collects real-time social media feedback after the release of a new service or device, and analyzes and visualizes positive and negative sentiment. This application uses Python's requests library to collect data from social media APIs, combines natural language processing and an emotion engine to analyze the feedback, and visualizes it using matplotlib. As a concrete example, if a customer posts on social media that "the wait time for service is long," this negative feedback will be immediately notified to the store manager.

[1114] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1115] Step 1: Data collection

[1116] The server collects posts based on the specified keywords using APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram).

[1117] Input: the specified keyword

[1118] Data processing: Acquiring posts through API, analyzing JSON format data

[1119] Output: Retrieved post data (metadata such as post content, user ID, post date and time)

[1120] Step 2: Save data

[1121] The server stores the collected posting data in a database.

[1122] Input: Collected submission data

[1123] Data processing: Inserting data into the database

[1124] Output: Post data saved in the database

[1125] Step 3: Remove spam noise

[1126] The server filters out spam and noise from posts stored in a database.

[1127] Input: Post data read from the database

[1128] Data processing: filtering based on specific keyword lists or blacklists

[1129] Output: Cleansed post data

[1130] Step 4: Sentiment analysis and topic extraction

[1131] The server uses natural language processing technology and an emotion engine to analyze the sentiment and topic of posts.

[1132] Input: Cleansed post data

[1133] Data processing: Sentiment determination and topic extraction using natural language processing techniques

[1134] Output: Analysis data with sentiment and topic annotations

[1135] Step 5: Data visualization

[1136] The server converts the analysis results into visualization formats such as graphs and charts.

[1137] Input: Analysis data with sentiment and topic annotations

[1138] Data processing: Graph generation using visualization libraries (e.g., matplotlib)

[1139] Output: Visualized graphs and charts

[1140] Step 6: Report generation and distribution

[1141] The server automatically generates reports based on the visualized data and distributes them to relevant parties.

[1142] Input: Data for visualizations of graphs and charts

[1143] Data processing: Report generation and distribution via email or chat tools

[1144] Output: Report sent to stakeholders

[1145] Step 7: Real-time notifications and dashboard display

[1146] The server provides a dashboard that periodically updates and displays the data in real time, and also generates alerts based on specific sentiment results.

[1147] Input: Real-time collected analytics data

[1148] Data processing: Display on dashboard and generate alerts

[1149] Output: Latest data displayed in the dashboard and delivered alerts

[1150] 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.

[1151] 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.

[1152] 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.

[1153] [Fourth embodiment]

[1154] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1155] 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.

[1156] 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).

[1157] 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.

[1158] 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.

[1159] 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).

[1160] 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. 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.

[1161] 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.

[1162] 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.

[1163] 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.

[1164] 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.

[1165] 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.

[1166] 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."

[1167] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to stakeholders. This system is implemented through the following steps.

[1168] First, the server uses the APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords, and then automatically collects comments and ratings posted by users about new devices and services.

[1169] The server then stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used, allowing for efficient subsequent analysis and filtering processes.

[1170] Next, the server removes spam and noise from the posted data stored in the database. In this step, spam is identified based on specific keyword lists and blacklists, and inappropriate data is filtered out. This process improves the accuracy of analysis and produces reliable data.

[1171] The server then uses natural language processing technology to analyze the sentiment and topics of the posts. This analysis classifies each post as positive, negative, or neutral, and extracts key topics and frequently occurring keywords. This provides a concrete understanding of users' opinions and sentiments.

[1172] The server then converts the analysis results into visualizations such as graphs and charts, such as pie charts showing sentiment percentages or word clouds displaying frequently occurring keywords, providing data in an intuitive and easy-to-understand format.

[1173] The server then automatically generates a report with visualized data, including the percentage of positive vs. negative sentiment, major topics and trends, and specific feedback from users.

[1174] The generated reports are distributed to relevant parties by the server automatically via email or chat tools (such as Slack or Microsoft Teams), allowing relevant parties to quickly grasp the voice of the market and take any necessary action immediately.

[1175] Finally, the server periodically updates the aggregated data and provides a means for displaying it in real time. This dashboard allows stakeholders to check the latest market evaluations and customer satisfaction at any time. In this way, the present invention enables quick and accurate market responses, contributing to improving a company's competitiveness and customer satisfaction.

[1176] The above is an embodiment of the present invention. This embodiment allows each step to work together, enabling efficient and effective collection and analysis of market feedback. For example, if a user posts on social media immediately after the release of a new device, saying, "The battery life of the new device is poor," this system instantly collects the post and determines through sentiment analysis that it is a negative evaluation. It then classifies the post as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. This allows developers to quickly identify the problem and take measures to improve it.

[1177] In this way, the system of the present invention becomes a powerful tool for companies to take advantage of real-time feedback from the market and respond quickly.

[1178] The processing flow will be explained below.

[1179] Step 1:

[1180] The server periodically searches and collects posts containing specified keywords using the APIs of multiple online platforms (Twitter, Facebook, Instagram, etc.), sends API requests, and retrieves the relevant post data.

[1181] Step 2:

[1182] The server stores the collected post data in a database, specifically metadata such as the post content, user ID, posting date and time, and used hashtags and mentions, based on an appropriate schema.

[1183] Step 3:

[1184] The server filters out spam and noise from the submissions stored in the database, using specific keyword lists and blacklists to filter out spam submissions and inappropriate data, eliminating unnecessary data.

[1185] Step 4:

[1186] The server then analyzes the cleansed post data using natural language processing (NLP) technology. This involves performing sentiment analysis on each post to determine whether it is classified as positive, negative, or neutral, and extracting key topics and frequently occurring keywords.

[1187] Step 5:

[1188] The server visualizes the analysis results, converting the sentiment interpretations and keyword frequencies obtained through text mining into graphs, charts, word clouds, and other diagrams to visually display the data.

[1189] Step 6:

[1190] The server automatically generates reports based on the visualized data, including analysis results such as sentiment ratings, key topics, and user feedback, and presents this information in an intuitive format for stakeholders.

[1191] Step 7:

[1192] The server distributes the generated reports to the relevant parties. The reports are automatically sent via email or chat tools (Slack, Microsoft Teams, etc.). It also manages distribution logs and monitors whether the distribution was successful.

[1193] Step 8:

[1194] The server runs a process that periodically updates the aggregated data and displays it on the dashboard in real time, allowing stakeholders to always check the latest market evaluations and customer satisfaction. Data is updated at specified time intervals, and the dashboard display is updated accordingly.

[1195] Example 1

[1196] 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."

[1197] If market feedback is not collected quickly and effectively after the release of a new device or service, companies will be unable to respond appropriately to customer opinions and sentiments, resulting in a decline in competitiveness and customer satisfaction. Furthermore, if collected data is left unorganized, unreliable analysis results may result. In such situations, it becomes difficult to respond to the market in real time, requiring companies to make quick decisions and take action.

[1198] 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.

[1199] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, and means for periodically updating the aggregated data and displaying it in real time. This makes it possible to quickly and accurately grasp market feedback about new devices and new services and take appropriate measures.

[1200] "Specified keywords" refer to words or phrases that a user has specified to gather specific information.

[1201] "Post" means a message, comment or review posted publicly by a User on an Online Platform.

[1202] "Online Platform" refers to web-based services that enable users to publish and share information, such as social networking services, blogs, and forums.

[1203] An "application program interface (API)" refers to a set of rules or protocols that allow different software applications to communicate with each other.

[1204] A "database" refers to a system that stores data in a structured manner that allows it to be efficiently managed, queried, and manipulated.

[1205] "Spam" refers to unsolicited messages or irrelevant postings sent in large quantities over the Internet.

[1206] "Noise" refers to unnecessary information or inaccurate data contained in the data being analyzed.

[1207] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[1208] "Sentiment analysis" refers to the technology of classifying emotional states (positive, negative, neutral, etc.) from text data.

[1209] "Topic extraction" refers to the technique of identifying key concepts or themes from text data.

[1210] "Visualization format" refers to the way data is visually represented in the form of graphs and charts.

[1211] "Report" refers to a document summarizing the analysis results and providing them to relevant parties.

[1212] "Aggregated Data" refers to data that compiles multiple data points into statistical information.

[1213] "Real-time display" means that data is displayed immediately as soon as it is updated.

[1214] The system of the present invention aims to collect and analyze real-time feedback from the market after the release of a new terminal or new service, visualize the results, and provide them to the relevant parties. This system is implemented as follows.

[1215] Hardware and software used

[1216] First, the main hardware and software used in this system are listed below.

[1217] Hardware

[1218] Server: Primarily responsible for collecting, storing, analyzing, visualizing, and distributing data. For example, an EC2 instance from Amazon Web Services (AWS) is used.

[1219] Database server: Stores and manages collected data. For example, AWS RDS or MySQL is used.

[1220] software

[1221] Social media platform APIs: Used to collect data. Examples include Twitter API and Facebook Graph API.

[1222] Database management systems: Examples include MySQL and PostgreSQL.

[1223] Natural language processing libraries: Mainly use NLTK and spaCy.

[1224] Data visualization tools: Matplotlib and D3.js are used.

[1225] Communication tools: Slack API and Microsoft Teams API are used for report distribution.

[1226] Specific operation of the system

[1227] The server first automatically collects posts related to the specified keywords from multiple online platforms. To do this, it uses the APIs of the social media platforms. For example, it uses the Twitter API to search for and retrieve posts using the keyword "new device." The collected post data is then saved in a database. The data is received in JSON format, parsed, and stored in the database as structured data.

[1228] After the collected submission data is saved, it is extracted from the database and filtered for spam and noise. Specific keyword lists and blacklists are used to identify spam, and the data is converted into a data frame using the Python pandas library to remove inappropriate data.

[1229] The server then uses natural language processing techniques to analyze the sentiment and topics of the collected posts. Specifically, it uses the NLTK library to perform sentiment analysis of the text and classify it as positive, negative, or neutral. It also uses TF-IDF (Term Frequency-Inverse Document Frequency) scores to extract major topics and frequently occurring keywords.

[1230] The analysis results are converted into an intuitively understandable visualization format. The server uses Matplotlib to generate pie charts showing the percentage of each sentiment, and the wordcloud library to generate word clouds of frequently occurring keywords. This allows users to visually grasp the overall trends and main opinions of the collected data.

[1231] Additionally, the server automatically generates reports containing visualized data in HTML format using the Jinja2 template engine, which are then distributed to interested parties via email using the SMTP protocol, allowing for quick sharing of market opinions and assessments.

[1232] Finally, the server periodically refreshes the data and provides a dashboard that displays it in real time. Using the Flask web framework, we expose a real-time dashboard, allowing users to see the latest status of the aggregated data at any time.

[1233] Examples of concrete examples and prompts

[1234] For example, if a user posts on social media immediately after a new device is released that "the battery life of the new device is poor," the system instantly collects the post and determines that it is a negative evaluation through sentiment analysis. It then classifies it as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. This allows developers to quickly identify the problem and take measures to improve it.

[1235] Prompt Sentence Examples

[1236] "Please explain the steps in your system to collect posts from social media and perform sentiment analysis and topic extraction. Please be specific about how your system collects data, analyzes it using natural language processing techniques, and visualizes the results."

[1237] By utilizing this system, companies will have a powerful tool to quickly analyze real-time feedback from the market and take appropriate countermeasures.

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

[1239] Step 1:

[1240] The server automatically collects posts related to a specified keyword from multiple online platforms. The input is a specific keyword (e.g., "new device") and the API credentials of the online platform. It uses the Python tweepy library to send a search query to the Twitter API and retrieves related post data. The output is the retrieved post data in JSON format.

[1241] Specific working example:

[1242] The server sends a request to the Twitter API with a pre-defined keyword.

[1243] The JSON data returned from the API contains information such as the content of each post, the user ID, and the posting date and time.

[1244] Step 2:

[1245] The server saves the collected post data in a database. The input is the JSON format post data obtained in step 1. It connects to the database using Python's MySQL-connector library, parses the JSON data, and inserts each field into the corresponding table. The output is structured data saved in the database.

[1246] Specific working example:

[1247] The server establishes a database connection and parses each field of the JSON data to generate an SQL INSERT statement.

[1248] The generated SQL statement is executed and the collected post data is stored in a database.

[1249] Step 3:

[1250] The server reads collected submission data from the database and removes spam and noise. The input is the raw data read from the database. The data is converted into a data frame using the Python pandas library and filtered based on a specific keyword list or blacklist. The output is clean data with spam and noise removed.

[1251] Specific working example:

[1252] The server fetches the data from the database and converts it into a pandas dataframe.

[1253] Apply criteria to filter out inappropriate data using keyword lists and blacklists.

[1254] Step 4:

[1255] The server uses natural language processing technology to analyze the sentiment and topics of the collected post data. The input is the clean data obtained in step 3. It performs sentiment analysis of the text using Python's NLTK library and classifies it as positive, negative, or neutral. It also uses the TF-IDF method to extract major topics and frequently occurring keywords. The output is the sentiment classification results and topic analysis results.

[1256] Specific working example:

[1257] The server applies the nltk.sentiment.vader.SentimentIntensityAnalyzer to calculate a sentiment score for each post.

[1258] Calculate the TF-IDF score and list the important topics.

[1259] Step 5:

[1260] The server converts the analysis results into visualization formats such as graphs and charts that are easy to understand intuitively. The input is the sentiment classification and topic analysis results obtained in Step 4. The Python Matplotlib library is used to generate a pie chart showing the proportion of each sentiment, and the wordcloud library is used to create a word cloud of frequently occurring keywords. The output is the visualized data.

[1261] Specific working example:

[1262] The server generates a pie chart based on the sentiment results and displays frequently occurring keywords in a word cloud format.

[1263] Step 6:

[1264] The server automatically generates a report containing the visualized data. The input is the visualization data created in step 5. It creates the report in HTML format using the Jinja2 template engine and delivers it via email using the SMTP protocol. The output is the generated report and the delivery status.

[1265] Specific working example:

[1266] The server generates an HTML report using Jinja2 templates, embedding the visualization data.

[1267] Generated reports are sent via email using the smtplib library.

[1268] Step 7:

[1269] The server periodically updates the data and provides a dashboard that displays it in real time. The input is the latest aggregated data. The real-time dashboard is built using the Flask web framework and the APScheduler library to update the data periodically. The output is the dashboard updated in real time.

[1270] Specific working example:

[1271] The server uses Flask to build a web dashboard that displays the latest data.

[1272] Use APScheduler to run data refresh jobs periodically to ensure your dashboard always reflects the latest information.

[1273] (Application example 1)

[1274] 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."

[1275] There is a need to quickly and efficiently collect real-time feedback from the market for newly released autonomous vehicles, analyze it, and provide visualized data to stakeholders in order to quickly improve vehicle performance and add new functions.Since such a feedback system requires real-time performance, it has been difficult to achieve this using conventional methods.

[1276] 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.

[1277] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, means for accessing a specific online platform that collects feedback via an API, means for displaying the analysis results in real time on a smartphone and an in-vehicle display, and means for periodically updating aggregated data and displaying it in real time, thereby enabling the system to quickly understand user feedback and improve performance or add new functions.

[1278] "Means for automatically collecting posts related to specified keywords from multiple online platforms" refers to a function that automatically collects posts related to specific keywords from multiple online platforms, such as Twitter, Facebook, and Instagram, via API.

[1279] "Means for storing collected posts in a database" refers to a function for safely and efficiently storing the content and metadata of collected posts in a database.

[1280] "Means to remove spam and noise from saved posts" refers to a function that filters inappropriate content and irrelevant information from collected posting data.

[1281] "Means for analyzing the sentiment and topics of posts using natural language processing technology" refers to technology that analyzes the collected content of posts and extracts sentiment classifications such as positive, negative, and neutral, as well as major topics.

[1282] "Means for converting analysis results into visualization formats such as graphs and charts" refers to a function that converts the data obtained from the analysis into formats such as pie charts, bar graphs, and word clouds in order to display them graphically.

[1283] The "means for automatically generating a report including visualized data" is a function for automatically creating a report based on visualized data and providing it to a user.

[1284] The "means for distributing the generated report to the relevant parties" is a function for quickly distributing the generated report to the relevant parties via email or chat tools.

[1285] "Means of accessing specific online platforms that collect feedback via API" refers to a function that obtains posting data using the API of designated online platforms such as Twitter, Facebook, and Instagram.

[1286] "Means for displaying analysis results in real time on a smartphone and in-vehicle display" refers to a function that displays the results of analysis of posts in real time on a smartphone or the in-vehicle display of an autonomous vehicle.

[1287] The "means for periodically updating the aggregated data and displaying it in real time" is a function for periodically updating the collected data and displaying the latest information in real time.

[1288] This invention is a system that efficiently collects, analyzes, and provides real-time feedback from the autonomous vehicle market to stakeholders. This system is configured as follows.

[1289] The server automatically collects posts related to the specified keywords from multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) via API. The collected data is stored in a database, including the post content, user ID, and posting date and time.

[1290] The server then filters out spam and noise from the stored submissions using filtering based on specific keyword lists and blacklists.

[1291] The server then uses natural language processing techniques (specifically, NLP libraries such as SpaCy and NLTK) to analyze the sentiment and topics of the posts, classifying each post as positive, negative, or neutral, and extracting major topics and frequently occurring keywords.

[1292] The analysis results are converted into visualization formats such as graphs and charts by the server. Graph drawing libraries such as D3.js are used for this visualization. Reports are automatically generated based on the visualized data and distributed to relevant parties via email or chat tools. This allows stakeholders to quickly grasp market feedback and respond immediately.

[1293] Furthermore, the system has the ability to access specific online platforms that collect feedback via API and display the analysis results in real time on a smartphone and in-car display, allowing drivers to check important feedback at the appropriate time while driving.

[1294] A dashboard is also provided that regularly updates aggregated data and displays it in real time, allowing stakeholders to always check the latest market valuations and user sentiment.

[1295] For example, if a user posts on social media that a new self-driving vehicle is too slow immediately after its release, the system will instantly collect the post, analyze it as a negative evaluation, classify it as a problem with the self-braking function, visualize it, and deliver it to the development team as a report.

[1296] An example prompt is:

[1297] "Collect social media posts about new autonomous vehicles and analyze them for sentiment and key topics. Visualize the results and generate a word cloud showing the percentage of positive and negative feedback, as well as key issues."

[1298] In this way, the system of the present invention can quickly and efficiently collect and analyze market feedback on autonomous vehicles and provide it in real time, thereby contributing to improved user satisfaction and product quality.

[1299] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1300] Step 1:

[1301] Data collection

[1302] Subject: Server

[1303] Input: the specified keyword

[1304] How it works: The server collects posts related to specified keywords via APIs of online platforms such as Twitter, Facebook, and Instagram.

[1305] Output: Collected submission data

[1306] Step 2:

[1307] Data storage

[1308] Subject: Server

[1309] Input: Collected submission data

[1310] How it works: The server stores the collected post data in a database, which includes metadata such as the post content, user ID, post date and time, and hashtags and mentions used.

[1311] Output: Post data saved in the database

[1312] Step 3:

[1313] Spam and noise removal

[1314] Subject: Server

[1315] Input: Post data stored in the database

[1316] How it works: The server filters submissions based on specific keyword lists and blacklists to remove spam and noise.

[1317] Output: Filtered post data

[1318] Step 4:

[1319] Sentiment and topic analysis

[1320] Subject: Server

[1321] Input: Filtered post data

[1322] How it works: The server uses natural language processing techniques to analyze posts for sentiment (positive, negative, neutral), main topics, and frequently occurring keywords. Specifically, it uses NLP libraries (e.g., SpaCy, NLTK).

[1323] Output: Parsed sentiment and topic data

[1324] Step 5:

[1325] Data visualization

[1326] Subject: Server

[1327] Input: Parsed sentiment and topic data

[1328] How it works: The server converts the analysis results into visualizations such as graphs and charts (e.g., pie charts, word clouds), using a graph drawing library such as D3.js.

[1329] Output: Visualized data

[1330] Step 6:

[1331] Report Generation

[1332] Subject: Server

[1333] Input: Visualized data

[1334] How it works: The server automatically generates reports based on the visualized data, including the ratio of positive vs. negative sentiment, major topics and trends, and specific feedback from users.

[1335] Output: Generated report

[1336] Step 7:

[1337] Report Distribution

[1338] Subject: Server

[1339] Input: Generated report

[1340] How it works: The server delivers automatically generated reports to relevant parties via email or chat tools (e.g., Slack, Microsoft Teams).

[1341] Output: Delivered report

[1342] Step 8:

[1343] Real-time display

[1344] Subject: Server

[1345] Input: Aggregate data

[1346] How it works: The server periodically updates the aggregated data and provides real-time display, allowing users to check the latest market valuation and sentiment data on their smartphone or in-car display.

[1347] Output: Data displayed in real time

[1348] Step 9:

[1349] Feedback collection

[1350] Subject: Server

[1351] Input: API of a specific online platform

[1352] Operation: The server accesses a specific online platform via API and collects feedback.

[1353] Output: Collected feedback data

[1354] 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.

[1355] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to stakeholders. Furthermore, by combining it with an emotion engine that recognizes user emotions, more detailed and accurate feedback analysis is possible. This system is implemented through the following steps:

[1356] First, the server uses the APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords. In this step, comments and ratings about new devices and services posted by users on SNS are automatically acquired and stored in a database.

[1357] The server then stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used, allowing for efficient subsequent analysis and filtering processes.

[1358] The server then filters out spam and noise from the submissions stored in the database. This filtering step removes spam submissions and inappropriate data based on specific keyword lists and blacklists, resulting in reliable, cleansed data.

[1359] The server then analyzes the cleansed post data using natural language processing technology and an emotion engine. The emotion engine recognizes the user's emotions expressed in each post and determines whether the post is positive, negative, or neutral. It also extracts major topics and frequently occurring keywords. This emotion analysis provides a clear understanding of the user's specific emotional state.

[1360] The server converts the analysis results into visualizations such as graphs and charts. For example, it generates a pie chart showing the percentage of emotions or a word cloud showing frequently occurring keywords. Furthermore, the analysis results of the emotion engine are also visualized, allowing users to intuitively understand the detailed data.

[1361] The server then automatically generates a report based on the visualized data, including the ratio of positive vs. negative sentiment, key topics, user feedback, and sentiment analysis results from the sentiment engine, all in a visually easy-to-understand format, allowing stakeholders to easily understand the market situation.

[1362] The generated reports are distributed to relevant parties by the server automatically via email or chat tools (such as Slack or Microsoft Teams), allowing relevant parties to quickly grasp the voice of the market and take any necessary action immediately.

[1363] Finally, the server periodically updates the aggregated data and provides a means to display it in real time. This dashboard allows stakeholders to check the latest market valuation and customer satisfaction at any time. Furthermore, the emotion engine generates alerts to notify stakeholders of specific emotional states (e.g., extreme dissatisfaction).

[1364] For example, if a user posts on social media immediately after the release of a new device that "the battery life of the new device is poor," the system immediately collects the post and uses sentiment analysis to determine that it is a negative evaluation. Next, it uses natural language processing to classify it as a complaint about the battery, visualizes it, and distributes it as a report to relevant parties. The sentiment engine detects strong user dissatisfaction and generates an alert to immediately notify relevant parties. This series of processes allows developers to quickly identify the problem and take measures to improve it.

[1365] This concludes the description of the embodiment of the present invention. This embodiment allows each step to work together, efficiently and effectively collecting and analyzing market feedback, and enabling rapid market response. The combination of emotion engines allows for a detailed understanding of the user's emotional state, enabling appropriate responses to be taken promptly.

[1366] The processing flow will be explained below.

[1367] Step 1:

[1368] The server uses APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords, thereby automatically obtaining comments and ratings about new devices and new services posted by users on SNS.

[1369] Step 2:

[1370] The server stores the collected post data in a database, where metadata such as the post content, user ID, posting date and time, and used hashtags and mentions are stored based on a schema.

[1371] Step 3:

[1372] The server filters spam and noise from the submissions stored in the database, using specific keyword lists and blacklists to filter out spam submissions and inappropriate data, resulting in reliable, cleansed data.

[1373] Step 4:

[1374] The server analyzes the cleansed post data using natural language processing technology and an emotion engine. The emotion engine recognizes the user's emotions expressed in each post and determines whether the post is positive, negative, or neutral. It also extracts major topics and frequently occurring keywords.

[1375] Step 5:

[1376] The server visualizes the analysis results, generating graphs, charts, and word clouds based on the sentiment analysis results and keyword frequencies obtained through text mining, and creating diagrams to visually display the data.

[1377] Step 6:

[1378] The server automatically generates reports based on the visualized data, including sentiment ratios, major topics, user feedback, and detailed sentiment analysis results from the sentiment engine.

[1379] Step 7:

[1380] The server distributes the generated reports to the relevant parties, automatically sending the reports via email or chat tools (e.g., Slack, Microsoft Teams, etc.), and managing the distribution logs.

[1381] Step 8:

[1382] The server runs a calculation process that periodically updates the aggregated data and displays it on the dashboard in real time, allowing stakeholders to always see the latest market evaluations and customer satisfaction figures.

[1383] Step 9:

[1384] The server generates alerts for specific emotional states (e.g., extreme dissatisfaction) recognized by the emotion engine, allowing relevant parties to be notified immediately and respond quickly.

[1385] Example 2

[1386] 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."

[1387] With conventional systems, it was difficult to efficiently collect, analyze, visualize, and quickly provide real-time feedback from the market after the release of new devices or services. Furthermore, the analytical technology required to grasp user sentiment in detail was insufficient, making it difficult to quickly take appropriate action.

[1388] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1389] In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering out spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology and an emotion engine, means for converting the analysis results into a visualized format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to interested parties via email or a chat tool, means for periodically updating the aggregated data and displaying it in real time, and means for detecting specific emotional states using the emotion engine and generating alerts. This makes it possible to quickly and precisely collect, analyze, visualize, and provide relevant parties with feedback from the market after the release of a new device or service.

[1390] "Specified Keywords" are specific words or phrases used to collect targeted posts.

[1391] An "online platform" is a system that provides services over the Internet and allows users to post and share content. Examples include social networking platforms.

[1392] A "post" is any content such as a comment, rating, photo, or video posted by a user on an online platform.

[1393] "Collection methods" refers to technologies or methods for automatically obtaining posts related to designated keywords from online platforms.

[1394] A "database" is a storage device for systematically storing and managing collected submission data.

[1395] "Spam" and "noise" refer to information that is inappropriate or irrelevant for analysis. Spam is irrelevant posts sent in large quantities, while noise is unnecessary data that reduces the accuracy of analysis.

[1396] "Natural language processing technology" refers to the technology that uses computers to analyze, understand, and generate human language.

[1397] An "emotion engine" is software or algorithms used to identify and classify user emotions contained in posts.

[1398] A "visualization format" is a method of converting analytical results into graphics such as graphs and charts so that they can be understood at a glance.

[1399] A "report" is a document or file that summarizes the results of analysis and visualization and provides them to stakeholders.

[1400] "Email and chat tools" refers to applications for sending generated reports to relevant parties via communication means.

[1401] "Means of displaying in real time" refers to a system that regularly updates the latest data so that relevant parties can check it immediately.

[1402] An "alert" is a notification function that alerts relevant parties when a specific condition is met.

[1403] This invention is a system that collects real-time feedback from the market when a new device or service is released, analyzes it, and provides visualized data to stakeholders. Furthermore, by combining it with an emotion engine, detailed and accurate feedback analysis is achieved. This system is mainly composed of a server, a device, and a user.

[1404] server

[1405] The server first uses APIs from multiple online platforms (Twitter, Facebook, Instagram, etc.) to collect posts related to the specified keywords. It authenticates with each platform using an API key and obtains data in JSON format. The collected post data is then stored in a NoSQL database such as MongoDB. The stored data includes metadata such as the post content, user ID, posting date and time, and used hashtags and mentions.

[1406] The server then filters the collected submission data to remove spam and noise. This involves filtering the data using specific keyword lists and blacklists. By removing spam submissions and eliminating noise data, the server obtains reliable, cleansed data.

[1407] The server then analyzes the cleansed post data using natural language processing techniques (NLP libraries, e.g., SpaCy, NLTK) and a sentiment engine (e.g., Hugging Face sentiment analysis model). The sentiment engine identifies user sentiment expressed in each post and classifies it as positive, negative, or neutral. It also extracts major topics and frequently occurring keywords.

[1408] The analysis results are converted by the server into visualization formats such as graphs and charts (using Matplotlib, D3.js, Plotly, and Chart.js), with pie charts showing sentiment percentages and word clouds showing frequent keywords.

[1409] Finally, the server automatically generates reports based on the visualized data and distributes them to relevant parties via email or chat tools (Slack, Microsoft Teams, etc.). Furthermore, it provides a dashboard that periodically aggregates data and displays it in real time. It also has a function that generates alerts to relevant parties when a specific emotional state (such as extreme dissatisfaction) is detected by the emotion engine.

[1410] Terminal

[1411] The terminals display reports and real-time evaluation data delivered from the server, allowing participants to quickly grasp market conditions and take any necessary action immediately.

[1412] User

[1413] Users provide feedback on new devices and services on the online platform, which allows the system to collect and analyze specific market evaluations and sentiments.

[1414] Specific examples

[1415] For example, if a user posts on social media that "my new device's battery life is poor," the server collects the post via the Twitter API and stores it in MongoDB. It then uses a blacklist to filter out spam posts, and the content is saved as cleansed data. The server then uses natural language processing technology and an emotion engine to analyze the negative emotions, including dissatisfaction with the "battery." The results are then distributed to relevant parties in a visualized format (pie chart or word cloud). Additionally, if a specific emotional state is detected, an immediate alert is sent via Slack or other means.

[1416] Prompt Sentence Examples

[1417] "Describe a system that instantly analyzes market reactions after the release of a new device, categorizes user feedback with an emotion engine, and generates real-time visualizations."

[1418] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1419] Step 1: Data collection

[1420] The server uses APIs of online platforms such as Twitter, Facebook, and Instagram to collect posts containing specified keywords related to new devices and new services. It requires an API key and keywords as input, and sends a request to each platform to retrieve the posted data in JSON format. The output is the collected posted data.

[1421] As a specific example of how this works, the server uses the Twitter API to collect tweets containing the keyword "new device."

[1422] Step 2: Save data

[1423] The server stores the collected post data in a NoSQL database such as MongoDB. The input is the collected post data in JSON format, and the output is the data stored in the database.

[1424] As a specific example of how this works, the server stores the acquired post data as a document in MongoDB, including metadata such as the post content, user ID, posting date and time, and hashtags.

[1425] Step 3: Data cleansing

[1426] The server filters out spam and noise from the stored data. The input is the submitted data stored in the database, and the output is the cleansed data.

[1427] In particular, the server may use specific keyword lists or blacklists to filter out irrelevant or spam posts and remove them.

[1428] Step 4: Data analysis

[1429] The server analyzes the cleansed data using natural language processing technology and an emotion engine. The input is the cleansed posted data, and the output is the analysis results.

[1430] For example, the server analyzes posts using an NLP library (e.g., SpaCy) to extract topics, and then uses an emotion engine (e.g., the Hugging Face model) to classify emotions into positive, negative, and neutral.

[1431] Step 5: Data visualization

[1432] The server converts the analysis results into a visualization format: the input is the analysis results and the output is the visualized graphs and charts.

[1433] As a specific example of how it works, the server uses Matplotlib and D3.js to create pie charts showing the percentage of sentiment analysis and word clouds showing frequently occurring keywords.

[1434] Step 6: Report generation and delivery

[1435] The server generates reports based on the visualized data and distributes them to relevant parties via email or chat tools. The input is the visualized data, and the output is the generated report and the distribution completion status.

[1436] For example, the server generates a report in PDF format and emails it to interested parties via an SMTP server, and also sends a message containing the visualization data using the Slack API.

[1437] Step 7: Real-time updates and alerts

[1438] The server periodically aggregates data and provides a dashboard that displays it in real time. Furthermore, an emotion engine detects specific emotional states and generates alerts. The input is newly collected post data and analysis results, and the output is an updated dashboard and alert notifications.

[1439] For example, the server uses Node.js and Socket.IO to update the dashboard in real time, and when it detects certain emotional states, such as extreme dissatisfaction, it sends alerts to relevant parties via SMS or push notifications.

[1440] (Application example 2)

[1441] 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."

[1442] After the release of a new device or service, there is a need to collect, analyze, and visualize customer feedback in real time so that quick and specific responses can be taken. However, traditional feedback collection methods have problems with incomplete spam and noise removal and low sentiment analysis accuracy, making it difficult to accurately grasp market trends. In addition, the inability to generate notifications or alerts in real time makes it difficult to take quick action.

[1443] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically collecting posts related to specified keywords from multiple online platforms, means for storing the collected posts in a database, means for filtering spam and noise from the stored posts, means for analyzing the sentiment and topics of the posts using natural language processing technology, means for converting the analysis results into a visualization format such as a graph or chart, means for automatically generating a report including the visualized data, means for distributing the generated report to relevant parties, means for periodically updating and displaying aggregated data in real time, means for notifying customer feedback in real time, means for generating and distributing alerts based on specific sentiment results, and means for viewing the visualized data on a dashboard. This allows relevant parties to grasp the market's voice in real time and respond promptly and appropriately.

[1444] "Post" means a message or comment written by a User on an Online Platform.

[1445] "Online platform" refers to an internet service that provides social networking services such as Twitter, Facebook, and Instagram.

[1446] A "database" is a storage medium for structuring and storing collected data.

[1447] "Spam and noise" refers to unnecessary advertising and irrelevant, meaningless data.

[1448] "Natural language processing technology" is a technology that analyzes human language and converts it into a format that a computer can understand and process.

[1449] "Sentiment analysis" is the use of natural language processing technology to classify users' emotions into positive, negative, or neutral based on the content of their posts.

[1450] "Topic" refers to a recurring theme or subject matter within a post.

[1451] A "visualization format" is a method of presenting analytical results in a visually easy-to-understand format, such as a graph or chart.

[1452] A "report" is a document that summarizes visualized data and analysis results.

[1453] "Real-time notification" means instantly informing relevant parties of analysis results and feedback.

[1454] An "alert" refers to issuing a warning to relevant parties when a specific condition or emotional outcome is detected.

[1455] A "dashboard" is an interface for visually and centrally managing analysis results and feedback.

[1456] This invention is a system that collects and analyzes real-time feedback from the market after the release of a new device or service, and provides visualized data to relevant parties. In particular, it provides a mechanism that allows quick confirmation of customer feedback and immediate response as needed.

[1457] The system includes the following components:

[1458] 1. Data Collection

[1459] The server automatically collects relevant posts from multiple online platforms (e.g., social networking services) and retrieves posts based on specified keywords using the API of each platform.

[1460] 2. Data storage

[1461] The server stores the collected post data in a database, including metadata such as the post content, user ID, posting date and time, and hashtags and mentions used.

[1462] 3. Data Cleansing

[1463] The server filters out spam and noise from the submission data stored in the database, and filters out inappropriate data based on specific keyword lists and blacklists.

[1464] 4. Sentiment Analysis and Topic Extraction

[1465] The server analyzes the cleansed post data using natural language processing technology and an emotion engine, which classifies the sentiment of posts into positive, negative, and neutral, and extracts major topics and frequently occurring keywords.

[1466] 5. Data Visualization

[1467] The server then converts the analysis results into visualizations such as graphs and charts, including pie charts showing sentiment percentages and word clouds showing major topics.

[1468] 6. Report Generation and Delivery

[1469] The server automatically generates reports based on the visualized data and distributes them to relevant parties via email or chat tools.

[1470] 7. Real-time notifications and dashboard display

[1471] The server periodically updates the data, providing a dashboard with real-time display, and also provides real-time customer feedback and generates alerts based on specific sentiment results.

[1472] Program processing explanation

[1473] The hardware used includes servers and devices such as smartphones and tablets, while the software used includes APIs from each online platform, the Python requests library, the NLTK library for natural language processing, a sentiment analysis engine, and the matplotlib library for visualization.

[1474] Data collection:

[1475] Post data is obtained from each platform via API and stored in a database.

[1476] Data cleansing:

[1477] Filter out spam and noise to create a clean dataset.

[1478] Sentiment analysis and topic extraction:

[1479] We use the NLTK library and a sentiment analysis engine to classify and extract the sentiment and main topics of each post.

[1480] Data Visualization:

[1481] The matplotlib library is used to convert the analysis results into visually understandable formats such as pie charts and word clouds.

[1482] Report generation and delivery:

[1483] Reports are automatically created based on the generated visualization data and distributed to relevant parties via email or chat tools.

[1484] Real-time notifications and dashboard views:

[1485] It regularly updates the data, providing a dashboard with up-to-date feedback, and provides real-time alerts when specific sentiment results are detected.

[1486] Specific examples

[1487] For example, if a store launches a new service and a customer posts on social media, "This new service is so convenient!", this positive feedback will be immediately notified to the store manager. Similarly, if there is a negative post such as "The wait time for service is long," the store manager will be notified in the same way, so that they can take immediate action.

[1488] Prompt sentence for generative AI model

[1489] We will design a smartphone application that collects real-time social media feedback after the release of a new service or device, and analyzes and visualizes positive and negative sentiment. This application uses Python's requests library to collect data from social media APIs, combines natural language processing and an emotion engine to analyze the feedback, and visualizes it using matplotlib. As a concrete example, if a customer posts on social media that "the wait time for service is long," this negative feedback will be immediately notified to the store manager.

[1490] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1491] Step 1: Data collection

[1492] The server collects posts based on the specified keywords using APIs of multiple online platforms (e.g., Twitter, Facebook, Instagram).

[1493] Input: the specified keyword

[1494] Data processing: Acquiring posts through API, analyzing JSON format data

[1495] Output: Retrieved post data (metadata such as post content, user ID, post date and time)

[1496] Step 2: Save data

[1497] The server stores the collected posting data in a database.

[1498] Input: Collected submission data

[1499] Data processing: Inserting data into the database

[1500] Output: Post data saved in the database

[1501] Step 3: Remove spam noise

[1502] The server filters out spam and noise from posts stored in a database.

[1503] Input: Post data read from the database

[1504] Data processing: filtering based on specific keyword lists or blacklists

[1505] Output: Cleansed post data

[1506] Step 4: Sentiment analysis and topic extraction

[1507] The server uses natural language processing technology and an emotion engine to analyze the sentiment and topic of posts.

[1508] Input: Cleansed post data

[1509] Data processing: Sentiment determination and topic extraction using natural language processing techniques

[1510] Output: Analysis data with sentiment and topic annotations

[1511] Step 5: Data visualization

[1512] The server converts the analysis results into visualization formats such as graphs and charts.

[1513] Input: Analysis data with sentiment and topic annotations

[1514] Data processing: Graph generation using visualization libraries (e.g., matplotlib)

[1515] Output: Visualized graphs and charts

[1516] Step 6: Report generation and distribution

[1517] The server automatically generates reports based on the visualized data and distributes them to relevant parties.

[1518] Input: Data for visualizations of graphs and charts

[1519] Data processing: Report generation and distribution via email or chat tools

[1520] Output: Report sent to stakeholders

[1521] Step 7: Real-time notifications and dashboard display

[1522] The server provides a dashboard that periodically updates and displays the data in real time, and also generates alerts based on specific sentiment results.

[1523] Input: Real-time collected analytics data

[1524] Data processing: Display on dashboard and generate alerts

[1525] Output: Latest data displayed in the dashboard and delivered alerts

[1526] 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.

[1527] 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.

[1528] 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.

[1529] 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.

[1530] 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.

[1531] 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.

[1532] 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).

[1533] 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.

[1534] 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."

[1535] 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.

[1536] 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).

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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.

[1544] 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.

[1545] 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.

[1546] 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.

[1547] The following is further disclosed regarding the above embodiment.

[1548] (Claim 1)

[1549] A means for automatically collecting posts related to a specified keyword from multiple online platforms;

[1550] a means for storing the collected posts in a database;

[1551] A way to filter out spam and noise from saved posts, and

[1552] means for analyzing the sentiment and topic of posts using natural language processing techniques;

[1553] A means of converting analytical results into visualization formats such as graphs and charts;

[1554] means for automatically generating a report including the visualized data;

[1555] a means for distributing the generated reports to interested parties;

[1556] A system that includes a means to periodically update aggregate data and display it in real time.

[1557] (Claim 2)

[1558] 10. The system of claim 1, wherein the system uses APIs of multiple online platforms to collect posts related to a specific keyword.

[1559] (Claim 3)

[1560] In the system of claim 1, means for performing sentiment analysis and topic extraction as natural language processing techniques.

[1561] (Claim 4)

[1562] 2. The system according to claim 1, further comprising means for distributing the visualized data to each of the participants via email or a chat tool.

[1563] (Claim 5)

[1564] 2. The system of claim 1, further comprising means for filtering spam from posted data stored in the database based on a specific keyword list or blacklist.

[1565] (Claim 6)

[1566] 10. The system of claim 1, wherein the system provides a dashboard for displaying fixed point observation data in real time.

[1567] "Example 1"

[1568] (Claim 1)

[1569] A means for automatically collecting posts related to a specified keyword from multiple online platforms;

[1570] a means for storing the collected posts in a database;

[1571] A way to filter out spam and noise from saved posts, and

[1572] means for analyzing the sentiment and topic of posts using natural language processing techniques;

[1573] A means of converting analytical results into visualization formats such as graphs and charts;

[1574] means for automatically generating a report including the visualized data;

[1575] a means for distributing the generated reports to interested parties;

[1576] A system that includes a means to periodically update aggregate data and display it in real time.

[1577] (Claim 2)

[1578] 10. The system of claim 1, further comprising: means for collecting posts related to a particular keyword using application program interfaces of multiple online platforms.

[1579] (Claim 3)

[1580] The system according to claim 1, characterized by means for performing sentiment analysis and topic extraction on the collected posting data using natural language processing technology.

[1581] "Application Example 1"

[1582] (Claim 1)

[1583] A means for automatically collecting posts related to a specified keyword from multiple online platforms;

[1584] a means for storing the collected posts in a database;

[1585] A way to filter out spam and noise from saved posts, and

[1586] means for analyzing the sentiment and topic of posts using natural language processing techniques;

[1587] A means of converting analytical results into visualization formats such as graphs and charts;

[1588] means for automatically generating a report including the visualized data;

[1589] a means for distributing the generated reports to interested parties;

[1590] Access via API to certain online platforms that collect feedback;

[1591] A means to display the analysis results in real time on a smartphone and on an in-car display,

[1592] A system that includes a means to periodically update aggregate data and display it in real time.

[1593] (Claim 2)

[1594] The system of claim 1, which uses APIs of multiple online platforms to collect posts related to specific keywords.

[1595] (Claim 3)

[1596] The system according to claim 1, wherein the natural language processing techniques include sentiment analysis and topic extraction.

[1597] "Example 2: Combining Emotion Engines"

[1598] (Claim 1)

[1599] A means for automatically collecting posts related to a specified keyword from multiple online platforms;

[1600] a means for storing the collected posts in a database;

[1601] A means of filtering out spam and noise from saved posts;

[1602] means for analyzing the sentiment and topic of posts using natural language processing techniques and a sentiment engine;

[1603] A means of converting analytical results into visualization formats such as graphs and charts;

[1604] means for automatically generating a report including the visualized data;

[1605] A means to distribute the generated reports to relevant parties via email or chat tools, and

[1606] A means to periodically update the aggregated data and display it in real time;

[1607] A system including means for detecting a particular emotional state and generating an alert using an emotion engine.

[1608] (Claim 2)

[1609] 10. The system of claim 1, further comprising: means for using APIs of multiple online platforms to collect posts related to a specific keyword.

[1610] (Claim 3)

[1611] 10. The system of claim 1, further comprising means for performing sentiment analysis and topic extraction of posts using natural language processing techniques and a sentiment engine.

[1612] "Application example 2 when combining emotion engines"

[1613] (Claim 1)

[1614] A means for automatically collecting posts related to a specified keyword from multiple online platforms;

[1615] a means for storing the collected posts in a database;

[1616] A way to filter out spam and noise from saved posts, and

[1617] means for analyzing the sentiment and topic of posts using natural language processing techniques;

[1618] A means of converting analytical results into visualization formats such as graphs and charts;

[1619] means for automatically generating a report including the visualized data;

[1620] a means for distributing the generated reports to interested parties;

[1621] A means to periodically update the aggregated data and display it in real time;

[1622] A means of notifying customers of their feedback in real time, and

[1623] means for generating and delivering alerts based on specific sentiment results;

[1624] A system that includes a means to view visualized data on a dashboard.

[1625] (Claim 2)

[1626] The system of claim 1, wherein the system uses an API to collect posts related to specified keywords.

[1627] (Claim 3)

[1628] 10. The system of claim 1, which uses natural language processing techniques to perform sentiment analysis and topic extraction. [Explanation of symbols]

[1629] 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 automatically collecting posts related to a specified keyword from multiple online platforms; a means for storing the collected posts in a database; A way to filter out spam and noise from saved posts, and means for analyzing the sentiment and topic of posts using natural language processing techniques; A means of converting analytical results into visualization formats such as graphs and charts; means for automatically generating a report including the visualized data; a means for distributing the generated reports to interested parties; A system that includes a means to periodically update aggregate data and display it in real time.

2. The system of claim 1 , wherein the collecting means uses APIs of multiple online platforms to collect posts related to a specific keyword.

3. The system according to claim 1 , wherein the analyzing means performs sentiment analysis and topic extraction as natural language processing techniques.

4. The system according to claim 1 , wherein the means for distributing distributes the visualized data to each of the participants using email or a chat tool.

5. 2. The system according to claim 1, wherein the filtering means performs spam filtering of the posted data stored in the database based on a specific keyword list or blacklist.

6. 2. The system of claim 1, wherein the displaying means provides a dashboard for displaying fixed point observation data in real time.

Images