System

Abstract

A system is provided.SOLUTION: A system, comprising: means for periodically collecting information about a market from a data source; means for analyzing the collected information; means for forecasting a market trend based on the analysis; and means for displaying the forecast through a user interface.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With the spread of online conferences, meeting progress management, multilingual support, and emotional understanding have become increasingly important. However, performing all of these functions requires diverse skills and knowledge, making it difficult to secure the necessary personnel. Furthermore, limited means of quickly and accurately grasping market trends present challenges that make strategic decision-making difficult for companies. [Means for solving the problem]

[0005] This invention provides a system that periodically collects market information from data sources, analyzes the collected information, predicts market trends based on the analysis results, and displays the prediction results through a user interface. Furthermore, it provides a system that can solve these problems by including a means for translating comments in real time during a meeting and displaying the translation results on the user interface, a means for analyzing the emotions of the comments, and displaying the emotion analysis results on the user interface. This system, which integrates meeting progress management, multilingual support, and emotion understanding, enables efficient and effective meeting management and market trend understanding.

[0006] "Data Source" refers to the source of data used to gather market information, including news articles, company research reports, public databases, etc.

[0007] "Means of collection" refers to the functions and methods for regularly obtaining the necessary information from data sources.

[0008] "Means of analysis" refers to the techniques used to process collected information and extract patterns and trends.

[0009] "Predictive tools" refers to algorithms and models that estimate future market trends based on analytical results.

[0010] "User interface" refers to a display screen or operating device that allows a user to visually check prediction results and analysis results.

[0011] "Real-time translation means" refers to technology that instantly converts what is being said during a meeting into another language.

[0012] "Means of emotion analysis" refers to technology for determining the emotional state of a speaker from the content and tone of what is said during a meeting.

[0013] "Sentiment analysis results" refers to information about the speaker's emotions obtained by means of analyzing emotions.

[0014] "Display means" refers to the technology for presenting analysis results, translation results, and sentiment analysis results to the user via a user interface. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0023] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] The present invention relates to a system for managing the progress of a web conference, performing real-time translation, analyzing emotions, and forecasting market trends. Hereinafter, an embodiment of this system will be described.

[0037] System Configuration

[0038] This system consists of a server, terminals, and users. The server performs the main data processing and analysis, while the terminals provide the user interface and the users operate the system. The server also obtains information from various data sources and performs analysis and predictions.

[0039] Server Functions and Operations

[0040] 1. Information gathering

[0041] The server regularly collects information about the web conferencing market from multiple data sources, including news APIs, corporate research reports, and public databases.

[0042] For example, once a day, the server retrieves the latest market articles from a news API and stores them in an internal database.

[0043] 2. Data Analysis

[0044] The server uses natural language processing technology and text mining to analyze the collected data.

[0045] For example, the server extracts frequently occurring keywords from collected articles to understand market interest.

[0046] 3. Generate a predictive model

[0047] The server generates a model to predict market trends based on the analysis results, and uses historical data to train machine learning algorithms to predict future market trends.

[0048] For example, the server predicts the market size trends for the next quarter based on past data.

[0049] 4. Real-time translation

[0050] The server translates what is said during the meeting in real time and sends it to the terminal.

[0051] For example, a Japanese utterance is translated into English and displayed to an English-speaking user.

[0052] 5. Sentiment analysis

[0053] The server analyzes the emotions of the speaker based on the content of what was said during the meeting.

[0054] For example, the server might classify a statement such as "I'm not confident in this plan" as negative.

[0055] Device features and operations

[0056] 1. Providing a user interface

[0057] The device provides a dashboard that allows users to visually check analysis and prediction results.

[0058] For example, the terminal may generate and display graphs and charts of market trends to the user.

[0059] 2. Real-time display

[0060] The device instantly displays the results of real-time translation and sentiment analysis sent from the server.

[0061] For example, comments made during a meeting are translated and displayed, along with the results of sentiment analysis.

[0062] User operations

[0063] 1. Viewing Information

[0064] Users can check market trends and analysis results in real time through their devices.

[0065] For example, users can view charts on a dashboard to quickly understand current market trends.

[0066] 2. Meeting progress management

[0067] Users can use the system to efficiently manage the progress of meetings, checking whether the agenda is being followed and making adjustments as necessary.

[0068] For example, the user is notified when the system is distracted from the agenda to focus on a sales strategy agenda.

[0069] 3. Multilingual support

[0070] Even if multiple languages ​​are used during a meeting, users can use the system's real-time translation function to understand what is being said in different languages.

[0071] For example, an English-speaking user can see Japanese utterances translated into English in real time.

[0072] In this way, the system supports the efficient operation of web conferences and becomes a powerful tool for companies to quickly grasp market trends.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The server periodically collects information about the web conferencing market from multiple data sources, specifically, retrieving the latest market articles from news APIs, and relevant data from corporate research reports and public databases, and stores this information in an internal database.

[0076] Step 2:

[0077] The server cleans the collected data, for example, by completing missing values ​​and removing duplicate data, and also by removing unnecessary HTML tags and special characters from text data to improve the quality of the data.

[0078] Step 3:

[0079] The server analyzes the cleaned data. Specifically, it performs text mining using natural language processing technology to extract important market keywords. It also performs frequency analysis of the extracted keywords to identify trends.

[0080] Step 4:

[0081] The server uses machine learning algorithms to cluster keywords and phrases, for example applying the K-means clustering algorithm to categorize the data by related topics, which reveals market interests.

[0082] Step 5:

[0083] The server collects historical data and uses it to train machine learning algorithms, for example using the past five years of market data to generate a linear regression model to predict market trends over the next five years.

[0084] Step 6:

[0085] The server uses the trained model to predict market trends based on the analysis results, and the prediction results are formatted in a way that is easy for users to understand and stored in an internal database.

[0086] Step 7:

[0087] The server translates comments made during the meeting in real time. For example, it translates Japanese comments into English and sends the translation results to the terminal. This enables multilingual support.

[0088] Step 8:

[0089] The server analyzes the emotions of the speaker based on what is said during the meeting. For example, it classifies a statement such as "I'm not confident about this plan" as negative and generates a sentiment analysis result.

[0090] Step 9:

[0091] The device displays analysis results, prediction results, real-time translation, and sentiment analysis results through a user interface. For example, the device's dashboard displays market trend graphs and charts, allowing users to understand current market trends and the progress of meetings.

[0092] Step 10:

[0093] Users can check market trends and analysis results in real time through their devices, efficiently manage the progress of meetings, and use the system's real-time translation function to understand statements in multiple languages.

[0094] Example 1

[0095] 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."

[0096] In today's business environment, fast and accurate market trend forecasting is crucial for maintaining a company's competitive edge. However, collecting and properly analyzing information from diverse data sources can be challenging, particularly due to language barriers and the difficulty of accurately understanding the speaker's emotions during meetings. Furthermore, there are few systems that integrate real-time translation and sentiment analysis, which can reduce the efficiency of meetings.

[0097] 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.

[0098] In this invention, the server includes means for periodically collecting market information from multiple data sources such as news APIs, research reports, and public databases, means for analyzing the collected data using natural language processing technology to extract frequently occurring keywords and sentiments, and means for predicting market trends using machine learning algorithms based on the analysis results, thereby enabling rapid and accurate understanding of market trends.

[0099] The system also includes a means for converting speech during a conference into text, a means for translating the converted text in real time, and a means for displaying the translation results on a user interface, thereby enabling smooth communication across language barriers.

[0100] The system also includes a means for analyzing the content of comments made during a meeting and classifying the emotions of the comments, and a means for displaying the real-time emotion analysis results on a user interface, which allows for accurate understanding of the emotions of the speakers and improves the efficiency of the meeting.

[0101] A "news API" is an application program interface for automatically retrieving news articles and information published on the web.

[0102] A "research report" is a document that compiles the results of specialized research on a market, industry, product, etc.

[0103] A "public database" is a collection of data provided by a government agency or public institution that is open to the public.

[0104] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0105] A "machine learning algorithm" is an algorithm that automatically learns patterns based on data and makes predictions and classifications.

[0106] A "user interface" refers to the screen and operating means that allow a user to interact with a system.

[0107] "Speech recognition" is a technology in which a computer converts human speech into text data.

[0108] "Real-time translation" is a technology that translates conversations and text into other languages ​​in real time.

[0109] "Sentiment analysis" is a technology that automatically analyzes emotional states from text data and classifies them as positive, negative, neutral, etc.

[0110] This invention relates to a system for managing the progress of web conferences, performing real-time translation, analyzing emotions, and forecasting market trends. This system is composed of a server, terminals, and users. A specific embodiment of this system will be described below.

[0111] Server Functions and Operations

[0112] The server is responsible for the main data processing and analysis functions. First, the server accesses multiple data sources, such as news APIs, research reports, and public databases. These APIs are accessed using news API keys and corporate research report access keys. The server periodically collects information from these data sources and stores it in an internal database. For example, every morning at 9:00, the server retrieves the latest articles about the web conferencing market from the news API and stores them in the database.

[0113] The server then analyzes the collected data using natural language processing techniques (e.g., NLTK, spaCy). It extracts frequently occurring keywords from the collected articles to understand market interest. It also uses sentiment analysis algorithms (e.g., TextBlob, VADER) to classify the content of the articles as positive, negative, or neutral. For example, it identifies the phrase "I'm not confident in this plan" as a negative sentiment.

[0114] The analyzed data is used as training data to predict market trends using machine learning algorithms. The server uses the past data to generate a model that predicts future market trends. The model trained by the machine learning algorithm predicts, for example, the market size for the next quarter.

[0115] Furthermore, to provide a real-time translation function, the server converts the conference voice into text using a speech recognition service (e.g., Google Speech-to-Text API) and translates the acquired text into a specified language using a translation service (e.g., Google Translate API). For example, Japanese statements may be translated into English and sent to the terminal for display to an English-speaking user.

[0116] Device features and operations

[0117] The device provides a dashboard that allows users to visually check analysis and forecast results. Web technologies such as HTML, CSS, and JavaScript are used for the user interface. For example, the device generates graphs and charts of market trends and displays them to the user. It also has the ability to display real-time translation results and sentiment analysis results on the conference screen. For example, the translation result of "Hello" can be displayed as "Hello," and the sentiment analysis result (negative) of the statement "I'm not confident in this plan" can be displayed at the same time.

[0118] User operations

[0119] Users can check market trends and analysis results in real time through their devices. They can quickly grasp current market trends by looking at market trend graphs on the dashboard. Users can also use the system to efficiently manage meeting progress, checking whether the meeting is proceeding according to the agenda and making adjustments as necessary. For example, users can be notified if the system deviates from the agenda in order to focus on the sales strategy topic. In addition, the real-time translation function allows users to understand statements in different languages. For example, an English-speaking user can see Japanese statements translated into English in real time.

[0120] Examples of prompt statements

[0121] Below are some examples of prompt sentences.

[0122] 1. Information Collection:

[0123] "Do you have sample code for a news API that retrieves the latest articles about the web conferencing market?"

[0124] 2. Data Analysis:

[0125] "Can you please give me some Python code to extract frequently occurring keywords from news articles about the web conferencing market?"

[0126] 3. Generate predictive models:

[0127] "I'd like to build a machine learning model to predict the market size for the next quarter based on historical market data. Can you give me some advice?"

[0128] 4. Real-time translation:

[0129] "Please tell me an API for translating Japanese to English in real time."

[0130] 5. Sentiment analysis:

[0131] "Please tell me a Python library that can analyze emotions from speech content."

[0132] 6. Progress management:

[0133] "I want to create a script to manage the progress of a meeting. Can you tell me the relevant APIs and libraries?"

[0134] In this way, the system helps to efficiently manage web conferences and is a powerful tool for companies to quickly grasp market trends.

[0135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0136] The flow of this system's program processing

[0137] Information gathering steps:

[0138] Step 1:

[0139] The server accesses the news API using the API key and sends a request to get the "latest articles about the web conferencing market." The input is the API key and request parameters, and the output is the latest article data.

[0140] Specific operation: The server calls the news API on a set schedule every morning at 9:00 and analyzes the JSON format data received as a response.

[0141] Step 2:

[0142] The server stores the retrieved news article data in an internal database. The input is news article data in JSON format, and the output is the articles stored in the database.

[0143] Specific operation: The server breaks down the retrieved article data into each field (e.g., title, content, publication date) and inserts it into the database using an SQL query.

[0144] Data analysis steps:

[0145] Step 1:

[0146] The server reads the stored news article data for analysis using natural language processing techniques. The input is the article data stored in the database, and the output is a tokenized word sequence.

[0147] Specific operation: The server retrieves article data in text format and tokenizes it using a natural language processing library (e.g., NLTK, spaCy).

[0148] Step 2:

[0149] The server extracts frequent keywords from the tokenized word string. The input is the tokenized word string, and the output is a list of frequent keywords.

[0150] Specific operation: The server analyzes the tokenized word string, calculates the frequency of each word, and selects particularly important keywords.

[0151] Step 3:

[0152] The server analyzes the content of articles using a sentiment analysis algorithm and classifies them as positive, negative, or neutral. The input is the text data of the article, and the output is the sentiment label (positive, negative, or neutral).

[0153] How it works: The server uses a sentiment analysis library such as TextBlob or VADER to calculate a sentiment score for each sentence.

[0154] Steps for generating a predictive model:

[0155] Step 1:

[0156] The server preprocesses the analyzed data as training data for a machine learning model. The input is the analyzed article data and a list of frequently occurring keywords, and the output is a training dataset.

[0157] Specific operation: The server quantifies the data and converts it into a format that can be used by the machine learning model (e.g., normalization, feature extraction).

[0158] Step 2:

[0159] The server uses machine learning algorithms to train models that predict market trends, where the input is a pre-processed training dataset and the output is a predictive model.

[0160] What it does: The server applies algorithms such as time series analysis and regression analysis to train a model using the data.

[0161] Real-time translation steps:

[0162] Step 1:

[0163] The server captures the voice during the conference and sends it to the speech recognition service to convert it into text. The input is real-time voice data, and the output is text data of the speech recognition results.

[0164] What it does: The server captures the audio stream in real time and sends it to the Google Speech-to-Text API to get the text data.

[0165] Step 2:

[0166] The server translates the text obtained by speech recognition into the specified language using a translation service. The input is the text data of the speech recognition result, and the output is the text data of the translation result.

[0167] Specific operation: The server uses the Google Translate API to translate the speech recognition results in real time and convert them into the specified language.

[0168] Sentiment analysis steps:

[0169] Step 1:

[0170] The server analyzes the content of speech during a meeting in real time and classifies the speaker's emotions. The input is the text data of the meeting audio, and the output is an emotion label (positive, negative, neutral).

[0171] Specific operation: The server analyzes the text obtained from the speech recognition results, calculates the emotion score using libraries such as TextBlob and VADER, and assigns emotion labels.

[0172] User operation steps:

[0173] Step 1:

[0174] Users can check the analysis and prediction results through a dashboard on their device. The input is the analysis and prediction results sent from the server, and the output is the graphs and charts displayed on the dashboard.

[0175] Specific operation: The user sees graphs and charts of market trends updated in real time on the device screen.

[0176] Step 2:

[0177] Users use the system to manage the progress of a conference. The input is real-time information about the progress of the conference, and the output is actions based on the user's decisions.

[0178] Specific operation: The user checks whether the meeting is proceeding according to the agenda and instructs the speaker to make adjustments if necessary.

[0179] Through the above processing steps, this system supports the efficient operation of web conferences and provides users with a powerful tool for timely understanding of market trends.

[0180] (Application example 1)

[0181] 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."

[0182] In modern store operations, serving customers who speak different languages ​​and understanding their immediate satisfaction are key issues. Insufficient multilingual support can lead to dissatisfaction among customers, leading to more negative feedback. It is also necessary to analyze customer sentiment in real time and respond quickly to improve customer satisfaction.

[0183] 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.

[0184] In this invention, the server includes means for periodically collecting market information from a data source, means for analyzing the collected information, means for predicting market trends based on the analysis results, means for displaying the prediction results through a user interface, means for real-time translation of customer responses, means for displaying the translation results on the user interface, means for sentiment analysis of customer comments, and means for displaying the sentiment analysis results on the user interface. This makes it possible to efficiently respond to customers who speak different languages, analyze customer sentiment in real time, and immediately provide appropriate responses, thereby improving customer satisfaction.

[0185] A "data source" is an external or internal source from which information is obtained.

[0186] "Means for periodically collecting information" are technological means for collecting data on the market at regular intervals.

[0187] "Means of analyzing information" refers to the technical means used to analyze collected data and extract meaning and trends.

[0188] "Means for predicting market trends" are technical means for predicting future market movements from analysis results.

[0189] A "user interface" is a screen or input device that allows a user to interact with a system.

[0190] A "translation tool" is a technical tool for converting an utterance in one language into another language.

[0191] "Means for emotion analysis" refers to a technical means for analyzing emotions from the content of statements and recognizing emotions such as positive and negative.

[0192] "Display means" refers to the technical means for visually presenting analysis results, translation results, etc. to the user.

[0193] "Customer response" refers to the activities of store staff to communicate with customers.

[0194] The system for implementing the present invention mainly comprises a server, a terminal, and a user. The server processes and analyzes data, the terminal provides a user interface, and the user operates the system.

[0195] Server Functions and Operations

[0196] 1. Information gathering

[0197] The server periodically collects market information from data sources, such as news APIs, corporate research reports, and public databases, and stores the information in an internal database. This allows you to always have access to the latest market information.

[0198] 2. Data Analysis

[0199] The server uses natural language processing (NLP) and text mining to analyze the collected data. For example, it extracts frequently occurring keywords from collected articles to understand market interest. This makes it possible to quickly detect changes in market trends.

[0200] 3. Generate a predictive model

[0201] The server generates a model to predict market trends based on the analysis results. Using past data, the machine learning algorithm is trained to predict future market trends. For example, predicting market size trends for the next quarter can help formulate future strategies.

[0202] 4. Real-time translation

[0203] The server translates comments made during meetings or customer interactions in real time. For example, Japanese comments can be translated into English and instantly displayed to English-speaking staff.

[0204] 5. Sentiment analysis

[0205] The server analyzes the speaker's sentiment based on the content of the comment. For example, it can classify a comment such as "This product is not very good" as negative and provide appropriate feedback.

[0206] Device features and operations

[0207] 1. Providing a user interface

[0208] The terminal provides a dashboard where users can visually check analysis and forecast results. Graphs and charts of market trends are generated and displayed to users, allowing them to intuitively grasp the information.

[0209] 2. Real-time display

[0210] The device instantly displays the translation results and sentiment analysis results sent from the server. For example, during a meeting or customer service, when a comment is translated and displayed, sentiment analysis results are also displayed at the same time.

[0211] User operations

[0212] 1. Viewing Information

[0213] Users can check market trends and analysis results in real time through their devices, and quickly grasp current market trends by looking at charts on the dashboard.

[0214] 2. Meeting progress management

[0215] Users can use the system to efficiently manage the progress of meetings and client interactions, check whether the agenda is being followed and make adjustments as necessary. For example, they can be notified if the system deviates from the agenda.

[0216] 3. Multilingual support

[0217] Even when multiple languages ​​are used during meetings or customer interactions, users can use the system's real-time translation function to understand what is being said in different languages. For example, an English-speaking user can see what is being said in Japanese translated into English in real time.

[0218] Specific examples

[0219] Technology used

[0220] Hardware: Smartphones, servers

[0221] Software: Python (textblob, googletrans, requests libraries)

[0222] Prompt Sentence Examples

[0223] If a customer says 'This product is not very good', perform sentiment analysis and output the results.

[0224] By combining these elements, it becomes possible to improve the efficiency of customer service in stores, increase customer satisfaction, and grasp market trends in real time.

[0225] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0226] Step 1:

[0227] Information gathering

[0228] The server periodically collects market information from data sources. This process retrieves the latest market data from news APIs, company research reports, public databases, etc. The input requires an API key and a search query, and the output is a dataset of news articles and reports. This data is then stored in an internal database.

[0229] Specific behavior:

[0230] 1. Send a query to the News API.

[0231] 2. Get the news article data returned as a response.

[0232] 3. The acquired data is stored in an internal database.

[0233] Step 2:

[0234] Data analysis

[0235] The server analyzes the collected data. Using natural language processing (NLP) and text mining, it extracts frequently occurring keywords from articles and understands market interest. The data collected in step 1 is required as input, and the extracted frequently occurring keywords and their frequency of appearance are obtained as output.

[0236] Specific behavior:

[0237] 1. Analyze the collected data using text mining tools.

[0238] 2. Extract frequently occurring keywords and calculate their frequency of occurrence.

[0239] 3. Compile the extracted keywords and their frequency into a report.

[0240] Step 3:

[0241] Generate predictive models

[0242] The server generates a model to predict market trends based on the analysis results. It uses past data to train a machine learning algorithm to predict future market trends. The inputs are past data and analysis results, and the output is a prediction of future market trends.

[0243] Specific behavior:

[0244] 1. Collect historical data and analysis results.

[0245] 2. Train the model using machine learning algorithms.

[0246] 3. Use the trained model to predict future market trends.

[0247] Step 4:

[0248] Real-time translation

[0249] The server translates customer utterances in real time. For example, Japanese utterances can be translated into English and instantly displayed to English-speaking staff. This process requires the customer's utterance as input and the translation result as output.

[0250] Specific behavior:

[0251] 1. Get what your customers say.

[0252] 2. Translate the speech through the translation API.

[0253] 3. The translated results are sent to the device and displayed.

[0254] Step 5:

[0255] sentiment analysis

[0256] The server performs sentiment analysis on customer comments. For example, it classifies a comment like "This product is not very good" as negative. The input is the customer's comment, and the output is the result of the sentiment analysis.

[0257] Specific behavior:

[0258] 1. Get what your customers say.

[0259] 2. Analyze the sentiment of statements using NLP technology.

[0260] 3. The results of the sentiment analysis are sent to the device and displayed.

[0261] Step 6:

[0262] Providing a user interface

[0263] The terminal provides a user interface and displays a dashboard for users to visually check the analysis results and prediction results. This process requires data sent from the server as input, and generates a dashboard that users can view as output.

[0264] Specific behavior:

[0265] 1. Receive data from the server.

[0266] 2. Generate a dashboard.

[0267] 3. Display analysis and prediction results.

[0268] Step 7:

[0269] Real-time display

[0270] The device displays translation results and sentiment analysis results in real time. Data sent from the server is required as input, and a screen that the user can view in real time is generated as output.

[0271] Specific behavior:

[0272] 1. Receive data from the server.

[0273] 2. Display on the screen in real time.

[0274] 3. Users can check the results on the spot.

[0275] Step 8:

[0276] Viewing information

[0277] Users can check market trends and analysis results in real time through their devices. This process requires dashboard data as input, and users can quickly grasp the information as output.

[0278] Specific behavior:

[0279] 1. Navigate the dashboard to find the information you need.

[0280] 2. View various graphs and charts.

[0281] 3. Filter the information as needed.

[0282] Step 9:

[0283] Meeting progress management

[0284] Users use the system to efficiently manage the progress of meetings and customer interactions. The system requires an agenda as input and provides progress notifications as output.

[0285] Specific behavior:

[0286] 1. Set the agenda.

[0287] 2. Monitor the progress of meetings and interactions.

[0288] 3. Receive notifications when you deviate from progress.

[0289] Step 10:

[0290] Multilingual support

[0291] Users can use real-time translation to understand utterances in different languages. An utterance is required as input, and a translation result is obtained as output.

[0292] Specific behavior:

[0293] 1. Get the statement.

[0294] 2. Translate the speech through the translation API.

[0295] 3. The translation results are displayed on the screen.

[0296] 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.

[0297] This invention combines a system that manages the progress of web conferences, performs real-time translation, analyzes emotions, and predicts market trends with an emotion engine that recognizes user emotions. Below, we will explain an embodiment of this system.

[0298] System Configuration

[0299] This system consists of a server, a terminal, a user, and an emotion engine. The server performs the main data processing and analysis, the terminal provides the user interface, and the user operates the system. The emotion engine recognizes and analyzes the user's emotions and feeds the results back to the system.

[0300] Server Functions and Operations

[0301] 1. Information gathering

[0302] The server periodically collects information about the web conferencing market from multiple data sources, such as news APIs, company research reports, public databases, etc. For example, once a day, the server retrieves the latest market articles from the news API and stores them in its internal database.

[0303] 2. Data Analysis

[0304] The server cleans the collected data and analyzes it using natural language processing technology and text mining. For example, the server extracts frequently appearing keywords from the collected articles to understand market interest.

[0305] 3. Generate a predictive model

[0306] The server generates a model to predict market trends based on the analysis results. It uses past data to train a machine learning algorithm to predict future market trends. For example, the server predicts the market size for the next quarter based on past data.

[0307] 4. Real-time translation

[0308] The server translates comments made during the meeting in real time and sends the translation to the terminal. For example, it translates Japanese comments into English and displays the translation results on the terminal.

[0309] 5. Sentiment analysis

[0310] The server analyzes the emotions of the speaker based on what is said during the meeting. For example, it classifies a statement such as "I'm not confident about this plan" as negative.

[0311] Device features and operations

[0312] 1. Providing a user interface

[0313] The terminal provides a dashboard that allows users to visually check the analysis and forecast results. For example, the terminal generates and displays graphs and charts of market trends to the user.

[0314] 2. Real-time display

[0315] The device instantly displays the results of real-time translation and sentiment analysis sent from the server. For example, when a comment made during a meeting is translated and displayed, the sentiment analysis results are also displayed at the same time.

[0316] Functions and operation of the Emotion Engine

[0317] 1. Emotional awareness

[0318] The emotion engine recognizes emotions by analyzing a user's tone of voice, facial recognition data, and word choice. For example, if a user is participating in a meeting through a camera, the emotion engine analyzes facial expression data to determine the user's emotion.

[0319] 2. Emotional Data Storage

[0320] The emotion engine stores the recognized emotion data, for example, the history of emotions expressed by users during a meeting, in a database for later analysis and feedback.

[0321] 3. Emotional Data Feedback

[0322] The server grasps the progress and tone of the meeting based on the emotion data obtained from the emotion engine, and dynamically adjusts the user interface. For example, the user interface displays a warning to the user if the meeting tone is biased toward a negative one.

[0323] User operations

[0324] 1. Viewing Information

[0325] Users can check market trends and analysis results in real time through their devices and simultaneously receive feedback from the emotion engine. For example, users can quickly grasp current market trends by looking at charts on the dashboard.

[0326] 2. Meeting progress management

[0327] Users use the system to efficiently manage the progress of meetings, checking whether the agenda is being followed and making adjustments as necessary. For example, users are notified when the system deviates from the agenda to focus on a sales strategy topic.

[0328] 3. Multilingual support

[0329] Even when multiple languages ​​are used during a meeting, users can use the system's real-time translation function to understand what is being said in different languages. For example, an English-speaking user can see what is being said in Japanese translated into English in real time.

[0330] 4. Use emotional feedback

[0331] Users can adjust the tone of the meeting and discussion based on feedback from the emotion engine. For example, if the meeting is heading in a negative direction, users can take measures such as actively encouraging positive opinions.

[0332] In this way, the system not only supports the efficient operation of web conferences and is a powerful tool for companies to quickly grasp market trends, but also enables more effective communication by recognizing participants' emotions and providing appropriate feedback.

[0333] The processing flow will be explained below.

[0334] Step 1:

[0335] The server periodically collects information about the web conferencing market from multiple data sources, including news APIs, company research reports, and public databases, and stores the latest information in an internal database. This process is performed automatically on a scheduled basis.

[0336] Step 2:

[0337] The server cleans the collected data by completing missing values, removing duplicate data, and removing unnecessary HTML tags and special characters from text data. This improves the quality of the data and increases the accuracy of analysis.

[0338] Step 3:

[0339] The server then uses natural language processing techniques and text mining to analyze the cleaned data, extracting key keywords and analyzing the frequency of these keywords, for example, to see if certain keywords related to market trends are increasing.

[0340] Step 4:

[0341] The server then clusters the extracted keywords and phrases using machine learning algorithms, such as the K-means clustering algorithm, to categorize the data by related topics, thereby revealing market interests.

[0342] Step 5:

[0343] The server collects historical data and uses it to train machine learning algorithms. For example, it uses the past five years of market data to generate a linear regression model to forecast market trends for the next five years. This model is then used to predict future market size and trends.

[0344] Step 6:

[0345] The server uses the trained model to predict market trends based on the analysis results. The prediction results are saved in JSON format and can be displayed through the user interface, allowing users to quickly grasp future market trends.

[0346] Step 7:

[0347] The server translates comments made during a meeting in real time. For example, if a user speaks in Japanese, it translates the comment into English in real time and sends it to the terminal. The translation result is displayed immediately, facilitating communication between participants who speak different languages.

[0348] Step 8:

[0349] The server analyzes the speaker's emotions from what is said during the meeting. The emotion engine analyzes voice tone, word choice, and facial recognition data to recognize the speaker's emotions. For example, it classifies a statement such as "I'm not confident about this plan" as negative.

[0350] Step 9:

[0351] The emotion engine stores the recognized emotion data, for example, the history of emotions expressed during a meeting, in a database for future analysis and feedback.

[0352] Step 10:

[0353] The device displays analysis results, prediction results, real-time translation, and sentiment analysis results through a user interface. For example, the device's dashboard displays market trend graphs and charts, allowing users to quickly grasp current market trends.

[0354] Step 11:

[0355] The device dynamically adjusts the content displayed in the user interface based on the emotion data acquired from the emotion engine. For example, if the tone of the meeting is biased toward negative, the user interface will display a warning to alert the user.

[0356] Step 12:

[0357] Users can view market trends and analysis results in real time through their devices, while simultaneously receiving feedback from the emotion engine, allowing them to understand the progress and tone of the meeting and make adjustments as needed.

[0358] Step 13:

[0359] Users can use the system to efficiently manage the progress of meetings, for example, by checking whether the meeting is proceeding according to the agenda and receiving notifications if the meeting deviates from the agenda, enabling smooth meeting management.

[0360] Step 14:

[0361] Users can use the system's real-time translation function to understand multilingual utterances. For example, an English-speaking user can see a Japanese utterance translated into English in real time.

[0362] In this way, this system not only improves the efficiency of web conferences and supports multiple languages, but also promotes more effective communication by using an emotion engine to recognize participants' emotions and provide appropriate feedback.

[0363] Example 2

[0364] 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."

[0365] Conventional web conferencing systems rarely offer integrated functions such as market trend forecasting, real-time translation, and sentiment analysis, making them insufficient for effective user decision-making and meeting progress. Furthermore, functions for recognizing user emotions and utilizing them in meeting progress are limited, making it difficult to respond appropriately based on participants' emotions. As a result, there are problems with reduced meeting efficiency and effectiveness.

[0366] 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.

[0367] In this invention, the server includes means for periodically collecting market information from data sources, means for analyzing the collected information, means for predicting market trends based on the analysis results, means for translating comments in real time during a conference, means for displaying the translation results on a user interface, means for analyzing the emotions of the comments, means for displaying the emotion analysis results on the user interface, means for analyzing facial recognition data and voice tone to recognize emotions, means for saving the recognized emotion data, and means for dynamically adjusting the user interface based on the emotion data. This makes it possible to efficiently manage the progress of a conference, quickly grasp market trends, and recognize users' emotions and provide appropriate feedback.

[0368] "Data Source" means an external source of information that provides information about the market.

[0369] "Means for collecting information" refers to systems and programs for periodically obtaining market information from data sources.

[0370] "Means for analyzing information" refers to systems and programs that cleanse collected data and analyze it using techniques such as natural language processing and text mining.

[0371] "Means for predicting market trends" are machine learning models and algorithms that predict future market trends based on analysis results.

[0372] "Means for translating statements made during a meeting in real time" refers to a system or program that instantly converts statements made during a meeting into a different language.

[0373] "Means for displaying the translation results on a user interface" refers to a system or program that displays the translated content on a terminal screen in real time.

[0374] A "means for analyzing the emotions of statements" is a system or program that identifies and classifies emotions based on the content of statements made during a meeting.

[0375] The "means for displaying the emotion analysis results on a user interface" refers to a system or program that displays the emotion analysis results on a terminal screen.

[0376] "Means for recognizing emotions by analyzing facial recognition data and voice tone" refers to a system or program that analyzes facial expressions and voice tone to identify a user's emotions.

[0377] The "means for storing recognized emotion data" refers to a system or program that stores analyzed emotion data in a database.

[0378] "Means for dynamically adjusting the user interface based on emotional data" refers to a system or program that changes the screen display in real time based on the user's emotional data.

[0379] This invention combines a system that manages the progress of web conferences, performs real-time translation, analyzes emotions, and predicts market trends with an emotion engine that recognizes user emotions. Below, we will explain an embodiment of this system.

[0380] System Configuration

[0381] This system consists of a server, a terminal, a user, and an emotion engine. The server performs the main data processing and analysis, the terminal provides the user interface, and the user operates the system. The emotion engine recognizes and analyzes the user's emotions and feeds the results back to the system.

[0382] Server Functions and Operations

[0383] The server performs the functions of information collection, data analysis, predictive model generation, real-time translation, and sentiment analysis, using the following software and tools:

[0384] Information gathering

[0385] The server periodically collects information about the web conferencing market from multiple data sources, such as news APIs, company research reports, public databases, etc. For example, once a day, the server retrieves the latest market articles from the news API and stores them in its internal database.

[0386] Data analysis

[0387] The server cleans the collected data and analyzes it using Python NLP libraries (NLTK, Spacy) and text mining tools. For example, the server extracts frequently occurring keywords from the collected articles to understand market interest.

[0388] Generate predictive models

[0389] The server generates a model to predict market trends based on the analysis results. It uses past data to train the model using Python machine learning libraries (scikit-learn, TensorFlow) and predicts future market trends. For example, the server predicts market size trends for the next quarter based on past data.

[0390] Real-time translation

[0391] The server uses Google's real-time translation API to translate what is said during the meeting and send it to the device. For example, it can translate Japanese comments into English and display the translation results on the device.

[0392] sentiment analysis

[0393] The server uses natural language processing technology to analyze the emotions of people speaking during meetings. For example, it classifies statements such as "I'm not confident about this plan" as negative.

[0394] Device features and operations

[0395] The terminal provides a user interface and displays analysis results, prediction results, and sentiment analysis results in real time.

[0396] Providing a user interface

[0397] The terminal provides a dashboard where users can visually check analysis and forecast results, and uses D3.js and Chart.js to generate and display graphs and charts of market trends.

[0398] Real-time display

[0399] The device instantly displays the results of real-time translation and sentiment analysis sent from the server. When speech is translated and displayed during a meeting, the sentiment analysis results are also displayed.

[0400] Functions and operation of the Emotion Engine

[0401] The emotion engine analyzes the user's voice tone and facial recognition data to recognize emotions.

[0402] Emotion recognition

[0403] The emotion engine uses OpenCV and dlib, and Google's Speech-to-Text API for voice recognition to recognize the user's emotions. For example, if a user is participating in a meeting via camera, facial expression data is analyzed to determine the user's emotions.

[0404] Storing Emotional Data

[0405] The emotion engine stores the recognized emotion data in a database (MySQL, PostgreSQL), for example, to store the history of emotions expressed during a meeting, for later analysis and feedback.

[0406] Emotional Data Feedback

[0407] The server uses the emotion data obtained from the emotion engine to grasp the progress and tone of the meeting and dynamically adjusts the user interface. For example, if the meeting tone is biased towards a negative one, it will display a warning to the user.

[0408] User operations

[0409] Users can operate the system through their terminals, view information in real time, and manage the progress of the conference.

[0410] Viewing information

[0411] Users can view market trends and analysis results in real time through their devices and receive feedback from the emotion engine. For example, they can view charts on a dashboard to understand current market trends.

[0412] Meeting progress management

[0413] Users use the system to efficiently manage the progress of meetings, check whether the agenda is being followed and make adjustments as necessary, for example, receive notifications if the agenda is deviating.

[0414] Multilingual support

[0415] Users can use the system's real-time translation feature to understand statements in different languages, for example, an English-speaking user can see a Japanese statement translated into English in real time.

[0416] Utilizing emotional feedback

[0417] Users can adjust the tone of the meeting and discussion based on feedback from the emotion engine. For example, if the meeting is heading in a negative direction, users can take measures such as actively encouraging positive opinions.

[0418] Specific examples and prompts for the generative AI model

[0419] Example 1: A user opens a dashboard and sees a graph of the latest market trends. The graph displays a 10% increase in market growth forecast for the next quarter compared to the previous year.

[0420] Example 2: During a meeting, someone says in Japanese, "We need to introduce a new product line." This is translated into English in real time and displayed as, "We need to introduce a new product line."

[0421] Example prompt 1:

[0422] "This system will tell us about the latest trends in the market."

[0423] Example prompt 2:

[0424] "Generate a model that predicts market trends for the next quarter."

[0425] Example prompt 3:

[0426] "Please translate what is being said in a meeting in real time and display the results."

[0427] As described above, this system supports efficient web conference management and is a powerful tool for companies to quickly grasp market trends. Furthermore, it recognizes participants' emotions and provides appropriate feedback, enabling more effective communication.

[0428] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0429] Step 1:

[0430] Information gathering

[0431] The server regularly collects information about the web conferencing market from multiple data sources, including news APIs, corporate research reports, and public databases.

[0432] Input: News API endpoint URL, API key

[0433] Data processing: The server uses the API key to send an HTTP request to the news API to retrieve new articles.

[0434] Output: Store the retrieved market articles in an internal database.

[0435] Specific operation: The server sets up a scheduled task to retrieve the latest information from the news API at a specific time every day and store it in a database.

[0436] Step 2:

[0437] Data analysis

[0438] The server cleans the collected data and analyzes it using natural language processing libraries (e.g., NLTK, Spacy) and text mining tools.

[0439] Input: Unparsed article data in the internal database

[0440] Data processing: Remove unnecessary information from the articles (HTML tags, spaces, etc.), tokenize the text, and extract keywords.

[0441] Output: Analysis results (keywords, phrases, etc.) are saved in a database.

[0442] Specific operation: The server runs the cleansing script to clean the raw data, and then uses NLP algorithms to extract keywords.

[0443] Step 3:

[0444] Generate predictive models

[0445] The server uses historical data to generate models that predict market trends using Python machine learning libraries (e.g., scikit-learn, TensorFlow).

[0446] Input: Analysis result database, historical market data

[0447] Data processing: Split the dataset into a training set and a test set, and apply an algorithm to train the model.

[0448] Output: A trained predictive model

[0449] Specific operation: The server periodically runs model training jobs and deploys the generated models to the prediction engine.

[0450] Step 4:

[0451] Real-time translation

[0452] The server uses Google's real-time translation API to translate what is said during the meeting and send it to the device.

[0453] Input: Audio data during the meeting

[0454] Data processing: Convert the voice data into text and call the translation API to obtain the translated text.

[0455] Output: Translation result text

[0456] Specific operation: The server performs speech recognition in real time, sends a request to the translation API, and sends the resulting translation results to the device.

[0457] Step 5:

[0458] sentiment analysis

[0459] The server uses natural language processing technology to analyze the emotions of speakers from what is said during the meeting.

[0460] Input: Text data during the meeting

[0461] Data processing: Text data is input into a sentiment analysis model and sentiment labels are assigned.

[0462] Output: Sentiment analysis label (e.g. positive, negative, neutral)

[0463] Specific operation: The server uses a sentiment analysis model to classify comments made during the meeting in real time and saves the analysis results.

[0464] Step 6:

[0465] Providing a user interface

[0466] The device provides a dashboard that allows users to visually check analysis results, prediction results, and sentiment analysis results.

[0467] Input: Analysis results, prediction results, and sentiment analysis results sent from the server

[0468] Data processing: Converts received data into graph or chart format and displays it.

[0469] Output: Visual information on a dashboard

[0470] Specific operation: The device uses D3.js and Chart.js to display and update data in real time.

[0471] Step 7:

[0472] Real-time display

[0473] The device instantly displays the results of real-time translation and sentiment analysis sent from the server.

[0474] Input: Real-time translation results, sentiment analysis results

[0475] Data processing: The received data is immediately displayed and updated.

[0476] Output: On-screen translated text and sentiment labels

[0477] Specific behavior: When the device receives new data, it updates the current display, providing the user with information in real time.

[0478] Step 8:

[0479] emotion recognition

[0480] The emotion engine uses OpenCV and dlib to analyze facial expression data and Google's Speech-to-Text API to analyze voice tones to recognize emotions.

[0481] Input: Camera feed, audio feed

[0482] Data processing: Analyze facial expression data and voice tone to classify emotions.

[0483] Output: Emotion identification result

[0484] Specific operation: The emotion engine analyzes video and audio data in real time and stores the recognized emotions in a database.

[0485] Step 9:

[0486] Storing Emotional Data

[0487] The emotion engine stores the recognized emotion data in a database (e.g., MySQL, PostgreSQL).

[0488] Input: Emotion identification result

[0489] Data processing: Converting the emotion data into an appropriate format and inserting it into the database.

[0490] Output: Emotion data stored in a database

[0491] Specific operation: The emotion engine periodically writes emotion data to the database.

[0492] Step 10:

[0493] Emotional Data Feedback

[0494] The server dynamically adjusts the user interface based on the emotion data obtained from the emotion engine.

[0495] Input: Emotion data

[0496] Data processing: Analyzes emotional data and instructs UI changes.

[0497] Output: Updated user interface

[0498] Specific operation: The server analyzes the emotional data and displays a warning in negative situations and highlights positive situations.

[0499] The above is a description of the specific processing steps of the program for this system. Each step works together to provide useful information to users in real time and to efficiently manage the progress of the conference.

[0500] (Application example 2)

[0501] 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."

[0502] Conventional food delivery services lack sufficient communication between delivery personnel and customers, making it difficult to provide real-time feedback to improve customer satisfaction. Furthermore, they lack multilingual capabilities, making it difficult to communicate smoothly with customers who speak different languages. Furthermore, they do not properly recognize customer emotions and improve services based on them, limiting the improvement of service quality. To address these issues, a system with more advanced communication support and emotion analysis capabilities is needed.

[0503] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0504] In this invention, the server includes means for periodically collecting market information from a data source, means for analyzing the collected information, means for predicting market trends based on the analysis results, means for displaying the prediction results through a user interface, means for collecting voices of delivery personnel and customers, means for converting the collected voices into text, means for translating the converted text in real time, means for analyzing customer emotions, means for saving analyzed emotion data, and means for providing feedback based on the emotion data. This enables real-time, multilingual communication during delivery, and by immediately understanding customer emotions and providing feedback, it is possible to improve service quality and customer satisfaction.

[0505] A "data source" is an external information provider from which market information can be obtained.

[0506] A "market trend" is a collection of data that describes the current state and expected future changes in a particular market.

[0507] A "user interface" is an interface consisting of a display device and an input device that allows a user to interact with a system.

[0508] The "means for collecting voices of delivery personnel and customers" refers to a device or method for collecting voice data of interactions between delivery personnel and customers during the delivery process.

[0509] A "means for converting speech to text" is a device or method that analyzes collected speech data and converts it into text format data.

[0510] A "means for real-time text translation" is a device or method for instantly translating text data into another language.

[0511] The "means for analyzing customer emotions" refers to a device or method for analyzing emotions using customer voice and facial expression data.

[0512] "Means for saving analyzed emotion data" refers to a device or method for saving analyzed emotion data in a database or the like.

[0513] A "means for providing feedback based on emotional data" is a device or method that provides real-time service adjustments or advice based on stored emotional data.

[0514] The system embodying this invention is realized by the following main components: a server, a terminal, a delivery person, a customer, and an emotion engine. The server processes and analyzes data, the terminal provides a user interface through which delivery people and customers operate the system, and the emotion engine recognizes and analyzes the customer's emotions and feeds the results back to the system.

[0515] Server Functions and Operations

[0516] 1. Information gathering

[0517] The server periodically collects market information from multiple data sources, such as news APIs, company research reports, public databases, etc. For example, once a day, the server retrieves the latest market articles from the news API and stores them in its internal database.

[0518] 2. Data Analysis

[0519] The server cleans the collected data and analyzes it using natural language processing technology and text mining. For example, the server extracts frequently appearing keywords from the collected articles to understand market interest.

[0520] 3. Market Trend Forecast

[0521] The server generates a model to predict market trends based on the analysis results. It uses past data to train a machine learning algorithm to predict future market trends. For example, the server predicts the market size for the next quarter based on past data.

[0522] 4. Real-time translation

[0523] The server translates the conversation between the delivery person and the customer in real time and sends it to the terminal. For example, it translates Japanese statements into English and displays the translation results on the terminal.

[0524] 5. Emotion analysis

[0525] The server analyzes the content and tone of the conversation between the delivery person and the customer to recognize emotions. For example, if a customer says, "Thank you, that was very helpful," it classifies the comment as positive.

[0526] Device features and operations

[0527] 1. Providing a user interface

[0528] The terminal provides a dashboard where delivery personnel and customers can visually view analytics and feedback, such as graphs of delivery satisfaction and market trends.

[0529] 2. Real-time display

[0530] The device instantly displays the results of real-time translation and sentiment analysis sent from the server. For example, when a delivery person's words are translated and displayed, the sentiment analysis results are also displayed.

[0531] Functions and operation of the Emotion Engine

[0532] 1. Emotional awareness

[0533] The emotion engine recognizes emotions by analyzing the customer's voice tone and facial expression data. For example, if a customer accepts a delivery via camera, the emotion engine analyzes facial expression data to determine the emotion.

[0534] 2. Emotional Data Storage

[0535] The emotion engine stores the recognized emotion data, for example, the history of emotions expressed by customers during delivery, in a database for later analysis and feedback.

[0536] 3. Emotional Data Feedback

[0537] The server grasps the delivery status and customer satisfaction level based on the emotion data obtained from the emotion engine, and dynamically adjusts the user interface. For example, the user interface displays a warning to the delivery person if the customer is in a negative state.

[0538] User operations

[0539] 1. Viewing Information

[0540] Users can check market trends and analysis results in real time through their devices and simultaneously receive feedback from the emotion engine. For example, users can quickly grasp current market trends by looking at charts on the dashboard.

[0541] 2. Communication support

[0542] Users can use the system to facilitate communication during deliveries, using the real-time translation function between different languages ​​to ensure smooth delivery.

[0543] 3. Use emotional feedback

[0544] Users can improve the quality of their deliveries based on feedback from the emotion engine. For example, if a customer has a negative reaction, users can take immediate action to improve the quality of their deliveries.

[0545] Examples of specific examples and prompts

[0546] Examples:

[0547] If the delivery person only speaks Japanese and the customer only speaks English

[0548] Delivery Person: "Hello, here's a delivery for you."

[0549] English translation example: "Hello, I have a delivery for you."

[0550] Customer response (sentiment analysis results): Customer: "Thank you! This is perfect!" → Positive evaluation

[0551] Application-generated feedback: Smart glasses display to delivery driver, "We've confirmed that the customer is satisfied."

[0552] Example prompt sentence:

[0553] Customer says: "Thank you! This is perfect!"

[0554] Prompt to the sentiment analysis engine: "Analyze the customer's voice and determine whether it is positive or negative."

[0555] Output: "Positive"

[0556] Prompt the generative AI model: "Analyze the customer's voice and generate emotional feedback."

[0557] Example output: "The customer appears to be very satisfied. We will leave positive feedback."

[0558] In this way, the present invention supports smooth communication during delivery and improves real-time customer satisfaction.

[0559] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0560] Step 1:

[0561] The server collects the voices of the delivery person and the customer using the smartphone's microphone, and the collected voice data is sent directly to the next processing step.

[0562] Input: Audio data

[0563] Output: Raw audio data

[0564] What it does: The delivery person's smartphone captures the conversation with the customer.

[0565] Step 2:

[0566] The server converts the collected voice data into text data using the Google Cloud Speech-to-Text API, which converts the speech obtained from the voice into text format.

[0567] Input: Raw audio data

[0568] Output: Text data

[0569] Specific operation: The server sends the audio data to Google Cloud and receives it as text data.

[0570] Step 3:

[0571] The server uses the Google Cloud Translation API to translate the generated text data into other languages ​​in real time, and the translated data is displayed through the user interface.

[0572] Input: Text data

[0573] Output: Translated text data

[0574] Specific operation: The server sends text data to the Google Cloud Translation API and receives the translated text data.

[0575] Step 4:

[0576] The server uses the Microsoft Azure Emotion API to analyze the translated text data and voice tone to recognize the customer's emotions, which are then used for immediate feedback.

[0577] Input: Translated text data, audio tone

[0578] Output: Sentiment data (positive, negative, etc.)

[0579] Specific operation: The server sends text data and audio tones to Microsoft Azure and receives emotion data.

[0580] Step 5:

[0581] The server stores the analyzed emotion data in a database, which is then used to analyze market trends and provide feedback.

[0582] Input: Emotion data

[0583] Output: Stored emotion data

[0584] Specific operation: The server stores the emotion data in an internal database.

[0585] Step 6:

[0586] The server provides real-time feedback based on the emotion data and displays it on the user interface, allowing the delivery person to understand the customer's satisfaction level and take necessary action.

[0587] Input: Stored emotion data

[0588] Output: Feedback displayed in the user interface

[0589] Specific operation: The server analyzes the emotional data, generates positive or negative feedback, and sends it to the device for display.

[0590] Step 7:

[0591] Through the user interface, users can check market trends and feedback results in real time and take action as needed, for example, identifying areas for improvement for the next delivery.

[0592] Input: Feedback and market trend data displayed in the user interface

[0593] Output: User response or action

[0594] Specific actions: The user checks the device dashboard and takes the necessary action.

[0595] Although I have summarized it in a simple manner, the above invention is implemented smoothly by the detailed processes of collection, conversion, translation, recognition, storage, feedback, and response at each step.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] [Second embodiment]

[0600] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0601] 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.

[0602] 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).

[0603] 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.

[0604] 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.

[0605] 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).

[0606] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0607] 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.

[0608] 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.

[0609] 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.

[0610] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0611] 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."

[0612] The present invention relates to a system for managing the progress of a web conference, performing real-time translation, analyzing emotions, and forecasting market trends. Hereinafter, an embodiment of this system will be described.

[0613] System Configuration

[0614] This system consists of a server, terminals, and users. The server performs the main data processing and analysis, while the terminals provide the user interface and the users operate the system. The server also obtains information from various data sources and performs analysis and predictions.

[0615] Server Functions and Operations

[0616] 1. Information gathering

[0617] The server regularly collects information about the web conferencing market from multiple data sources, including news APIs, corporate research reports, and public databases.

[0618] For example, once a day, the server retrieves the latest market articles from a news API and stores them in an internal database.

[0619] 2. Data Analysis

[0620] The server uses natural language processing technology and text mining to analyze the collected data.

[0621] For example, the server extracts frequently occurring keywords from collected articles to understand market interest.

[0622] 3. Generate a predictive model

[0623] The server generates a model to predict market trends based on the analysis results, and uses historical data to train machine learning algorithms to predict future market trends.

[0624] For example, the server predicts the market size trends for the next quarter based on past data.

[0625] 4. Real-time translation

[0626] The server translates what is said during the meeting in real time and sends it to the terminal.

[0627] For example, a Japanese utterance is translated into English and displayed to an English-speaking user.

[0628] 5. Sentiment analysis

[0629] The server analyzes the emotions of the speaker based on the content of what was said during the meeting.

[0630] For example, the server might classify a statement such as "I'm not confident in this plan" as negative.

[0631] Device features and operations

[0632] 1. Providing a user interface

[0633] The device provides a dashboard that allows users to visually check analysis and prediction results.

[0634] For example, the terminal may generate and display graphs and charts of market trends to the user.

[0635] 2. Real-time display

[0636] The device instantly displays the results of real-time translation and sentiment analysis sent from the server.

[0637] For example, comments made during a meeting are translated and displayed, along with the results of sentiment analysis.

[0638] User operations

[0639] 1. Viewing Information

[0640] Users can check market trends and analysis results in real time through their devices.

[0641] For example, users can view charts on a dashboard to quickly understand current market trends.

[0642] 2. Meeting progress management

[0643] Users can use the system to efficiently manage the progress of meetings, checking whether the agenda is being followed and making adjustments as necessary.

[0644] For example, the user is notified when the system is distracted from the agenda to focus on a sales strategy agenda.

[0645] 3. Multilingual support

[0646] Even if multiple languages ​​are used during a meeting, users can use the system's real-time translation function to understand what is being said in different languages.

[0647] For example, an English-speaking user can see Japanese utterances translated into English in real time.

[0648] In this way, the system supports the efficient operation of web conferences and becomes a powerful tool for companies to quickly grasp market trends.

[0649] The processing flow will be explained below.

[0650] Step 1:

[0651] The server periodically collects information about the web conferencing market from multiple data sources, specifically, retrieving the latest market articles from news APIs, and relevant data from corporate research reports and public databases, and stores this information in an internal database.

[0652] Step 2:

[0653] The server cleans the collected data, for example, by completing missing values ​​and removing duplicate data, and also by removing unnecessary HTML tags and special characters from text data to improve the quality of the data.

[0654] Step 3:

[0655] The server analyzes the cleaned data. Specifically, it performs text mining using natural language processing technology to extract important market keywords. It also performs frequency analysis of the extracted keywords to identify trends.

[0656] Step 4:

[0657] The server uses machine learning algorithms to cluster keywords and phrases, for example applying the K-means clustering algorithm to categorize the data by related topics, which reveals market interests.

[0658] Step 5:

[0659] The server collects historical data and uses it to train machine learning algorithms, for example using the past five years of market data to generate a linear regression model to predict market trends over the next five years.

[0660] Step 6:

[0661] The server uses the trained model to predict market trends based on the analysis results, and the prediction results are formatted in a way that is easy for users to understand and stored in an internal database.

[0662] Step 7:

[0663] The server translates comments made during the meeting in real time. For example, it translates Japanese comments into English and sends the translation results to the terminal. This enables multilingual support.

[0664] Step 8:

[0665] The server analyzes the emotions of the speaker based on what is said during the meeting. For example, it classifies a statement such as "I'm not confident about this plan" as negative and generates a sentiment analysis result.

[0666] Step 9:

[0667] The device displays analysis results, prediction results, real-time translation, and sentiment analysis results through a user interface. For example, the device's dashboard displays market trend graphs and charts, allowing users to understand current market trends and the progress of meetings.

[0668] Step 10:

[0669] Users can check market trends and analysis results in real time through their devices, efficiently manage the progress of meetings, and use the system's real-time translation function to understand statements in multiple languages.

[0670] Example 1

[0671] 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."

[0672] In today's business environment, fast and accurate market trend forecasting is crucial for maintaining a company's competitive edge. However, collecting and properly analyzing information from diverse data sources can be challenging, particularly due to language barriers and the difficulty of accurately understanding the speaker's emotions during meetings. Furthermore, there are few systems that integrate real-time translation and sentiment analysis, which can reduce the efficiency of meetings.

[0673] 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.

[0674] In this invention, the server includes means for periodically collecting market information from multiple data sources such as news APIs, research reports, and public databases, means for analyzing the collected data using natural language processing technology to extract frequently occurring keywords and sentiments, and means for predicting market trends using machine learning algorithms based on the analysis results, thereby enabling rapid and accurate understanding of market trends.

[0675] The system also includes a means for converting speech during a conference into text, a means for translating the converted text in real time, and a means for displaying the translation results on a user interface, thereby enabling smooth communication across language barriers.

[0676] The system also includes a means for analyzing the content of comments made during a meeting and classifying the emotions of the comments, and a means for displaying the real-time emotion analysis results on a user interface, which allows for accurate understanding of the emotions of the speakers and improves the efficiency of the meeting.

[0677] A "news API" is an application program interface for automatically retrieving news articles and information published on the web.

[0678] A "research report" is a document that compiles the results of specialized research on a market, industry, product, etc.

[0679] A "public database" is a collection of data provided by a government agency or public institution that is open to the public.

[0680] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0681] A "machine learning algorithm" is an algorithm that automatically learns patterns based on data and makes predictions and classifications.

[0682] A "user interface" refers to the screen and operating means that allow a user to interact with a system.

[0683] "Speech recognition" is a technology in which a computer converts human speech into text data.

[0684] "Real-time translation" is a technology that translates conversations and text into other languages ​​in real time.

[0685] "Sentiment analysis" is a technology that automatically analyzes emotional states from text data and classifies them as positive, negative, neutral, etc.

[0686] This invention relates to a system for managing the progress of web conferences, performing real-time translation, analyzing emotions, and forecasting market trends. This system is composed of a server, terminals, and users. A specific embodiment of this system will be described below.

[0687] Server Functions and Operations

[0688] The server is responsible for the main data processing and analysis functions. First, the server accesses multiple data sources, such as news APIs, research reports, and public databases. These APIs are accessed using news API keys and corporate research report access keys. The server periodically collects information from these data sources and stores it in an internal database. For example, every morning at 9:00, the server retrieves the latest articles about the web conferencing market from the news API and stores them in the database.

[0689] The server then analyzes the collected data using natural language processing techniques (e.g., NLTK, spaCy). It extracts frequently occurring keywords from the collected articles to understand market interest. It also uses sentiment analysis algorithms (e.g., TextBlob, VADER) to classify the content of the articles as positive, negative, or neutral. For example, it identifies the phrase "I'm not confident in this plan" as a negative sentiment.

[0690] The analyzed data is used as training data to predict market trends using machine learning algorithms. The server uses the past data to generate a model that predicts future market trends. The model trained by the machine learning algorithm predicts, for example, the market size for the next quarter.

[0691] Furthermore, to provide a real-time translation function, the server converts the conference voice into text using a speech recognition service (e.g., Google Speech-to-Text API) and translates the acquired text into a specified language using a translation service (e.g., Google Translate API). For example, Japanese statements may be translated into English and sent to the terminal for display to an English-speaking user.

[0692] Device features and operations

[0693] The device provides a dashboard that allows users to visually check analysis and forecast results. Web technologies such as HTML, CSS, and JavaScript are used for the user interface. For example, the device generates graphs and charts of market trends and displays them to the user. It also has the ability to display real-time translation results and sentiment analysis results on the conference screen. For example, the translation result of "Hello" can be displayed as "Hello," and the sentiment analysis result (negative) of the statement "I'm not confident in this plan" can be displayed at the same time.

[0694] User operations

[0695] Users can check market trends and analysis results in real time through their devices. They can quickly grasp current market trends by looking at market trend graphs on the dashboard. Users can also use the system to efficiently manage meeting progress, checking whether the meeting is proceeding according to the agenda and making adjustments as necessary. For example, users can be notified if the system deviates from the agenda in order to focus on the sales strategy topic. In addition, the real-time translation function allows users to understand statements in different languages. For example, an English-speaking user can see Japanese statements translated into English in real time.

[0696] Examples of prompt statements

[0697] Below are some examples of prompt sentences.

[0698] 1. Information Collection:

[0699] "Do you have sample code for a news API that retrieves the latest articles about the web conferencing market?"

[0700] 2. Data Analysis:

[0701] "Can you please give me some Python code to extract frequently occurring keywords from news articles about the web conferencing market?"

[0702] 3. Generate predictive models:

[0703] "I'd like to build a machine learning model to predict the market size for the next quarter based on historical market data. Can you give me some advice?"

[0704] 4. Real-time translation:

[0705] "Please tell me an API for translating Japanese to English in real time."

[0706] 5. Sentiment analysis:

[0707] "Please tell me a Python library that can analyze emotions from speech content."

[0708] 6. Progress management:

[0709] "I want to create a script to manage the progress of a meeting. Can you tell me the relevant APIs and libraries?"

[0710] In this way, the system helps to efficiently manage web conferences and is a powerful tool for companies to quickly grasp market trends.

[0711] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0712] The flow of this system's program processing

[0713] Information gathering steps:

[0714] Step 1:

[0715] The server accesses the news API using the API key and sends a request to get the "latest articles about the web conferencing market." The input is the API key and request parameters, and the output is the latest article data.

[0716] Specific operation: The server calls the news API on a set schedule every morning at 9:00 and analyzes the JSON format data received as a response.

[0717] Step 2:

[0718] The server stores the retrieved news article data in an internal database. The input is news article data in JSON format, and the output is the articles stored in the database.

[0719] Specific operation: The server breaks down the retrieved article data into each field (e.g., title, content, publication date) and inserts it into the database using an SQL query.

[0720] Data analysis steps:

[0721] Step 1:

[0722] The server reads the stored news article data for analysis using natural language processing techniques. The input is the article data stored in the database, and the output is a tokenized word sequence.

[0723] Specific operation: The server retrieves article data in text format and tokenizes it using a natural language processing library (e.g., NLTK, spaCy).

[0724] Step 2:

[0725] The server extracts frequent keywords from the tokenized word string. The input is the tokenized word string, and the output is a list of frequent keywords.

[0726] Specific operation: The server analyzes the tokenized word string, calculates the frequency of each word, and selects particularly important keywords.

[0727] Step 3:

[0728] The server analyzes the content of articles using a sentiment analysis algorithm and classifies them as positive, negative, or neutral. The input is the text data of the article, and the output is the sentiment label (positive, negative, or neutral).

[0729] How it works: The server uses a sentiment analysis library such as TextBlob or VADER to calculate a sentiment score for each sentence.

[0730] Steps for generating a predictive model:

[0731] Step 1:

[0732] The server preprocesses the analyzed data as training data for a machine learning model. The input is the analyzed article data and a list of frequently occurring keywords, and the output is a training dataset.

[0733] Specific operation: The server quantifies the data and converts it into a format that can be used by the machine learning model (e.g., normalization, feature extraction).

[0734] Step 2:

[0735] The server uses machine learning algorithms to train models that predict market trends, where the input is a pre-processed training dataset and the output is a predictive model.

[0736] What it does: The server applies algorithms such as time series analysis and regression analysis to train a model using the data.

[0737] Real-time translation steps:

[0738] Step 1:

[0739] The server captures the voice during the conference and sends it to the speech recognition service to convert it into text. The input is real-time voice data, and the output is text data of the speech recognition results.

[0740] What it does: The server captures the audio stream in real time and sends it to the Google Speech-to-Text API to get the text data.

[0741] Step 2:

[0742] The server translates the text obtained by speech recognition into the specified language using a translation service. The input is the text data of the speech recognition result, and the output is the text data of the translation result.

[0743] Specific operation: The server uses the Google Translate API to translate the speech recognition results in real time and convert them into the specified language.

[0744] Sentiment analysis steps:

[0745] Step 1:

[0746] The server analyzes the content of speech during a meeting in real time and classifies the speaker's emotions. The input is the text data of the meeting audio, and the output is an emotion label (positive, negative, neutral).

[0747] Specific operation: The server analyzes the text obtained from the speech recognition results, calculates the emotion score using libraries such as TextBlob and VADER, and assigns emotion labels.

[0748] User operation steps:

[0749] Step 1:

[0750] Users can check the analysis and prediction results through a dashboard on their device. The input is the analysis and prediction results sent from the server, and the output is the graphs and charts displayed on the dashboard.

[0751] Specific operation: The user sees graphs and charts of market trends updated in real time on the device screen.

[0752] Step 2:

[0753] Users use the system to manage the progress of a conference. The input is real-time information about the progress of the conference, and the output is actions based on the user's decisions.

[0754] Specific operation: The user checks whether the meeting is proceeding according to the agenda and instructs the speaker to make adjustments if necessary.

[0755] Through the above processing steps, this system supports the efficient operation of web conferences and provides users with a powerful tool for timely understanding of market trends.

[0756] (Application example 1)

[0757] 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."

[0758] In modern store operations, serving customers who speak different languages ​​and understanding their immediate satisfaction are key issues. Insufficient multilingual support can lead to dissatisfaction among customers, leading to more negative feedback. It is also necessary to analyze customer sentiment in real time and respond quickly to improve customer satisfaction.

[0759] 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.

[0760] In this invention, the server includes means for periodically collecting market information from a data source, means for analyzing the collected information, means for predicting market trends based on the analysis results, means for displaying the prediction results through a user interface, means for real-time translation of customer responses, means for displaying the translation results on the user interface, means for sentiment analysis of customer comments, and means for displaying the sentiment analysis results on the user interface. This makes it possible to efficiently respond to customers who speak different languages, analyze customer sentiment in real time, and immediately provide appropriate responses, thereby improving customer satisfaction.

[0761] A "data source" is an external or internal source from which information is obtained.

[0762] "Means for periodically collecting information" are technological means for collecting data on the market at regular intervals.

[0763] "Means of analyzing information" refers to the technical means used to analyze collected data and extract meaning and trends.

[0764] "Means for predicting market trends" are technical means for predicting future market movements from analysis results.

[0765] A "user interface" is a screen or input device that allows a user to interact with a system.

[0766] A "translation tool" is a technical tool for converting an utterance in one language into another language.

[0767] "Means for emotion analysis" refers to a technical means for analyzing emotions from the content of statements and recognizing emotions such as positive and negative.

[0768] "Display means" refers to the technical means for visually presenting analysis results, translation results, etc. to the user.

[0769] "Customer response" refers to the activities of store staff to communicate with customers.

[0770] The system for implementing the present invention mainly comprises a server, a terminal, and a user. The server processes and analyzes data, the terminal provides a user interface, and the user operates the system.

[0771] Server Functions and Operations

[0772] 1. Information gathering

[0773] The server periodically collects market information from data sources, such as news APIs, corporate research reports, and public databases, and stores the information in an internal database. This allows you to always have access to the latest market information.

[0774] 2. Data Analysis

[0775] The server uses natural language processing (NLP) and text mining to analyze the collected data. For example, it extracts frequently occurring keywords from collected articles to understand market interest. This makes it possible to quickly detect changes in market trends.

[0776] 3. Generate a predictive model

[0777] The server generates a model to predict market trends based on the analysis results. Using past data, the machine learning algorithm is trained to predict future market trends. For example, predicting market size trends for the next quarter can help formulate future strategies.

[0778] 4. Real-time translation

[0779] The server translates comments made during meetings or customer interactions in real time. For example, Japanese comments can be translated into English and instantly displayed to English-speaking staff.

[0780] 5. Sentiment analysis

[0781] The server analyzes the speaker's sentiment based on the content of the comment. For example, it can classify a comment such as "This product is not very good" as negative and provide appropriate feedback.

[0782] Device features and operations

[0783] 1. Providing a user interface

[0784] The terminal provides a dashboard where users can visually check analysis and forecast results. Graphs and charts of market trends are generated and displayed to users, allowing them to intuitively grasp the information.

[0785] 2. Real-time display

[0786] The device instantly displays the translation results and sentiment analysis results sent from the server. For example, during a meeting or customer service, when a comment is translated and displayed, sentiment analysis results are also displayed at the same time.

[0787] User operations

[0788] 1. Viewing Information

[0789] Users can check market trends and analysis results in real time through their devices, and quickly grasp current market trends by looking at charts on the dashboard.

[0790] 2. Meeting progress management

[0791] Users can use the system to efficiently manage the progress of meetings and client interactions, check whether the agenda is being followed and make adjustments as necessary. For example, they can be notified if the system deviates from the agenda.

[0792] 3. Multilingual support

[0793] Even when multiple languages ​​are used during meetings or customer interactions, users can use the system's real-time translation function to understand what is being said in different languages. For example, an English-speaking user can see what is being said in Japanese translated into English in real time.

[0794] Specific examples

[0795] Technology used

[0796] Hardware: Smartphones, servers

[0797] Software: Python (textblob, googletrans, requests libraries)

[0798] Prompt Sentence Examples

[0799] If a customer says 'This product is not very good', perform sentiment analysis and output the results.

[0800] By combining these elements, it becomes possible to improve the efficiency of customer service in stores, increase customer satisfaction, and grasp market trends in real time.

[0801] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0802] Step 1:

[0803] Information gathering

[0804] The server periodically collects market information from data sources. This process retrieves the latest market data from news APIs, company research reports, public databases, etc. The input requires an API key and a search query, and the output is a dataset of news articles and reports. This data is then stored in an internal database.

[0805] Specific behavior:

[0806] 1. Send a query to the News API.

[0807] 2. Get the news article data returned as a response.

[0808] 3. The acquired data is stored in an internal database.

[0809] Step 2:

[0810] Data analysis

[0811] The server analyzes the collected data. Using natural language processing (NLP) and text mining, it extracts frequently occurring keywords from articles and understands market interest. The data collected in step 1 is required as input, and the extracted frequently occurring keywords and their frequency of appearance are obtained as output.

[0812] Specific behavior:

[0813] 1. Analyze the collected data using text mining tools.

[0814] 2. Extract frequently occurring keywords and calculate their frequency of occurrence.

[0815] 3. Compile the extracted keywords and their frequency into a report.

[0816] Step 3:

[0817] Generate predictive models

[0818] The server generates a model to predict market trends based on the analysis results. It uses past data to train a machine learning algorithm to predict future market trends. The inputs are past data and analysis results, and the output is a prediction of future market trends.

[0819] Specific behavior:

[0820] 1. Collect historical data and analysis results.

[0821] 2. Train the model using machine learning algorithms.

[0822] 3. Use the trained model to predict future market trends.

[0823] Step 4:

[0824] Real-time translation

[0825] The server translates customer utterances in real time. For example, Japanese utterances can be translated into English and instantly displayed to English-speaking staff. This process requires the customer's utterance as input and the translation result as output.

[0826] Specific behavior:

[0827] 1. Get what your customers say.

[0828] 2. Translate the speech through the translation API.

[0829] 3. The translated results are sent to the device and displayed.

[0830] Step 5:

[0831] sentiment analysis

[0832] The server performs sentiment analysis on customer comments. For example, it classifies a comment like "This product is not very good" as negative. The input is the customer's comment, and the output is the result of the sentiment analysis.

[0833] Specific behavior:

[0834] 1. Get what your customers say.

[0835] 2. Analyze the sentiment of statements using NLP technology.

[0836] 3. The results of the sentiment analysis are sent to the device and displayed.

[0837] Step 6:

[0838] Providing a user interface

[0839] The terminal provides a user interface and displays a dashboard for users to visually check the analysis results and prediction results. This process requires data sent from the server as input, and generates a dashboard that users can view as output.

[0840] Specific behavior:

[0841] 1. Receive data from the server.

[0842] 2. Generate a dashboard.

[0843] 3. Display analysis and prediction results.

[0844] Step 7:

[0845] Real-time display

[0846] The device displays translation results and sentiment analysis results in real time. Data sent from the server is required as input, and a screen that the user can view in real time is generated as output.

[0847] Specific behavior:

[0848] 1. Receive data from the server.

[0849] 2. Display on the screen in real time.

[0850] 3. Users can check the results on the spot.

[0851] Step 8:

[0852] Viewing information

[0853] Users can check market trends and analysis results in real time through their devices. This process requires dashboard data as input, and users can quickly grasp the information as output.

[0854] Specific behavior:

[0855] 1. Navigate the dashboard to find the information you need.

[0856] 2. View various graphs and charts.

[0857] 3. Filter the information as needed.

[0858] Step 9:

[0859] Meeting progress management

[0860] Users use the system to efficiently manage the progress of meetings and customer interactions. The system requires an agenda as input and provides progress notifications as output.

[0861] Specific behavior:

[0862] 1. Set the agenda.

[0863] 2. Monitor the progress of meetings and interactions.

[0864] 3. Receive notifications when you deviate from progress.

[0865] Step 10:

[0866] Multilingual support

[0867] Users can use real-time translation to understand utterances in different languages. An utterance is required as input, and a translation result is obtained as output.

[0868] Specific behavior:

[0869] 1. Get the statement.

[0870] 2. Translate the speech through the translation API.

[0871] 3. The translation results are displayed on the screen.

[0872] 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.

[0873] This invention combines a system that manages the progress of web conferences, performs real-time translation, analyzes emotions, and predicts market trends with an emotion engine that recognizes user emotions. Below, we will explain an embodiment of this system.

[0874] System Configuration

[0875] This system consists of a server, a terminal, a user, and an emotion engine. The server performs the main data processing and analysis, the terminal provides the user interface, and the user operates the system. The emotion engine recognizes and analyzes the user's emotions and feeds the results back to the system.

[0876] Server Functions and Operations

[0877] 1. Information gathering

[0878] The server periodically collects information about the web conferencing market from multiple data sources, such as news APIs, company research reports, public databases, etc. For example, once a day, the server retrieves the latest market articles from the news API and stores them in its internal database.

[0879] 2. Data Analysis

[0880] The server cleans the collected data and analyzes it using natural language processing technology and text mining. For example, the server extracts frequently appearing keywords from the collected articles to understand market interest.

[0881] 3. Generate a predictive model

[0882] The server generates a model to predict market trends based on the analysis results. It uses past data to train a machine learning algorithm to predict future market trends. For example, the server predicts the market size for the next quarter based on past data.

[0883] 4. Real-time translation

[0884] The server translates comments made during the meeting in real time and sends the translation to the terminal. For example, it translates Japanese comments into English and displays the translation results on the terminal.

[0885] 5. Sentiment analysis

[0886] The server analyzes the emotions of the speaker based on what is said during the meeting. For example, it classifies a statement such as "I'm not confident about this plan" as negative.

[0887] Device features and operations

[0888] 1. Providing a user interface

[0889] The terminal provides a dashboard that allows users to visually check the analysis and forecast results. For example, the terminal generates and displays graphs and charts of market trends to the user.

[0890] 2. Real-time display

[0891] The device instantly displays the results of real-time translation and sentiment analysis sent from the server. For example, when a comment made during a meeting is translated and displayed, the sentiment analysis results are also displayed at the same time.

[0892] Functions and operation of the Emotion Engine

[0893] 1. Emotional awareness

[0894] The emotion engine recognizes emotions by analyzing a user's tone of voice, facial recognition data, and word choice. For example, if a user is participating in a meeting through a camera, the emotion engine analyzes facial expression data to determine the user's emotion.

[0895] 2. Emotional Data Storage

[0896] The emotion engine stores the recognized emotion data, for example, the history of emotions expressed by users during a meeting, in a database for later analysis and feedback.

[0897] 3. Emotional Data Feedback

[0898] The server grasps the progress and tone of the meeting based on the emotion data obtained from the emotion engine, and dynamically adjusts the user interface. For example, the user interface displays a warning to the user if the meeting tone is biased toward a negative one.

[0899] User operations

[0900] 1. Viewing Information

[0901] Users can check market trends and analysis results in real time through their devices and simultaneously receive feedback from the emotion engine. For example, users can quickly grasp current market trends by looking at charts on the dashboard.

[0902] 2. Meeting progress management

[0903] Users use the system to efficiently manage the progress of meetings, checking whether the agenda is being followed and making adjustments as necessary. For example, users are notified when the system deviates from the agenda to focus on a sales strategy topic.

[0904] 3. Multilingual support

[0905] Even when multiple languages ​​are used during a meeting, users can use the system's real-time translation function to understand what is being said in different languages. For example, an English-speaking user can see what is being said in Japanese translated into English in real time.

[0906] 4. Use emotional feedback

[0907] Users can adjust the tone of the meeting and discussion based on feedback from the emotion engine. For example, if the meeting is heading in a negative direction, users can take measures such as actively encouraging positive opinions.

[0908] In this way, the system not only supports the efficient operation of web conferences and is a powerful tool for companies to quickly grasp market trends, but also enables more effective communication by recognizing participants' emotions and providing appropriate feedback.

[0909] The processing flow will be explained below.

[0910] Step 1:

[0911] The server periodically collects information about the web conferencing market from multiple data sources, including news APIs, company research reports, and public databases, and stores the latest information in an internal database. This process is performed automatically on a scheduled basis.

[0912] Step 2:

[0913] The server cleans the collected data by completing missing values, removing duplicate data, and removing unnecessary HTML tags and special characters from text data. This improves the quality of the data and increases the accuracy of analysis.

[0914] Step 3:

[0915] The server then uses natural language processing techniques and text mining to analyze the cleaned data, extracting key keywords and analyzing the frequency of these keywords, for example, to see if certain keywords related to market trends are increasing.

[0916] Step 4:

[0917] The server then clusters the extracted keywords and phrases using machine learning algorithms, such as the K-means clustering algorithm, to categorize the data by related topics, thereby revealing market interests.

[0918] Step 5:

[0919] The server collects historical data and uses it to train machine learning algorithms. For example, it uses the past five years of market data to generate a linear regression model to forecast market trends for the next five years. This model is then used to predict future market size and trends.

[0920] Step 6:

[0921] The server uses the trained model to predict market trends based on the analysis results. The prediction results are saved in JSON format and can be displayed through the user interface, allowing users to quickly grasp future market trends.

[0922] Step 7:

[0923] The server translates comments made during a meeting in real time. For example, if a user speaks in Japanese, it translates the comment into English in real time and sends it to the terminal. The translation result is displayed immediately, facilitating communication between participants who speak different languages.

[0924] Step 8:

[0925] The server analyzes the speaker's emotions from what is said during the meeting. The emotion engine analyzes voice tone, word choice, and facial recognition data to recognize the speaker's emotions. For example, it classifies a statement such as "I'm not confident about this plan" as negative.

[0926] Step 9:

[0927] The emotion engine stores the recognized emotion data, for example, the history of emotions expressed during a meeting, in a database for future analysis and feedback.

[0928] Step 10:

[0929] The device displays analysis results, prediction results, real-time translation, and sentiment analysis results through a user interface. For example, the device's dashboard displays market trend graphs and charts, allowing users to quickly grasp current market trends.

[0930] Step 11:

[0931] The device dynamically adjusts the content displayed in the user interface based on the emotion data acquired from the emotion engine. For example, if the tone of the meeting is biased toward negative, the user interface will display a warning to alert the user.

[0932] Step 12:

[0933] Users can view market trends and analysis results in real time through their devices, while simultaneously receiving feedback from the emotion engine, allowing them to understand the progress and tone of the meeting and make adjustments as needed.

[0934] Step 13:

[0935] Users can use the system to efficiently manage the progress of meetings, for example, by checking whether the meeting is proceeding according to the agenda and receiving notifications if the meeting deviates from the agenda, enabling smooth meeting management.

[0936] Step 14:

[0937] Users can use the system's real-time translation function to understand multilingual utterances. For example, an English-speaking user can see a Japanese utterance translated into English in real time.

[0938] In this way, this system not only improves the efficiency of web conferences and supports multiple languages, but also promotes more effective communication by using an emotion engine to recognize participants' emotions and provide appropriate feedback.

[0939] Example 2

[0940] 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."

[0941] Conventional web conferencing systems rarely offer integrated functions such as market trend forecasting, real-time translation, and sentiment analysis, making them insufficient for effective user decision-making and meeting progress. Furthermore, functions for recognizing user emotions and utilizing them in meeting progress are limited, making it difficult to respond appropriately based on participants' emotions. As a result, there are problems with reduced meeting efficiency and effectiveness.

[0942] 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.

[0943] In this invention, the server includes means for periodically collecting market information from data sources, means for analyzing the collected information, means for predicting market trends based on the analysis results, means for translating comments in real time during a conference, means for displaying the translation results on a user interface, means for analyzing the emotions of the comments, means for displaying the emotion analysis results on the user interface, means for analyzing facial recognition data and voice tone to recognize emotions, means for saving the recognized emotion data, and means for dynamically adjusting the user interface based on the emotion data. This makes it possible to efficiently manage the progress of a conference, quickly grasp market trends, and recognize users' emotions and provide appropriate feedback.

[0944] "Data Source" means an external source of information that provides information about the market.

[0945] "Means for collecting information" refers to systems and programs for periodically obtaining market information from data sources.

[0946] "Means for analyzing information" refers to systems and programs that cleanse collected data and analyze it using techniques such as natural language processing and text mining.

[0947] "Means for predicting market trends" are machine learning models and algorithms that predict future market trends based on analysis results.

[0948] "Means for translating statements made during a meeting in real time" refers to a system or program that instantly converts statements made during a meeting into a different language.

[0949] "Means for displaying the translation results on a user interface" refers to a system or program that displays the translated content on a terminal screen in real time.

[0950] A "means for analyzing the emotions of statements" is a system or program that identifies and classifies emotions based on the content of statements made during a meeting.

[0951] The "means for displaying the emotion analysis results on a user interface" refers to a system or program that displays the emotion analysis results on a terminal screen.

[0952] "Means for recognizing emotions by analyzing facial recognition data and voice tone" refers to a system or program that analyzes facial expressions and voice tone to identify a user's emotions.

[0953] The "means for storing recognized emotion data" refers to a system or program that stores analyzed emotion data in a database.

[0954] "Means for dynamically adjusting the user interface based on emotional data" refers to a system or program that changes the screen display in real time based on the user's emotional data.

[0955] This invention combines a system that manages the progress of web conferences, performs real-time translation, analyzes emotions, and predicts market trends with an emotion engine that recognizes user emotions. Below, we will explain an embodiment of this system.

[0956] System Configuration

[0957] This system consists of a server, a terminal, a user, and an emotion engine. The server performs the main data processing and analysis, the terminal provides the user interface, and the user operates the system. The emotion engine recognizes and analyzes the user's emotions and feeds the results back to the system.

[0958] Server Functions and Operations

[0959] The server performs the functions of information collection, data analysis, predictive model generation, real-time translation, and sentiment analysis, using the following software and tools:

[0960] Information gathering

[0961] The server periodically collects information about the web conferencing market from multiple data sources, such as news APIs, company research reports, public databases, etc. For example, once a day, the server retrieves the latest market articles from the news API and stores them in its internal database.

[0962] Data analysis

[0963] The server cleans the collected data and analyzes it using Python NLP libraries (NLTK, Spacy) and text mining tools. For example, the server extracts frequently occurring keywords from the collected articles to understand market interest.

[0964] Generate predictive models

[0965] The server generates a model to predict market trends based on the analysis results. It uses past data to train the model using Python machine learning libraries (scikit-learn, TensorFlow) and predicts future market trends. For example, the server predicts market size trends for the next quarter based on past data.

[0966] Real-time translation

[0967] The server uses Google's real-time translation API to translate what is said during the meeting and send it to the device. For example, it can translate Japanese comments into English and display the translation results on the device.

[0968] sentiment analysis

[0969] The server uses natural language processing technology to analyze the emotions of people speaking during meetings. For example, it classifies statements such as "I'm not confident about this plan" as negative.

[0970] Device features and operations

[0971] The terminal provides a user interface and displays analysis results, prediction results, and sentiment analysis results in real time.

[0972] Providing a user interface

[0973] The terminal provides a dashboard where users can visually check analysis and forecast results, and uses D3.js and Chart.js to generate and display graphs and charts of market trends.

[0974] Real-time display

[0975] The device instantly displays the results of real-time translation and sentiment analysis sent from the server. When speech is translated and displayed during a meeting, the sentiment analysis results are also displayed.

[0976] Functions and operation of the Emotion Engine

[0977] The emotion engine analyzes the user's voice tone and facial recognition data to recognize emotions.

[0978] Emotion recognition

[0979] The emotion engine uses OpenCV and dlib, and Google's Speech-to-Text API for voice recognition to recognize the user's emotions. For example, if a user is participating in a meeting via camera, facial expression data is analyzed to determine the user's emotions.

[0980] Storing Emotional Data

[0981] The emotion engine stores the recognized emotion data in a database (MySQL, PostgreSQL), for example, to store the history of emotions expressed during a meeting, for later analysis and feedback.

[0982] Emotional Data Feedback

[0983] The server uses the emotion data obtained from the emotion engine to grasp the progress and tone of the meeting and dynamically adjusts the user interface. For example, if the meeting tone is biased towards a negative one, it will display a warning to the user.

[0984] User operations

[0985] Users can operate the system through their terminals, view information in real time, and manage the progress of the conference.

[0986] Viewing information

[0987] Users can view market trends and analysis results in real time through their devices and receive feedback from the emotion engine. For example, they can view charts on a dashboard to understand current market trends.

[0988] Meeting progress management

[0989] Users use the system to efficiently manage the progress of meetings, check whether the agenda is being followed and make adjustments as necessary, for example, receive notifications if the agenda is deviating.

[0990] Multilingual support

[0991] Users can use the system's real-time translation feature to understand statements in different languages, for example, an English-speaking user can see a Japanese statement translated into English in real time.

[0992] Utilizing emotional feedback

[0993] Users can adjust the tone of the meeting and discussion based on feedback from the emotion engine. For example, if the meeting is heading in a negative direction, users can take measures such as actively encouraging positive opinions.

[0994] Specific examples and prompts for the generative AI model

[0995] Example 1: A user opens a dashboard and sees a graph of the latest market trends. The graph displays a 10% increase in market growth forecast for the next quarter compared to the previous year.

[0996] Example 2: During a meeting, someone says in Japanese, "We need to introduce a new product line." This is translated into English in real time and displayed as, "We need to introduce a new product line."

[0997] Example prompt 1:

[0998] "This system will tell us about the latest trends in the market."

[0999] Example prompt 2:

[1000] "Generate a model that predicts market trends for the next quarter."

[1001] Example prompt 3:

[1002] "Please translate what is being said in a meeting in real time and display the results."

[1003] As described above, this system supports efficient web conference management and is a powerful tool for companies to quickly grasp market trends. Furthermore, it recognizes participants' emotions and provides appropriate feedback, enabling more effective communication.

[1004] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1005] Step 1:

[1006] Information gathering

[1007] The server regularly collects information about the web conferencing market from multiple data sources, including news APIs, corporate research reports, and public databases.

[1008] Input: News API endpoint URL, API key

[1009] Data processing: The server uses the API key to send an HTTP request to the news API to retrieve new articles.

[1010] Output: Store the retrieved market articles in an internal database.

[1011] Specific operation: The server sets up a scheduled task to retrieve the latest information from the news API at a specific time every day and store it in a database.

[1012] Step 2:

[1013] Data analysis

[1014] The server cleans the collected data and analyzes it using natural language processing libraries (e.g., NLTK, Spacy) and text mining tools.

[1015] Input: Unparsed article data in the internal database

[1016] Data processing: Remove unnecessary information from the articles (HTML tags, spaces, etc.), tokenize the text, and extract keywords.

[1017] Output: Analysis results (keywords, phrases, etc.) are saved in a database.

[1018] Specific operation: The server runs the cleansing script to clean the raw data, and then uses NLP algorithms to extract keywords.

[1019] Step 3:

[1020] Generate predictive models

[1021] The server uses historical data to generate models that predict market trends using Python machine learning libraries (e.g., scikit-learn, TensorFlow).

[1022] Input: Analysis result database, historical market data

[1023] Data processing: Split the dataset into a training set and a test set, and apply an algorithm to train the model.

[1024] Output: A trained predictive model

[1025] Specific operation: The server periodically runs model training jobs and deploys the generated models to the prediction engine.

[1026] Step 4:

[1027] Real-time translation

[1028] The server uses Google's real-time translation API to translate what is said during the meeting and send it to the device.

[1029] Input: Audio data during the meeting

[1030] Data processing: Convert the voice data into text and call the translation API to obtain the translated text.

[1031] Output: Translation result text

[1032] Specific operation: The server performs speech recognition in real time, sends a request to the translation API, and sends the resulting translation results to the device.

[1033] Step 5:

[1034] sentiment analysis

[1035] The server uses natural language processing technology to analyze the emotions of speakers from what is said during the meeting.

[1036] Input: Text data during the meeting

[1037] Data processing: Text data is input into a sentiment analysis model and sentiment labels are assigned.

[1038] Output: Sentiment analysis label (e.g. positive, negative, neutral)

[1039] Specific operation: The server uses a sentiment analysis model to classify comments made during the meeting in real time and saves the analysis results.

[1040] Step 6:

[1041] Providing a user interface

[1042] The device provides a dashboard that allows users to visually check analysis results, prediction results, and sentiment analysis results.

[1043] Input: Analysis results, prediction results, and sentiment analysis results sent from the server

[1044] Data processing: Converts received data into graph or chart format and displays it.

[1045] Output: Visual information on a dashboard

[1046] Specific operation: The device uses D3.js and Chart.js to display and update data in real time.

[1047] Step 7:

[1048] Real-time display

[1049] The device instantly displays the results of real-time translation and sentiment analysis sent from the server.

[1050] Input: Real-time translation results, sentiment analysis results

[1051] Data processing: The received data is immediately displayed and updated.

[1052] Output: On-screen translated text and sentiment labels

[1053] Specific behavior: When the device receives new data, it updates the current display, providing the user with information in real time.

[1054] Step 8:

[1055] emotion recognition

[1056] The emotion engine uses OpenCV and dlib to analyze facial expression data and Google's Speech-to-Text API to analyze voice tones to recognize emotions.

[1057] Input: Camera feed, audio feed

[1058] Data processing: Analyze facial expression data and voice tone to classify emotions.

[1059] Output: Emotion identification result

[1060] Specific operation: The emotion engine analyzes video and audio data in real time and stores the recognized emotions in a database.

[1061] Step 9:

[1062] Storing Emotional Data

[1063] The emotion engine stores the recognized emotion data in a database (e.g., MySQL, PostgreSQL).

[1064] Input: Emotion identification result

[1065] Data processing: Converting the emotion data into an appropriate format and inserting it into the database.

[1066] Output: Emotion data stored in a database

[1067] Specific operation: The emotion engine periodically writes emotion data to the database.

[1068] Step 10:

[1069] Emotional Data Feedback

[1070] The server dynamically adjusts the user interface based on the emotion data obtained from the emotion engine.

[1071] Input: Emotion data

[1072] Data processing: Analyzes emotional data and instructs UI changes.

[1073] Output: Updated user interface

[1074] Specific operation: The server analyzes the emotional data and displays a warning in negative situations and highlights positive situations.

[1075] The above is a description of the specific processing steps of the program for this system. Each step works together to provide useful information to users in real time and to efficiently manage the progress of the conference.

[1076] (Application example 2)

[1077] 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."

[1078] Conventional food delivery services lack sufficient communication between delivery personnel and customers, making it difficult to provide real-time feedback to improve customer satisfaction. Furthermore, they lack multilingual capabilities, making it difficult to communicate smoothly with customers who speak different languages. Furthermore, they do not properly recognize customer emotions and improve services based on them, limiting the improvement of service quality. To address these issues, a system with more advanced communication support and emotion analysis capabilities is needed.

[1079] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1080] In this invention, the server includes means for periodically collecting market information from a data source, means for analyzing the collected information, means for predicting market trends based on the analysis results, means for displaying the prediction results through a user interface, means for collecting voices of delivery personnel and customers, means for converting the collected voices into text, means for translating the converted text in real time, means for analyzing customer emotions, means for saving analyzed emotion data, and means for providing feedback based on the emotion data. This enables real-time, multilingual communication during delivery, and by immediately understanding customer emotions and providing feedback, it is possible to improve service quality and customer satisfaction.

[1081] A "data source" is an external information provider from which market information can be obtained.

[1082] A "market trend" is a collection of data that describes the current state and expected future changes in a particular market.

[1083] A "user interface" is an interface consisting of a display device and an input device that allows a user to interact with a system.

[1084] The "means for collecting voices of delivery personnel and customers" refers to a device or method for collecting voice data of interactions between delivery personnel and customers during the delivery process.

[1085] A "means for converting speech to text" is a device or method that analyzes collected speech data and converts it into text format data.

[1086] A "means for real-time text translation" is a device or method for instantly translating text data into another language.

[1087] The "means for analyzing customer emotions" refers to a device or method for analyzing emotions using customer voice and facial expression data.

[1088] "Means for saving analyzed emotion data" refers to a device or method for saving analyzed emotion data in a database or the like.

[1089] A "means for providing feedback based on emotional data" is a device or method that provides real-time service adjustments or advice based on stored emotional data.

[1090] The system embodying this invention is realized by the following main components: a server, a terminal, a delivery person, a customer, and an emotion engine. The server processes and analyzes data, the terminal provides a user interface through which delivery people and customers operate the system, and the emotion engine recognizes and analyzes the customer's emotions and feeds the results back to the system.

[1091] Server Functions and Operations

[1092] 1. Information gathering

[1093] The server periodically collects market information from multiple data sources, such as news APIs, company research reports, public databases, etc. For example, once a day, the server retrieves the latest market articles from the news API and stores them in its internal database.

[1094] 2. Data Analysis

[1095] The server cleans the collected data and analyzes it using natural language processing technology and text mining. For example, the server extracts frequently appearing keywords from the collected articles to understand market interest.

[1096] 3. Market Trend Forecast

[1097] The server generates a model to predict market trends based on the analysis results. It uses past data to train a machine learning algorithm to predict future market trends. For example, the server predicts the market size for the next quarter based on past data.

[1098] 4. Real-time translation

[1099] The server translates the conversation between the delivery person and the customer in real time and sends it to the terminal. For example, it translates Japanese statements into English and displays the translation results on the terminal.

[1100] 5. Emotion analysis

[1101] The server analyzes the content and tone of the conversation between the delivery person and the customer to recognize emotions. For example, if a customer says, "Thank you, that was very helpful," it classifies the comment as positive.

[1102] Device features and operations

[1103] 1. Providing a user interface

[1104] The terminal provides a dashboard where delivery personnel and customers can visually view analytics and feedback, such as graphs of delivery satisfaction and market trends.

[1105] 2. Real-time display

[1106] The device instantly displays the results of real-time translation and sentiment analysis sent from the server. For example, when a delivery person's words are translated and displayed, the sentiment analysis results are also displayed.

[1107] Functions and operation of the Emotion Engine

[1108] 1. Emotional awareness

[1109] The emotion engine recognizes emotions by analyzing the customer's voice tone and facial expression data. For example, if a customer accepts a delivery via camera, the emotion engine analyzes facial expression data to determine the emotion.

[1110] 2. Emotional Data Storage

[1111] The emotion engine stores the recognized emotion data, for example, the history of emotions expressed by customers during delivery, in a database for later analysis and feedback.

[1112] 3. Emotional Data Feedback

[1113] The server grasps the delivery status and customer satisfaction level based on the emotion data obtained from the emotion engine, and dynamically adjusts the user interface. For example, the user interface displays a warning to the delivery person if the customer is in a negative state.

[1114] User operations

[1115] 1. Viewing Information

[1116] Users can check market trends and analysis results in real time through their devices and simultaneously receive feedback from the emotion engine. For example, users can quickly grasp current market trends by looking at charts on the dashboard.

[1117] 2. Communication support

[1118] Users can use the system to facilitate communication during deliveries, using the real-time translation function between different languages ​​to ensure smooth delivery.

[1119] 3. Use emotional feedback

[1120] Users can improve the quality of their deliveries based on feedback from the emotion engine. For example, if a customer has a negative reaction, users can take immediate action to improve the quality of their deliveries.

[1121] Examples of specific examples and prompts

[1122] Examples:

[1123] If the delivery person only speaks Japanese and the customer only speaks English

[1124] Delivery Person: "Hello, here's a delivery for you."

[1125] English translation example: "Hello, I have a delivery for you."

[1126] Customer response (sentiment analysis results): Customer: "Thank you! This is perfect!" → Positive evaluation

[1127] Application-generated feedback: Smart glasses display to delivery driver, "We've confirmed that the customer is satisfied."

[1128] Example prompt sentence:

[1129] Customer says: "Thank you! This is perfect!"

[1130] Prompt to the sentiment analysis engine: "Analyze the customer's voice and determine whether it is positive or negative."

[1131] Output: "Positive"

[1132] Prompt the generative AI model: "Analyze the customer's voice and generate emotional feedback."

[1133] Example output: "The customer appears to be very satisfied. We will leave positive feedback."

[1134] In this way, the present invention supports smooth communication during delivery and improves real-time customer satisfaction.

[1135] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1136] Step 1:

[1137] The server collects the voices of the delivery person and the customer using the smartphone's microphone, and the collected voice data is sent directly to the next processing step.

[1138] Input: Audio data

[1139] Output: Raw audio data

[1140] What it does: The delivery person's smartphone captures the conversation with the customer.

[1141] Step 2:

[1142] The server converts the collected voice data into text data using the Google Cloud Speech-to-Text API, which converts the speech obtained from the voice into text format.

[1143] Input: Raw audio data

[1144] Output: Text data

[1145] Specific operation: The server sends the audio data to Google Cloud and receives it as text data.

[1146] Step 3:

[1147] The server uses the Google Cloud Translation API to translate the generated text data into other languages ​​in real time, and the translated data is displayed through the user interface.

[1148] Input: Text data

[1149] Output: Translated text data

[1150] Specific operation: The server sends text data to the Google Cloud Translation API and receives the translated text data.

[1151] Step 4:

[1152] The server uses the Microsoft Azure Emotion API to analyze the translated text data and voice tone to recognize the customer's emotions, which are then used for immediate feedback.

[1153] Input: Translated text data, audio tone

[1154] Output: Sentiment data (positive, negative, etc.)

[1155] Specific operation: The server sends text data and audio tones to Microsoft Azure and receives emotion data.

[1156] Step 5:

[1157] The server stores the analyzed emotion data in a database, which is then used to analyze market trends and provide feedback.

[1158] Input: Emotion data

[1159] Output: Stored emotion data

[1160] Specific operation: The server stores the emotion data in an internal database.

[1161] Step 6:

[1162] The server provides real-time feedback based on the emotion data and displays it on the user interface, allowing the delivery person to understand the customer's satisfaction level and take necessary action.

[1163] Input: Stored emotion data

[1164] Output: Feedback displayed in the user interface

[1165] Specific operation: The server analyzes the emotional data, generates positive or negative feedback, and sends it to the device for display.

[1166] Step 7:

[1167] Through the user interface, users can check market trends and feedback results in real time and take action as needed, for example, identifying areas for improvement for the next delivery.

[1168] Input: Feedback and market trend data displayed in the user interface

[1169] Output: User response or action

[1170] Specific actions: The user checks the device dashboard and takes the necessary action.

[1171] Although I have summarized it in a simple manner, the above invention is implemented smoothly by the detailed processes of collection, conversion, translation, recognition, storage, feedback, and response at each step.

[1172] 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.

[1173] 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.

[1174] 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.

[1175] [Third embodiment]

[1176] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1177] 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.

[1178] 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).

[1179] 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.

[1180] 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.

[1181] 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).

[1182] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1183] 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.

[1184] 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.

[1185] 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.

[1186] 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.

[1187] 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."

[1188] The present invention relates to a system for managing the progress of a web conference, performing real-time translation, analyzing emotions, and forecasting market trends. Hereinafter, an embodiment of this system will be described.

[1189] System Configuration

[1190] This system consists of a server, terminals, and users. The server performs the main data processing and analysis, while the terminals provide the user interface and the users operate the system. The server also obtains information from various data sources and performs analysis and predictions.

[1191] Server Functions and Operations

[1192] 1. Information gathering

[1193] The server regularly collects information about the web conferencing market from multiple data sources, including news APIs, corporate research reports, and public databases.

[1194] For example, once a day, the server retrieves the latest market articles from a news API and stores them in an internal database.

[1195] 2. Data Analysis

[1196] The server uses natural language processing technology and text mining to analyze the collected data.

[1197] For example, the server extracts frequently occurring keywords from collected articles to understand market interest.

[1198] 3. Generate a predictive model

[1199] The server generates a model to predict market trends based on the analysis results, and uses historical data to train machine learning algorithms to predict future market trends.

[1200] For example, the server predicts the market size trends for the next quarter based on past data.

[1201] 4. Real-time translation

[1202] The server translates what is said during the meeting in real time and sends it to the terminal.

[1203] For example, a Japanese utterance is translated into English and displayed to an English-speaking user.

[1204] 5. Sentiment analysis

[1205] The server analyzes the emotions of the speaker based on the content of what was said during the meeting.

[1206] For example, the server might classify a statement such as "I'm not confident in this plan" as negative.

[1207] Device features and operations

[1208] 1. Providing a user interface

[1209] The device provides a dashboard that allows users to visually check analysis and prediction results.

[1210] For example, the terminal may generate and display graphs and charts of market trends to the user.

[1211] 2. Real-time display

[1212] The device instantly displays the results of real-time translation and sentiment analysis sent from the server.

[1213] For example, comments made during a meeting are translated and displayed, along with the results of sentiment analysis.

[1214] User operations

[1215] 1. Viewing Information

[1216] Users can check market trends and analysis results in real time through their devices.

[1217] For example, users can view charts on a dashboard to quickly understand current market trends.

[1218] 2. Meeting progress management

[1219] Users can use the system to efficiently manage the progress of meetings, checking whether the agenda is being followed and making adjustments as necessary.

[1220] For example, the user is notified when the system is distracted from the agenda to focus on a sales strategy agenda.

[1221] 3. Multilingual support

[1222] Even if multiple languages ​​are used during a meeting, users can use the system's real-time translation function to understand what is being said in different languages.

[1223] For example, an English-speaking user can see Japanese utterances translated into English in real time.

[1224] In this way, the system supports the efficient operation of web conferences and becomes a powerful tool for companies to quickly grasp market trends.

[1225] The processing flow will be explained below.

[1226] Step 1:

[1227] The server periodically collects information about the web conferencing market from multiple data sources, specifically, retrieving the latest market articles from news APIs, and relevant data from corporate research reports and public databases, and stores this information in an internal database.

[1228] Step 2:

[1229] The server cleans the collected data, for example, by completing missing values ​​and removing duplicate data, and also by removing unnecessary HTML tags and special characters from text data to improve the quality of the data.

[1230] Step 3:

[1231] The server analyzes the cleaned data. Specifically, it performs text mining using natural language processing technology to extract important market keywords. It also performs frequency analysis of the extracted keywords to identify trends.

[1232] Step 4:

[1233] The server uses machine learning algorithms to cluster keywords and phrases, for example applying the K-means clustering algorithm to categorize the data by related topics, which reveals market interests.

[1234] Step 5:

[1235] The server collects historical data and uses it to train machine learning algorithms, for example using the past five years of market data to generate a linear regression model to predict market trends over the next five years.

[1236] Step 6:

[1237] The server uses the trained model to predict market trends based on the analysis results, and the prediction results are formatted in a way that is easy for users to understand and stored in an internal database.

[1238] Step 7:

[1239] The server translates comments made during the meeting in real time. For example, it translates Japanese comments into English and sends the translation results to the terminal. This enables multilingual support.

[1240] Step 8:

[1241] The server analyzes the emotions of the speaker based on what is said during the meeting. For example, it classifies a statement such as "I'm not confident about this plan" as negative and generates a sentiment analysis result.

[1242] Step 9:

[1243] The device displays analysis results, prediction results, real-time translation, and sentiment analysis results through a user interface. For example, the device's dashboard displays market trend graphs and charts, allowing users to understand current market trends and the progress of meetings.

[1244] Step 10:

[1245] Users can check market trends and analysis results in real time through their devices, efficiently manage the progress of meetings, and use the system's real-time translation function to understand statements in multiple languages.

[1246] Example 1

[1247] 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."

[1248] In today's business environment, fast and accurate market trend forecasting is crucial for maintaining a company's competitive edge. However, collecting and properly analyzing information from diverse data sources can be challenging, particularly due to language barriers and the difficulty of accurately understanding the speaker's emotions during meetings. Furthermore, there are few systems that integrate real-time translation and sentiment analysis, which can reduce the efficiency of meetings.

[1249] 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.

[1250] In this invention, the server includes means for periodically collecting market information from multiple data sources such as news APIs, research reports, and public databases, means for analyzing the collected data using natural language processing technology to extract frequently occurring keywords and sentiments, and means for predicting market trends using machine learning algorithms based on the analysis results, thereby enabling rapid and accurate understanding of market trends.

[1251] The system also includes a means for converting speech during a conference into text, a means for translating the converted text in real time, and a means for displaying the translation results on a user interface, thereby enabling smooth communication across language barriers.

[1252] The system also includes a means for analyzing the content of comments made during a meeting and classifying the emotions of the comments, and a means for displaying the real-time emotion analysis results on a user interface, which allows for accurate understanding of the emotions of the speakers and improves the efficiency of the meeting.

[1253] A "news API" is an application program interface for automatically retrieving news articles and information published on the web.

[1254] A "research report" is a document that compiles the results of specialized research on a market, industry, product, etc.

[1255] A "public database" is a collection of data provided by a government agency or public institution that is open to the public.

[1256] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[1257] A "machine learning algorithm" is an algorithm that automatically learns patterns based on data and makes predictions and classifications.

[1258] A "user interface" refers to the screen and operating means that allow a user to interact with a system.

[1259] "Speech recognition" is a technology in which a computer converts human speech into text data.

[1260] "Real-time translation" is a technology that translates conversations and text into other languages ​​in real time.

[1261] "Sentiment analysis" is a technology that automatically analyzes emotional states from text data and classifies them as positive, negative, neutral, etc.

[1262] This invention relates to a system for managing the progress of web conferences, performing real-time translation, analyzing emotions, and forecasting market trends. This system is composed of a server, terminals, and users. A specific embodiment of this system will be described below.

[1263] Server Functions and Operations

[1264] The server is responsible for the main data processing and analysis functions. First, the server accesses multiple data sources, such as news APIs, research reports, and public databases. These APIs are accessed using news API keys and corporate research report access keys. The server periodically collects information from these data sources and stores it in an internal database. For example, every morning at 9:00, the server retrieves the latest articles about the web conferencing market from the news API and stores them in the database.

[1265] The server then analyzes the collected data using natural language processing techniques (e.g., NLTK, spaCy). It extracts frequently occurring keywords from the collected articles to understand market interest. It also uses sentiment analysis algorithms (e.g., TextBlob, VADER) to classify the content of the articles as positive, negative, or neutral. For example, it identifies the phrase "I'm not confident in this plan" as a negative sentiment.

[1266] The analyzed data is used as training data to predict market trends using machine learning algorithms. The server uses the past data to generate a model that predicts future market trends. The model trained by the machine learning algorithm predicts, for example, the market size for the next quarter.

[1267] Furthermore, to provide a real-time translation function, the server converts the conference voice into text using a speech recognition service (e.g., Google Speech-to-Text API) and translates the acquired text into a specified language using a translation service (e.g., Google Translate API). For example, Japanese statements may be translated into English and sent to the terminal for display to an English-speaking user.

[1268] Device features and operations

[1269] The device provides a dashboard that allows users to visually check analysis and forecast results. Web technologies such as HTML, CSS, and JavaScript are used for the user interface. For example, the device generates graphs and charts of market trends and displays them to the user. It also has the ability to display real-time translation results and sentiment analysis results on the conference screen. For example, the translation result of "Hello" can be displayed as "Hello," and the sentiment analysis result (negative) of the statement "I'm not confident in this plan" can be displayed at the same time.

[1270] User operations

[1271] Users can check market trends and analysis results in real time through their devices. They can quickly grasp current market trends by looking at market trend graphs on the dashboard. Users can also use the system to efficiently manage meeting progress, checking whether the meeting is proceeding according to the agenda and making adjustments as necessary. For example, users can be notified if the system deviates from the agenda in order to focus on the sales strategy topic. In addition, the real-time translation function allows users to understand statements in different languages. For example, an English-speaking user can see Japanese statements translated into English in real time.

[1272] Examples of prompt statements

[1273] Below are some examples of prompt sentences.

[1274] 1. Information Collection:

[1275] "Do you have sample code for a news API that retrieves the latest articles about the web conferencing market?"

[1276] 2. Data Analysis:

[1277] "Can you please give me some Python code to extract frequently occurring keywords from news articles about the web conferencing market?"

[1278] 3. Generate predictive models:

[1279] "I'd like to build a machine learning model to predict the market size for the next quarter based on historical market data. Can you give me some advice?"

[1280] 4. Real-time translation:

[1281] "Please tell me an API for translating Japanese to English in real time."

[1282] 5. Sentiment analysis:

[1283] "Please tell me a Python library that can analyze emotions from speech content."

[1284] 6. Progress management:

[1285] "I want to create a script to manage the progress of a meeting. Can you tell me the relevant APIs and libraries?"

[1286] In this way, the system helps to efficiently manage web conferences and is a powerful tool for companies to quickly grasp market trends.

[1287] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1288] The flow of this system's program processing

[1289] Information gathering steps:

[1290] Step 1:

[1291] The server accesses the news API using the API key and sends a request to get the "latest articles about the web conferencing market." The input is the API key and request parameters, and the output is the latest article data.

[1292] Specific operation: The server calls the news API on a set schedule every morning at 9:00 and analyzes the JSON format data received as a response.

[1293] Step 2:

[1294] The server stores the retrieved news article data in an internal database. The input is news article data in JSON format, and the output is the articles stored in the database.

[1295] Specific operation: The server breaks down the retrieved article data into each field (e.g., title, content, publication date) and inserts it into the database using an SQL query.

[1296] Data analysis steps:

[1297] Step 1:

[1298] The server reads the stored news article data for analysis using natural language processing techniques. The input is the article data stored in the database, and the output is a tokenized word sequence.

[1299] Specific operation: The server retrieves article data in text format and tokenizes it using a natural language processing library (e.g., NLTK, spaCy).

[1300] Step 2:

[1301] The server extracts frequent keywords from the tokenized word string. The input is the tokenized word string, and the output is a list of frequent keywords.

[1302] Specific operation: The server analyzes the tokenized word string, calculates the frequency of each word, and selects particularly important keywords.

[1303] Step 3:

[1304] The server analyzes the content of articles using a sentiment analysis algorithm and classifies them as positive, negative, or neutral. The input is the text data of the article, and the output is the sentiment label (positive, negative, or neutral).

[1305] How it works: The server uses a sentiment analysis library such as TextBlob or VADER to calculate a sentiment score for each sentence.

[1306] Steps for generating a predictive model:

[1307] Step 1:

[1308] The server preprocesses the analyzed data as training data for a machine learning model. The input is the analyzed article data and a list of frequently occurring keywords, and the output is a training dataset.

[1309] Specific operation: The server quantifies the data and converts it into a format that can be used by the machine learning model (e.g., normalization, feature extraction).

[1310] Step 2:

[1311] The server uses machine learning algorithms to train models that predict market trends, where the input is a pre-processed training dataset and the output is a predictive model.

[1312] What it does: The server applies algorithms such as time series analysis and regression analysis to train a model using the data.

[1313] Real-time translation steps:

[1314] Step 1:

[1315] The server captures the voice during the conference and sends it to the speech recognition service to convert it into text. The input is real-time voice data, and the output is text data of the speech recognition results.

[1316] What it does: The server captures the audio stream in real time and sends it to the Google Speech-to-Text API to get the text data.

[1317] Step 2:

[1318] The server translates the text obtained by speech recognition into the specified language using a translation service. The input is the text data of the speech recognition result, and the output is the text data of the translation result.

[1319] Specific operation: The server uses the Google Translate API to translate the speech recognition results in real time and convert them into the specified language.

[1320] Sentiment analysis steps:

[1321] Step 1:

[1322] The server analyzes the content of speech during a meeting in real time and classifies the speaker's emotions. The input is the text data of the meeting audio, and the output is an emotion label (positive, negative, neutral).

[1323] Specific operation: The server analyzes the text obtained from the speech recognition results, calculates the emotion score using libraries such as TextBlob and VADER, and assigns emotion labels.

[1324] User operation steps:

[1325] Step 1:

[1326] Users can check the analysis and prediction results through a dashboard on their device. The input is the analysis and prediction results sent from the server, and the output is the graphs and charts displayed on the dashboard.

[1327] Specific operation: The user sees graphs and charts of market trends updated in real time on the device screen.

[1328] Step 2:

[1329] Users use the system to manage the progress of a conference. The input is real-time information about the progress of the conference, and the output is actions based on the user's decisions.

[1330] Specific operation: The user checks whether the meeting is proceeding according to the agenda and instructs the speaker to make adjustments if necessary.

[1331] Through the above processing steps, this system supports the efficient operation of web conferences and provides users with a powerful tool for timely understanding of market trends.

[1332] (Application example 1)

[1333] 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."

[1334] In modern store operations, serving customers who speak different languages ​​and understanding their immediate satisfaction are key issues. Insufficient multilingual support can lead to dissatisfaction among customers, leading to more negative feedback. It is also necessary to analyze customer sentiment in real time and respond quickly to improve customer satisfaction.

[1335] 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.

[1336] In this invention, the server includes means for periodically collecting market information from a data source, means for analyzing the collected information, means for predicting market trends based on the analysis results, means for displaying the prediction results through a user interface, means for real-time translation of customer responses, means for displaying the translation results on the user interface, means for sentiment analysis of customer comments, and means for displaying the sentiment analysis results on the user interface. This makes it possible to efficiently respond to customers who speak different languages, analyze customer sentiment in real time, and immediately provide appropriate responses, thereby improving customer satisfaction.

[1337] A "data source" is an external or internal source from which information is obtained.

[1338] "Means for periodically collecting information" are technological means for collecting data on the market at regular intervals.

[1339] "Means of analyzing information" refers to the technical means used to analyze collected data and extract meaning and trends.

[1340] "Means for predicting market trends" are technical means for predicting future market movements from analysis results.

[1341] A "user interface" is a screen or input device that allows a user to interact with a system.

[1342] A "translation tool" is a technical tool for converting an utterance in one language into another language.

[1343] "Means for emotion analysis" refers to a technical means for analyzing emotions from the content of statements and recognizing emotions such as positive and negative.

[1344] "Display means" refers to the technical means for visually presenting analysis results, translation results, etc. to the user.

[1345] "Customer response" refers to the activities of store staff to communicate with customers.

[1346] The system for implementing the present invention mainly comprises a server, a terminal, and a user. The server processes and analyzes data, the terminal provides a user interface, and the user operates the system.

[1347] Server Functions and Operations

[1348] 1. Information gathering

[1349] The server periodically collects market information from data sources, such as news APIs, corporate research reports, and public databases, and stores the information in an internal database. This allows you to always have access to the latest market information.

[1350] 2. Data Analysis

[1351] The server uses natural language processing (NLP) and text mining to analyze the collected data. For example, it extracts frequently occurring keywords from collected articles to understand market interest. This makes it possible to quickly detect changes in market trends.

[1352] 3. Generate a predictive model

[1353] The server generates a model to predict market trends based on the analysis results. Using past data, the machine learning algorithm is trained to predict future market trends. For example, predicting market size trends for the next quarter can help formulate future strategies.

[1354] 4. Real-time translation

[1355] The server translates comments made during meetings or customer interactions in real time. For example, Japanese comments can be translated into English and instantly displayed to English-speaking staff.

[1356] 5. Sentiment analysis

[1357] The server analyzes the speaker's sentiment based on the content of the comment. For example, it can classify a comment such as "This product is not very good" as negative and provide appropriate feedback.

[1358] Device features and operations

[1359] 1. Providing a user interface

[1360] The terminal provides a dashboard where users can visually check analysis and forecast results. Graphs and charts of market trends are generated and displayed to users, allowing them to intuitively grasp the information.

[1361] 2. Real-time display

[1362] The device instantly displays the translation results and sentiment analysis results sent from the server. For example, during a meeting or customer service, when a comment is translated and displayed, sentiment analysis results are also displayed at the same time.

[1363] User operations

[1364] 1. Viewing Information

[1365] Users can check market trends and analysis results in real time through their devices, and quickly grasp current market trends by looking at charts on the dashboard.

[1366] 2. Meeting progress management

[1367] Users can use the system to efficiently manage the progress of meetings and client interactions, check whether the agenda is being followed and make adjustments as necessary. For example, they can be notified if the system deviates from the agenda.

[1368] 3. Multilingual support

[1369] Even when multiple languages ​​are used during meetings or customer interactions, users can use the system's real-time translation function to understand what is being said in different languages. For example, an English-speaking user can see what is being said in Japanese translated into English in real time.

[1370] Specific examples

[1371] Technology used

[1372] Hardware: Smartphones, servers

[1373] Software: Python (textblob, googletrans, requests libraries)

[1374] Prompt Sentence Examples

[1375] If a customer says 'This product is not very good', perform sentiment analysis and output the results.

[1376] By combining these elements, it becomes possible to improve the efficiency of customer service in stores, increase customer satisfaction, and grasp market trends in real time.

[1377] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1378] Step 1:

[1379] Information gathering

[1380] The server periodically collects market information from data sources. This process retrieves the latest market data from news APIs, company research reports, public databases, etc. The input requires an API key and a search query, and the output is a dataset of news articles and reports. This data is then stored in an internal database.

[1381] Specific behavior:

[1382] 1. Send a query to the News API.

[1383] 2. Get the news article data returned as a response.

[1384] 3. The acquired data is stored in an internal database.

[1385] Step 2:

[1386] Data analysis

[1387] The server analyzes the collected data. Using natural language processing (NLP) and text mining, it extracts frequently occurring keywords from articles and understands market interest. The data collected in step 1 is required as input, and the extracted frequently occurring keywords and their frequency of appearance are obtained as output.

[1388] Specific behavior:

[1389] 1. Analyze the collected data using text mining tools.

[1390] 2. Extract frequently occurring keywords and calculate their frequency of occurrence.

[1391] 3. Compile the extracted keywords and their frequency into a report.

[1392] Step 3:

[1393] Generate predictive models

[1394] The server generates a model to predict market trends based on the analysis results. It uses past data to train a machine learning algorithm to predict future market trends. The inputs are past data and analysis results, and the output is a prediction of future market trends.

[1395] Specific behavior:

[1396] 1. Collect historical data and analysis results.

[1397] 2. Train the model using machine learning algorithms.

[1398] 3. Use the trained model to predict future market trends.

[1399] Step 4:

[1400] Real-time translation

[1401] The server translates customer utterances in real time. For example, Japanese utterances can be translated into English and instantly displayed to English-speaking staff. This process requires the customer's utterance as input and the translation result as output.

[1402] Specific behavior:

[1403] 1. Get what your customers say.

[1404] 2. Translate the speech through the translation API.

[1405] 3. The translated results are sent to the device and displayed.

[1406] Step 5:

[1407] sentiment analysis

[1408] The server performs sentiment analysis on customer comments. For example, it classifies a comment like "This product is not very good" as negative. The input is the customer's comment, and the output is the result of the sentiment analysis.

[1409] Specific behavior:

[1410] 1. Get what your customers say.

[1411] 2. Analyze the sentiment of statements using NLP technology.

[1412] 3. The results of the sentiment analysis are sent to the device and displayed.

[1413] Step 6:

[1414] Providing a user interface

[1415] The terminal provides a user interface and displays a dashboard for users to visually check the analysis results and prediction results. This process requires data sent from the server as input, and generates a dashboard that users can view as output.

[1416] Specific behavior:

[1417] 1. Receive data from the server.

[1418] 2. Generate a dashboard.

[1419] 3. Display analysis and prediction results.

[1420] Step 7:

[1421] Real-time display

[1422] The device displays translation results and sentiment analysis results in real time. Data sent from the server is required as input, and a screen that the user can view in real time is generated as output.

[1423] Specific behavior:

[1424] 1. Receive data from the server.

[1425] 2. Display on the screen in real time.

[1426] 3. Users can check the results on the spot.

[1427] Step 8:

[1428] Viewing information

[1429] Users can check market trends and analysis results in real time through their devices. This process requires dashboard data as input, and users can quickly grasp the information as output.

[1430] Specific behavior:

[1431] 1. Navigate the dashboard to find the information you need.

[1432] 2. View various graphs and charts.

[1433] 3. Filter the information as needed.

[1434] Step 9:

[1435] Meeting progress management

[1436] Users use the system to efficiently manage the progress of meetings and customer interactions. The system requires an agenda as input and provides progress notifications as output.

[1437] Specific behavior:

[1438] 1. Set the agenda.

[1439] 2. Monitor the progress of meetings and interactions.

[1440] 3. Receive notifications when you deviate from progress.

[1441] Step 10:

[1442] Multilingual support

[1443] Users can use real-time translation to understand utterances in different languages. An utterance is required as input, and a translation result is obtained as output.

[1444] Specific behavior:

[1445] 1. Get the statement.

[1446] 2. Translate the speech through the translation API.

[1447] 3. The translation results are displayed on the screen.

[1448] 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.

[1449] This invention combines a system that manages the progress of web conferences, performs real-time translation, analyzes emotions, and predicts market trends with an emotion engine that recognizes user emotions. Below, we will explain an embodiment of this system.

[1450] System Configuration

[1451] This system consists of a server, a terminal, a user, and an emotion engine. The server performs the main data processing and analysis, the terminal provides the user interface, and the user operates the system. The emotion engine recognizes and analyzes the user's emotions and feeds the results back to the system.

[1452] Server Functions and Operations

[1453] 1. Information gathering

[1454] The server periodically collects information about the web conferencing market from multiple data sources, such as news APIs, company research reports, public databases, etc. For example, once a day, the server retrieves the latest market articles from the news API and stores them in its internal database.

[1455] 2. Data Analysis

[1456] The server cleans the collected data and analyzes it using natural language processing technology and text mining. For example, the server extracts frequently appearing keywords from the collected articles to understand market interest.

[1457] 3. Generate a predictive model

[1458] The server generates a model to predict market trends based on the analysis results. It uses past data to train a machine learning algorithm to predict future market trends. For example, the server predicts the market size for the next quarter based on past data.

[1459] 4. Real-time translation

[1460] The server translates comments made during the meeting in real time and sends the translation to the terminal. For example, it translates Japanese comments into English and displays the translation results on the terminal.

[1461] 5. Sentiment analysis

[1462] The server analyzes the emotions of the speaker based on what is said during the meeting. For example, it classifies a statement such as "I'm not confident about this plan" as negative.

[1463] Device features and operations

[1464] 1. Providing a user interface

[1465] The terminal provides a dashboard that allows users to visually check the analysis and forecast results. For example, the terminal generates and displays graphs and charts of market trends to the user.

[1466] 2. Real-time display

[1467] The device instantly displays the results of real-time translation and sentiment analysis sent from the server. For example, when a comment made during a meeting is translated and displayed, the sentiment analysis results are also displayed at the same time.

[1468] Functions and operation of the Emotion Engine

[1469] 1. Emotional awareness

[1470] The emotion engine recognizes emotions by analyzing a user's tone of voice, facial recognition data, and word choice. For example, if a user is participating in a meeting through a camera, the emotion engine analyzes facial expression data to determine the user's emotion.

[1471] 2. Emotional Data Storage

[1472] The emotion engine stores the recognized emotion data, for example, the history of emotions expressed by users during a meeting, in a database for later analysis and feedback.

[1473] 3. Emotional Data Feedback

[1474] The server grasps the progress and tone of the meeting based on the emotion data obtained from the emotion engine, and dynamically adjusts the user interface. For example, the user interface displays a warning to the user if the meeting tone is biased toward a negative one.

[1475] User operations

[1476] 1. Viewing Information

[1477] Users can check market trends and analysis results in real time through their devices and simultaneously receive feedback from the emotion engine. For example, users can quickly grasp current market trends by looking at charts on the dashboard.

[1478] 2. Meeting progress management

[1479] Users use the system to efficiently manage the progress of meetings, checking whether the agenda is being followed and making adjustments as necessary. For example, users are notified when the system deviates from the agenda to focus on a sales strategy topic.

[1480] 3. Multilingual support

[1481] Even when multiple languages ​​are used during a meeting, users can use the system's real-time translation function to understand what is being said in different languages. For example, an English-speaking user can see what is being said in Japanese translated into English in real time.

[1482] 4. Use emotional feedback

[1483] Users can adjust the tone of the meeting and discussion based on feedback from the emotion engine. For example, if the meeting is heading in a negative direction, users can take measures such as actively encouraging positive opinions.

[1484] In this way, the system not only supports the efficient operation of web conferences and is a powerful tool for companies to quickly grasp market trends, but also enables more effective communication by recognizing participants' emotions and providing appropriate feedback.

[1485] The processing flow will be explained below.

[1486] Step 1:

[1487] The server periodically collects information about the web conferencing market from multiple data sources, including news APIs, company research reports, and public databases, and stores the latest information in an internal database. This process is performed automatically on a scheduled basis.

[1488] Step 2:

[1489] The server cleans the collected data by completing missing values, removing duplicate data, and removing unnecessary HTML tags and special characters from text data. This improves the quality of the data and increases the accuracy of analysis.

[1490] Step 3:

[1491] The server then uses natural language processing techniques and text mining to analyze the cleaned data, extracting key keywords and analyzing the frequency of these keywords, for example, to see if certain keywords related to market trends are increasing.

[1492] Step 4:

[1493] The server then clusters the extracted keywords and phrases using machine learning algorithms, such as the K-means clustering algorithm, to categorize the data by related topics, thereby revealing market interests.

[1494] Step 5:

[1495] The server collects historical data and uses it to train machine learning algorithms. For example, it uses the past five years of market data to generate a linear regression model to forecast market trends for the next five years. This model is then used to predict future market size and trends.

[1496] Step 6:

[1497] The server uses the trained model to predict market trends based on the analysis results. The prediction results are saved in JSON format and can be displayed through the user interface, allowing users to quickly grasp future market trends.

[1498] Step 7:

[1499] The server translates comments made during a meeting in real time. For example, if a user speaks in Japanese, it translates the comment into English in real time and sends it to the terminal. The translation result is displayed immediately, facilitating communication between participants who speak different languages.

[1500] Step 8:

[1501] The server analyzes the speaker's emotions from what is said during the meeting. The emotion engine analyzes voice tone, word choice, and facial recognition data to recognize the speaker's emotions. For example, it classifies a statement such as "I'm not confident about this plan" as negative.

[1502] Step 9:

[1503] The emotion engine stores the recognized emotion data, for example, the history of emotions expressed during a meeting, in a database for future analysis and feedback.

[1504] Step 10:

[1505] The device displays analysis results, prediction results, real-time translation, and sentiment analysis results through a user interface. For example, the device's dashboard displays market trend graphs and charts, allowing users to quickly grasp current market trends.

[1506] Step 11:

[1507] The device dynamically adjusts the content displayed in the user interface based on the emotion data acquired from the emotion engine. For example, if the tone of the meeting is biased toward negative, the user interface will display a warning to alert the user.

[1508] Step 12:

[1509] Users can view market trends and analysis results in real time through their devices, while simultaneously receiving feedback from the emotion engine, allowing them to understand the progress and tone of the meeting and make adjustments as needed.

[1510] Step 13:

[1511] Users can use the system to efficiently manage the progress of meetings, for example, by checking whether the meeting is proceeding according to the agenda and receiving notifications if the meeting deviates from the agenda, enabling smooth meeting management.

[1512] Step 14:

[1513] Users can use the system's real-time translation function to understand multilingual utterances. For example, an English-speaking user can see a Japanese utterance translated into English in real time.

[1514] In this way, this system not only improves the efficiency of web conferences and supports multiple languages, but also promotes more effective communication by using an emotion engine to recognize participants' emotions and provide appropriate feedback.

[1515] Example 2

[1516] 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."

[1517] Conventional web conferencing systems rarely offer integrated functions such as market trend forecasting, real-time translation, and sentiment analysis, making them insufficient for effective user decision-making and meeting progress. Furthermore, functions for recognizing user emotions and utilizing them in meeting progress are limited, making it difficult to respond appropriately based on participants' emotions. As a result, there are problems with reduced meeting efficiency and effectiveness.

[1518] 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.

[1519] In this invention, the server includes means for periodically collecting market information from data sources, means for analyzing the collected information, means for predicting market trends based on the analysis results, means for translating comments in real time during a conference, means for displaying the translation results on a user interface, means for analyzing the emotions of the comments, means for displaying the emotion analysis results on the user interface, means for analyzing facial recognition data and voice tone to recognize emotions, means for saving the recognized emotion data, and means for dynamically adjusting the user interface based on the emotion data. This makes it possible to efficiently manage the progress of a conference, quickly grasp market trends, and recognize users' emotions and provide appropriate feedback.

[1520] "Data Source" means an external source of information that provides information about the market.

[1521] "Means for collecting information" refers to systems and programs for periodically obtaining market information from data sources.

[1522] "Means for analyzing information" refers to systems and programs that cleanse collected data and analyze it using techniques such as natural language processing and text mining.

[1523] "Means for predicting market trends" are machine learning models and algorithms that predict future market trends based on analysis results.

[1524] "Means for translating statements made during a meeting in real time" refers to a system or program that instantly converts statements made during a meeting into a different language.

[1525] "Means for displaying the translation results on a user interface" refers to a system or program that displays the translated content on a terminal screen in real time.

[1526] A "means for analyzing the emotions of statements" is a system or program that identifies and classifies emotions based on the content of statements made during a meeting.

[1527] The "means for displaying the emotion analysis results on a user interface" refers to a system or program that displays the emotion analysis results on a terminal screen.

[1528] "Means for recognizing emotions by analyzing facial recognition data and voice tone" refers to a system or program that analyzes facial expressions and voice tone to identify a user's emotions.

[1529] The "means for storing recognized emotion data" refers to a system or program that stores analyzed emotion data in a database.

[1530] "Means for dynamically adjusting the user interface based on emotional data" refers to a system or program that changes the screen display in real time based on the user's emotional data.

[1531] This invention combines a system that manages the progress of web conferences, performs real-time translation, analyzes emotions, and predicts market trends with an emotion engine that recognizes user emotions. Below, we will explain an embodiment of this system.

[1532] System Configuration

[1533] This system consists of a server, a terminal, a user, and an emotion engine. The server performs the main data processing and analysis, the terminal provides the user interface, and the user operates the system. The emotion engine recognizes and analyzes the user's emotions and feeds the results back to the system.

[1534] Server Functions and Operations

[1535] The server performs the functions of information collection, data analysis, predictive model generation, real-time translation, and sentiment analysis, using the following software and tools:

[1536] Information gathering

[1537] The server periodically collects information about the web conferencing market from multiple data sources, such as news APIs, company research reports, public databases, etc. For example, once a day, the server retrieves the latest market articles from the news API and stores them in its internal database.

[1538] Data analysis

[1539] The server cleans the collected data and analyzes it using Python NLP libraries (NLTK, Spacy) and text mining tools. For example, the server extracts frequently occurring keywords from the collected articles to understand market interest.

[1540] Generate predictive models

[1541] The server generates a model to predict market trends based on the analysis results. It uses past data to train the model using Python machine learning libraries (scikit-learn, TensorFlow) and predicts future market trends. For example, the server predicts market size trends for the next quarter based on past data.

[1542] Real-time translation

[1543] The server uses Google's real-time translation API to translate what is said during the meeting and send it to the device. For example, it can translate Japanese comments into English and display the translation results on the device.

[1544] sentiment analysis

[1545] The server uses natural language processing technology to analyze the emotions of people speaking during meetings. For example, it classifies statements such as "I'm not confident about this plan" as negative.

[1546] Device features and operations

[1547] The terminal provides a user interface and displays analysis results, prediction results, and sentiment analysis results in real time.

[1548] Providing a user interface

[1549] The terminal provides a dashboard where users can visually check analysis and forecast results, and uses D3.js and Chart.js to generate and display graphs and charts of market trends.

[1550] Real-time display

[1551] The device instantly displays the results of real-time translation and sentiment analysis sent from the server. When speech is translated and displayed during a meeting, the sentiment analysis results are also displayed.

[1552] Functions and operation of the Emotion Engine

[1553] The emotion engine analyzes the user's voice tone and facial recognition data to recognize emotions.

[1554] Emotion recognition

[1555] The emotion engine uses OpenCV and dlib, and Google's Speech-to-Text API for voice recognition to recognize the user's emotions. For example, if a user is participating in a meeting via camera, facial expression data is analyzed to determine the user's emotions.

[1556] Storing Emotional Data

[1557] The emotion engine stores the recognized emotion data in a database (MySQL, PostgreSQL), for example, to store the history of emotions expressed during a meeting, for later analysis and feedback.

[1558] Emotional Data Feedback

[1559] The server uses the emotion data obtained from the emotion engine to grasp the progress and tone of the meeting and dynamically adjusts the user interface. For example, if the meeting tone is biased towards a negative one, it will display a warning to the user.

[1560] User operations

[1561] Users can operate the system through their terminals, view information in real time, and manage the progress of the conference.

[1562] Viewing information

[1563] Users can view market trends and analysis results in real time through their devices and receive feedback from the emotion engine. For example, they can view charts on a dashboard to understand current market trends.

[1564] Meeting progress management

[1565] Users use the system to efficiently manage the progress of meetings, check whether the agenda is being followed and make adjustments as necessary, for example, receive notifications if the agenda is deviating.

[1566] Multilingual support

[1567] Users can use the system's real-time translation feature to understand statements in different languages, for example, an English-speaking user can see a Japanese statement translated into English in real time.

[1568] Utilizing emotional feedback

[1569] Users can adjust the tone of the meeting and discussion based on feedback from the emotion engine. For example, if the meeting is heading in a negative direction, users can take measures such as actively encouraging positive opinions.

[1570] Specific examples and prompts for the generative AI model

[1571] Example 1: A user opens a dashboard and sees a graph of the latest market trends. The graph displays a 10% increase in market growth forecast for the next quarter compared to the previous year.

[1572] Example 2: During a meeting, someone says in Japanese, "We need to introduce a new product line." This is translated into English in real time and displayed as, "We need to introduce a new product line."

[1573] Example prompt 1:

[1574] "This system will tell us about the latest trends in the market."

[1575] Example prompt 2:

[1576] "Generate a model that predicts market trends for the next quarter."

[1577] Example prompt 3:

[1578] "Please translate what is being said in a meeting in real time and display the results."

[1579] As described above, this system supports efficient web conference management and is a powerful tool for companies to quickly grasp market trends. Furthermore, it recognizes participants' emotions and provides appropriate feedback, enabling more effective communication.

[1580] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1581] Step 1:

[1582] Information gathering

[1583] The server regularly collects information about the web conferencing market from multiple data sources, including news APIs, corporate research reports, and public databases.

[1584] Input: News API endpoint URL, API key

[1585] Data processing: The server uses the API key to send an HTTP request to the news API to retrieve new articles.

[1586] Output: Store the retrieved market articles in an internal database.

[1587] Specific operation: The server sets up a scheduled task to retrieve the latest information from the news API at a specific time every day and store it in a database.

[1588] Step 2:

[1589] Data analysis

[1590] The server cleans the collected data and analyzes it using natural language processing libraries (e.g., NLTK, Spacy) and text mining tools.

[1591] Input: Unparsed article data in the internal database

[1592] Data processing: Remove unnecessary information from the articles (HTML tags, spaces, etc.), tokenize the text, and extract keywords.

[1593] Output: Analysis results (keywords, phrases, etc.) are saved in a database.

[1594] Specific operation: The server runs the cleansing script to clean the raw data, and then uses NLP algorithms to extract keywords.

[1595] Step 3:

[1596] Generate predictive models

[1597] The server uses historical data to generate models that predict market trends using Python machine learning libraries (e.g., scikit-learn, TensorFlow).

[1598] Input: Analysis result database, historical market data

[1599] Data processing: Split the dataset into a training set and a test set, and apply an algorithm to train the model.

[1600] Output: A trained predictive model

[1601] Specific operation: The server periodically runs model training jobs and deploys the generated models to the prediction engine.

[1602] Step 4:

[1603] Real-time translation

[1604] The server uses Google's real-time translation API to translate what is said during the meeting and send it to the device.

[1605] Input: Audio data during the meeting

[1606] Data processing: Convert the voice data into text and call the translation API to obtain the translated text.

[1607] Output: Translation result text

[1608] Specific operation: The server performs speech recognition in real time, sends a request to the translation API, and sends the resulting translation results to the device.

[1609] Step 5:

[1610] sentiment analysis

[1611] The server uses natural language processing technology to analyze the emotions of speakers from what is said during the meeting.

[1612] Input: Text data during the meeting

[1613] Data processing: Text data is input into a sentiment analysis model and sentiment labels are assigned.

[1614] Output: Sentiment analysis label (e.g. positive, negative, neutral)

[1615] Specific operation: The server uses a sentiment analysis model to classify comments made during the meeting in real time and saves the analysis results.

[1616] Step 6:

[1617] Providing a user interface

[1618] The device provides a dashboard that allows users to visually check analysis results, prediction results, and sentiment analysis results.

[1619] Input: Analysis results, prediction results, and sentiment analysis results sent from the server

[1620] Data processing: Converts received data into graph or chart format and displays it.

[1621] Output: Visual information on a dashboard

[1622] Specific operation: The device uses D3.js and Chart.js to display and update data in real time.

[1623] Step 7:

[1624] Real-time display

[1625] The device instantly displays the results of real-time translation and sentiment analysis sent from the server.

[1626] Input: Real-time translation results, sentiment analysis results

[1627] Data processing: The received data is immediately displayed and updated.

[1628] Output: On-screen translated text and sentiment labels

[1629] Specific behavior: When the device receives new data, it updates the current display, providing the user with information in real time.

[1630] Step 8:

[1631] emotion recognition

[1632] The emotion engine uses OpenCV and dlib to analyze facial expression data and Google's Speech-to-Text API to analyze voice tones to recognize emotions.

[1633] Input: Camera feed, audio feed

[1634] Data processing: Analyze facial expression data and voice tone to classify emotions.

[1635] Output: Emotion identification result

[1636] Specific operation: The emotion engine analyzes video and audio data in real time and stores the recognized emotions in a database.

[1637] Step 9:

[1638] Storing Emotional Data

[1639] The emotion engine stores the recognized emotion data in a database (e.g., MySQL, PostgreSQL).

[1640] Input: Emotion identification result

[1641] Data processing: Converting the emotion data into an appropriate format and inserting it into the database.

[1642] Output: Emotion data stored in a database

[1643] Specific operation: The emotion engine periodically writes emotion data to the database.

[1644] Step 10:

[1645] Emotional Data Feedback

[1646] The server dynamically adjusts the user interface based on the emotion data obtained from the emotion engine.

[1647] Input: Emotion data

[1648] Data processing: Analyzes emotional data and instructs UI changes.

[1649] Output: Updated user interface

[1650] Specific operation: The server analyzes the emotional data and displays a warning in negative situations and highlights positive situations.

[1651] The above is a description of the specific processing steps of the program for this system. Each step works together to provide useful information to users in real time and to efficiently manage the progress of the conference.

[1652] (Application example 2)

[1653] 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."

[1654] Conventional food delivery services lack sufficient communication between delivery personnel and customers, making it difficult to provide real-time feedback to improve customer satisfaction. Furthermore, they lack multilingual capabilities, making it difficult to communicate smoothly with customers who speak different languages. Furthermore, they do not properly recognize customer emotions and improve services based on them, limiting the improvement of service quality. To address these issues, a system with more advanced communication support and emotion analysis capabilities is needed.

[1655] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1656] In this invention, the server includes means for periodically collecting market information from a data source, means for analyzing the collected information, means for predicting market trends based on the analysis results, means for displaying the prediction results through a user interface, means for collecting voices of delivery personnel and customers, means for converting the collected voices into text, means for translating the converted text in real time, means for analyzing customer emotions, means for saving analyzed emotion data, and means for providing feedback based on the emotion data. This enables real-time, multilingual communication during delivery, and by immediately understanding customer emotions and providing feedback, it is possible to improve service quality and customer satisfaction.

[1657] A "data source" is an external information provider from which market information can be obtained.

[1658] A "market trend" is a collection of data that describes the current state and expected future changes in a particular market.

[1659] A "user interface" is an interface consisting of a display device and an input device that allows a user to interact with a system.

[1660] The "means for collecting voices of delivery personnel and customers" refers to a device or method for collecting voice data of interactions between delivery personnel and customers during the delivery process.

[1661] A "means for converting speech to text" is a device or method that analyzes collected speech data and converts it into text format data.

[1662] A "means for real-time text translation" is a device or method for instantly translating text data into another language.

[1663] The "means for analyzing customer emotions" refers to a device or method for analyzing emotions using customer voice and facial expression data.

[1664] "Means for saving analyzed emotion data" refers to a device or method for saving analyzed emotion data in a database or the like.

[1665] A "means for providing feedback based on emotional data" is a device or method that provides real-time service adjustments or advice based on stored emotional data.

[1666] The system embodying this invention is realized by the following main components: a server, a terminal, a delivery person, a customer, and an emotion engine. The server processes and analyzes data, the terminal provides a user interface through which delivery people and customers operate the system, and the emotion engine recognizes and analyzes the customer's emotions and feeds the results back to the system.

[1667] Server Functions and Operations

[1668] 1. Information gathering

[1669] The server periodically collects market information from multiple data sources, such as news APIs, company research reports, public databases, etc. For example, once a day, the server retrieves the latest market articles from the news API and stores them in its internal database.

[1670] 2. Data Analysis

[1671] The server cleans the collected data and analyzes it using natural language processing technology and text mining. For example, the server extracts frequently appearing keywords from the collected articles to understand market interest.

[1672] 3. Market Trend Forecast

[1673] The server generates a model to predict market trends based on the analysis results. It uses past data to train a machine learning algorithm to predict future market trends. For example, the server predicts the market size for the next quarter based on past data.

[1674] 4. Real-time translation

[1675] The server translates the conversation between the delivery person and the customer in real time and sends it to the terminal. For example, it translates Japanese statements into English and displays the translation results on the terminal.

[1676] 5. Emotion analysis

[1677] The server analyzes the content and tone of the conversation between the delivery person and the customer to recognize emotions. For example, if a customer says, "Thank you, that was very helpful," it classifies the comment as positive.

[1678] Device features and operations

[1679] 1. Providing a user interface

[1680] The terminal provides a dashboard where delivery personnel and customers can visually view analytics and feedback, such as graphs of delivery satisfaction and market trends.

[1681] 2. Real-time display

[1682] The device instantly displays the results of real-time translation and sentiment analysis sent from the server. For example, when a delivery person's words are translated and displayed, the sentiment analysis results are also displayed.

[1683] Functions and operation of the Emotion Engine

[1684] 1. Emotional awareness

[1685] The emotion engine recognizes emotions by analyzing the customer's voice tone and facial expression data. For example, if a customer accepts a delivery via camera, the emotion engine analyzes facial expression data to determine the emotion.

[1686] 2. Emotional Data Storage

[1687] The emotion engine stores the recognized emotion data, for example, the history of emotions expressed by customers during delivery, in a database for later analysis and feedback.

[1688] 3. Emotional Data Feedback

[1689] The server grasps the delivery status and customer satisfaction level based on the emotion data obtained from the emotion engine, and dynamically adjusts the user interface. For example, the user interface displays a warning to the delivery person if the customer is in a negative state.

[1690] User operations

[1691] 1. Viewing Information

[1692] Users can check market trends and analysis results in real time through their devices and simultaneously receive feedback from the emotion engine. For example, users can quickly grasp current market trends by looking at charts on the dashboard.

[1693] 2. Communication support

[1694] Users can use the system to facilitate communication during deliveries, using the real-time translation function between different languages ​​to ensure smooth delivery.

[1695] 3. Use emotional feedback

[1696] Users can improve the quality of their deliveries based on feedback from the emotion engine. For example, if a customer has a negative reaction, users can take immediate action to improve the quality of their deliveries.

[1697] Examples of specific examples and prompts

[1698] Examples:

[1699] If the delivery person only speaks Japanese and the customer only speaks English

[1700] Delivery Person: "Hello, here's a delivery for you."

[1701] English translation example: "Hello, I have a delivery for you."

[1702] Customer response (sentiment analysis results): Customer: "Thank you! This is perfect!" → Positive evaluation

[1703] Application-generated feedback: Smart glasses display to delivery driver, "We've confirmed that the customer is satisfied."

[1704] Example prompt sentence:

[1705] Customer says: "Thank you! This is perfect!"

[1706] Prompt to the sentiment analysis engine: "Analyze the customer's voice and determine whether it is positive or negative."

[1707] Output: "Positive"

[1708] Prompt the generative AI model: "Analyze the customer's voice and generate emotional feedback."

[1709] Example output: "The customer appears to be very satisfied. We will leave positive feedback."

[1710] In this way, the present invention supports smooth communication during delivery and improves real-time customer satisfaction.

[1711] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1712] Step 1:

[1713] The server collects the voices of the delivery person and the customer using the smartphone's microphone, and the collected voice data is sent directly to the next processing step.

[1714] Input: Audio data

[1715] Output: Raw audio data

[1716] What it does: The delivery person's smartphone captures the conversation with the customer.

[1717] Step 2:

[1718] The server converts the collected voice data into text data using the Google Cloud Speech-to-Text API, which converts the speech obtained from the voice into text format.

[1719] Input: Raw audio data

[1720] Output: Text data

[1721] Specific operation: The server sends the audio data to Google Cloud and receives it as text data.

[1722] Step 3:

[1723] The server uses the Google Cloud Translation API to translate the generated text data into other languages ​​in real time, and the translated data is displayed through the user interface.

[1724] Input: Text data

[1725] Output: Translated text data

[1726] Specific operation: The server sends text data to the Google Cloud Translation API and receives the translated text data.

[1727] Step 4:

[1728] The server uses the Microsoft Azure Emotion API to analyze the translated text data and voice tone to recognize the customer's emotions, which are then used for immediate feedback.

[1729] Input: Translated text data, audio tone

[1730] Output: Sentiment data (positive, negative, etc.)

[1731] Specific operation: The server sends text data and audio tones to Microsoft Azure and receives emotion data.

[1732] Step 5:

[1733] The server stores the analyzed emotion data in a database, which is then used to analyze market trends and provide feedback.

[1734] Input: Emotion data

[1735] Output: Stored emotion data

[1736] Specific operation: The server stores the emotion data in an internal database.

[1737] Step 6:

[1738] The server provides real-time feedback based on the emotion data and displays it on the user interface, allowing the delivery person to understand the customer's satisfaction level and take necessary action.

[1739] Input: Stored emotion data

[1740] Output: Feedback displayed in the user interface

[1741] Specific operation: The server analyzes the emotional data, generates positive or negative feedback, and sends it to the device for display.

[1742] Step 7:

[1743] Through the user interface, users can check market trends and feedback results in real time and take action as needed, for example, identifying areas for improvement for the next delivery.

[1744] Input: Feedback and market trend data displayed in the user interface

[1745] Output: User response or action

[1746] Specific actions: The user checks the device dashboard and takes the necessary action.

[1747] Although I have summarized it in a simple manner, the above invention is implemented smoothly by the detailed processes of collection, conversion, translation, recognition, storage, feedback, and response at each step.

[1748] 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.

[1749] 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.

[1750] 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.

[1751] [Fourth embodiment]

[1752] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1753] 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.

[1754] 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).

[1755] 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.

[1756] 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.

[1757] 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).

[1758] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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.

[1763] 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.

[1764] 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."

[1765] The present invention relates to a system for managing the progress of a web conference, performing real-time translation, analyzing emotions, and forecasting market trends. Hereinafter, an embodiment of this system will be described.

[1766] System Configuration

[1767] This system consists of a server, terminals, and users. The server performs the main data processing and analysis, while the terminals provide the user interface and the users operate the system. The server also obtains information from various data sources and performs analysis and predictions.

[1768] Server Functions and Operations

[1769] 1. Information gathering

[1770] The server regularly collects information about the web conferencing market from multiple data sources, including news APIs, corporate research reports, and public databases.

[1771] For example, once a day, the server retrieves the latest market articles from a news API and stores them in an internal database.

[1772] 2. Data Analysis

[1773] The server uses natural language processing technology and text mining to analyze the collected data.

[1774] For example, the server extracts frequently occurring keywords from collected articles to understand market interest.

[1775] 3. Generate a predictive model

[1776] The server generates a model to predict market trends based on the analysis results, and uses historical data to train machine learning algorithms to predict future market trends.

[1777] For example, the server predicts the market size trends for the next quarter based on past data.

[1778] 4. Real-time translation

[1779] The server translates what is said during the meeting in real time and sends it to the terminal.

[1780] For example, a Japanese utterance is translated into English and displayed to an English-speaking user.

[1781] 5. Sentiment analysis

[1782] The server analyzes the emotions of the speaker based on the content of what was said during the meeting.

[1783] For example, the server might classify a statement such as "I'm not confident in this plan" as negative.

[1784] Device features and operations

[1785] 1. Providing a user interface

[1786] The device provides a dashboard that allows users to visually check analysis and prediction results.

[1787] For example, the terminal may generate and display graphs and charts of market trends to the user.

[1788] 2. Real-time display

[1789] The device instantly displays the results of real-time translation and sentiment analysis sent from the server.

[1790] For example, comments made during a meeting are translated and displayed, along with the results of sentiment analysis.

[1791] User operations

[1792] 1. Viewing Information

[1793] Users can check market trends and analysis results in real time through their devices.

[1794] For example, users can view charts on a dashboard to quickly understand current market trends.

[1795] 2. Meeting progress management

[1796] Users can use the system to efficiently manage the progress of meetings, checking whether the agenda is being followed and making adjustments as necessary.

[1797] For example, the user is notified when the system is distracted from the agenda to focus on a sales strategy agenda.

[1798] 3. Multilingual support

[1799] Even if multiple languages ​​are used during a meeting, users can use the system's real-time translation function to understand what is being said in different languages.

[1800] For example, an English-speaking user can see Japanese utterances translated into English in real time.

[1801] In this way, the system supports the efficient operation of web conferences and becomes a powerful tool for companies to quickly grasp market trends.

[1802] The processing flow will be explained below.

[1803] Step 1:

[1804] The server periodically collects information about the web conferencing market from multiple data sources, specifically, retrieving the latest market articles from news APIs, and relevant data from corporate research reports and public databases, and stores this information in an internal database.

[1805] Step 2:

[1806] The server cleans the collected data, for example, by completing missing values ​​and removing duplicate data, and also by removing unnecessary HTML tags and special characters from text data to improve the quality of the data.

[1807] Step 3:

[1808] The server analyzes the cleaned data. Specifically, it performs text mining using natural language processing technology to extract important market keywords. It also performs frequency analysis of the extracted keywords to identify trends.

[1809] Step 4:

[1810] The server uses machine learning algorithms to cluster keywords and phrases, for example applying the K-means clustering algorithm to categorize the data by related topics, which reveals market interests.

[1811] Step 5:

[1812] The server collects historical data and uses it to train machine learning algorithms, for example using the past five years of market data to generate a linear regression model to predict market trends over the next five years.

[1813] Step 6:

[1814] The server uses the trained model to predict market trends based on the analysis results, and the prediction results are formatted in a way that is easy for users to understand and stored in an internal database.

[1815] Step 7:

[1816] The server translates comments made during the meeting in real time. For example, it translates Japanese comments into English and sends the translation results to the terminal. This enables multilingual support.

[1817] Step 8:

[1818] The server analyzes the emotions of the speaker based on what is said during the meeting. For example, it classifies a statement such as "I'm not confident about this plan" as negative and generates a sentiment analysis result.

[1819] Step 9:

[1820] The device displays analysis results, prediction results, real-time translation, and sentiment analysis results through a user interface. For example, the device's dashboard displays market trend graphs and charts, allowing users to understand current market trends and the progress of meetings.

[1821] Step 10:

[1822] Users can check market trends and analysis results in real time through their devices, efficiently manage the progress of meetings, and use the system's real-time translation function to understand statements in multiple languages.

[1823] Example 1

[1824] 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."

[1825] In today's business environment, fast and accurate market trend forecasting is crucial for maintaining a company's competitive edge. However, collecting and properly analyzing information from diverse data sources can be challenging, particularly due to language barriers and the difficulty of accurately understanding the speaker's emotions during meetings. Furthermore, there are few systems that integrate real-time translation and sentiment analysis, which can reduce the efficiency of meetings.

[1826] 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.

[1827] In this invention, the server includes means for periodically collecting market information from multiple data sources such as news APIs, research reports, and public databases, means for analyzing the collected data using natural language processing technology to extract frequently occurring keywords and sentiments, and means for predicting market trends using machine learning algorithms based on the analysis results, thereby enabling rapid and accurate understanding of market trends.

[1828] The system also includes a means for converting speech during a conference into text, a means for translating the converted text in real time, and a means for displaying the translation results on a user interface, thereby enabling smooth communication across language barriers.

[1829] The system also includes a means for analyzing the content of comments made during a meeting and classifying the emotions of the comments, and a means for displaying the real-time emotion analysis results on a user interface, which allows for accurate understanding of the emotions of the speakers and improves the efficiency of the meeting.

[1830] A "news API" is an application program interface for automatically retrieving news articles and information published on the web.

[1831] A "research report" is a document that compiles the results of specialized research on a market, industry, product, etc.

[1832] A "public database" is a collection of data provided by a government agency or public institution that is open to the public.

[1833] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[1834] A "machine learning algorithm" is an algorithm that automatically learns patterns based on data and makes predictions and classifications.

[1835] A "user interface" refers to the screen and operating means that allow a user to interact with a system.

[1836] "Speech recognition" is a technology in which a computer converts human speech into text data.

[1837] "Real-time translation" is a technology that translates conversations and text into other languages ​​in real time.

[1838] "Sentiment analysis" is a technology that automatically analyzes emotional states from text data and classifies them as positive, negative, neutral, etc.

[1839] This invention relates to a system for managing the progress of web conferences, performing real-time translation, analyzing emotions, and forecasting market trends. This system is composed of a server, terminals, and users. A specific embodiment of this system will be described below.

[1840] Server Functions and Operations

[1841] The server is responsible for the main data processing and analysis functions. First, the server accesses multiple data sources, such as news APIs, research reports, and public databases. These APIs are accessed using news API keys and corporate research report access keys. The server periodically collects information from these data sources and stores it in an internal database. For example, every morning at 9:00, the server retrieves the latest articles about the web conferencing market from the news API and stores them in the database.

[1842] The server then analyzes the collected data using natural language processing techniques (e.g., NLTK, spaCy). It extracts frequently occurring keywords from the collected articles to understand market interest. It also uses sentiment analysis algorithms (e.g., TextBlob, VADER) to classify the content of the articles as positive, negative, or neutral. For example, it identifies the phrase "I'm not confident in this plan" as a negative sentiment.

[1843] The analyzed data is used as training data to predict market trends using machine learning algorithms. The server uses the past data to generate a model that predicts future market trends. The model trained by the machine learning algorithm predicts, for example, the market size for the next quarter.

[1844] Furthermore, to provide a real-time translation function, the server converts the conference voice into text using a speech recognition service (e.g., Google Speech-to-Text API) and translates the acquired text into a specified language using a translation service (e.g., Google Translate API). For example, Japanese statements may be translated into English and sent to the terminal for display to an English-speaking user.

[1845] Device features and operations

[1846] The device provides a dashboard that allows users to visually check analysis and forecast results. Web technologies such as HTML, CSS, and JavaScript are used for the user interface. For example, the device generates graphs and charts of market trends and displays them to the user. It also has the ability to display real-time translation results and sentiment analysis results on the conference screen. For example, the translation result of "Hello" can be displayed as "Hello," and the sentiment analysis result (negative) of the statement "I'm not confident in this plan" can be displayed at the same time.

[1847] User operations

[1848] Users can check market trends and analysis results in real time through their devices. They can quickly grasp current market trends by looking at market trend graphs on the dashboard. Users can also use the system to efficiently manage meeting progress, checking whether the meeting is proceeding according to the agenda and making adjustments as necessary. For example, users can be notified if the system deviates from the agenda in order to focus on the sales strategy topic. In addition, the real-time translation function allows users to understand statements in different languages. For example, an English-speaking user can see Japanese statements translated into English in real time.

[1849] Examples of prompt statements

[1850] Below are some examples of prompt sentences.

[1851] 1. Information Collection:

[1852] "Do you have sample code for a news API that retrieves the latest articles about the web conferencing market?"

[1853] 2. Data Analysis:

[1854] "Can you please give me some Python code to extract frequently occurring keywords from news articles about the web conferencing market?"

[1855] 3. Generate predictive models:

[1856] "I'd like to build a machine learning model to predict the market size for the next quarter based on historical market data. Can you give me some advice?"

[1857] 4. Real-time translation:

[1858] "Please tell me an API for translating Japanese to English in real time."

[1859] 5. Sentiment analysis:

[1860] "Please tell me a Python library that can analyze emotions from speech content."

[1861] 6. Progress management:

[1862] "I want to create a script to manage the progress of a meeting. Can you tell me the relevant APIs and libraries?"

[1863] In this way, the system helps to efficiently manage web conferences and is a powerful tool for companies to quickly grasp market trends.

[1864] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1865] The flow of this system's program processing

[1866] Information gathering steps:

[1867] Step 1:

[1868] The server accesses the news API using the API key and sends a request to get the "latest articles about the web conferencing market." The input is the API key and request parameters, and the output is the latest article data.

[1869] Specific operation: The server calls the news API on a set schedule every morning at 9:00 and analyzes the JSON format data received as a response.

[1870] Step 2:

[1871] The server stores the retrieved news article data in an internal database. The input is news article data in JSON format, and the output is the articles stored in the database.

[1872] Specific operation: The server breaks down the retrieved article data into each field (e.g., title, content, publication date) and inserts it into the database using an SQL query.

[1873] Data analysis steps:

[1874] Step 1:

[1875] The server reads the stored news article data for analysis using natural language processing techniques. The input is the article data stored in the database, and the output is a tokenized word sequence.

[1876] Specific operation: The server retrieves article data in text format and tokenizes it using a natural language processing library (e.g., NLTK, spaCy).

[1877] Step 2:

[1878] The server extracts frequent keywords from the tokenized word string. The input is the tokenized word string, and the output is a list of frequent keywords.

[1879] Specific operation: The server analyzes the tokenized word string, calculates the frequency of each word, and selects particularly important keywords.

[1880] Step 3:

[1881] The server analyzes the content of articles using a sentiment analysis algorithm and classifies them as positive, negative, or neutral. The input is the text data of the article, and the output is the sentiment label (positive, negative, or neutral).

[1882] How it works: The server uses a sentiment analysis library such as TextBlob or VADER to calculate a sentiment score for each sentence.

[1883] Steps for generating a predictive model:

[1884] Step 1:

[1885] The server preprocesses the analyzed data as training data for a machine learning model. The input is the analyzed article data and a list of frequently occurring keywords, and the output is a training dataset.

[1886] Specific operation: The server quantifies the data and converts it into a format that can be used by the machine learning model (e.g., normalization, feature extraction).

[1887] Step 2:

[1888] The server uses machine learning algorithms to train models that predict market trends, where the input is a pre-processed training dataset and the output is a predictive model.

[1889] What it does: The server applies algorithms such as time series analysis and regression analysis to train a model using the data.

[1890] Real-time translation steps:

[1891] Step 1:

[1892] The server captures the voice during the conference and sends it to the speech recognition service to convert it into text. The input is real-time voice data, and the output is text data of the speech recognition results.

[1893] What it does: The server captures the audio stream in real time and sends it to the Google Speech-to-Text API to get the text data.

[1894] Step 2:

[1895] The server translates the text obtained by speech recognition into the specified language using a translation service. The input is the text data of the speech recognition result, and the output is the text data of the translation result.

[1896] Specific operation: The server uses the Google Translate API to translate the speech recognition results in real time and convert them into the specified language.

[1897] Sentiment analysis steps:

[1898] Step 1:

[1899] The server analyzes the content of speech during a meeting in real time and classifies the speaker's emotions. The input is the text data of the meeting audio, and the output is an emotion label (positive, negative, neutral).

[1900] Specific operation: The server analyzes the text obtained from the speech recognition results, calculates the emotion score using libraries such as TextBlob and VADER, and assigns emotion labels.

[1901] User operation steps:

[1902] Step 1:

[1903] Users can check the analysis and prediction results through a dashboard on their device. The input is the analysis and prediction results sent from the server, and the output is the graphs and charts displayed on the dashboard.

[1904] Specific operation: The user sees graphs and charts of market trends updated in real time on the device screen.

[1905] Step 2:

[1906] Users use the system to manage the progress of a conference. The input is real-time information about the progress of the conference, and the output is actions based on the user's decisions.

[1907] Specific operation: The user checks whether the meeting is proceeding according to the agenda and instructs the speaker to make adjustments if necessary.

[1908] Through the above processing steps, this system supports the efficient operation of web conferences and provides users with a powerful tool for timely understanding of market trends.

[1909] (Application example 1)

[1910] 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."

[1911] In modern store operations, serving customers who speak different languages ​​and understanding their immediate satisfaction are key issues. Insufficient multilingual support can lead to dissatisfaction among customers, leading to more negative feedback. It is also necessary to analyze customer sentiment in real time and respond quickly to improve customer satisfaction.

[1912] 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.

[1913] In this invention, the server includes means for periodically collecting market information from a data source, means for analyzing the collected information, means for predicting market trends based on the analysis results, means for displaying the prediction results through a user interface, means for real-time translation of customer responses, means for displaying the translation results on the user interface, means for sentiment analysis of customer comments, and means for displaying the sentiment analysis results on the user interface. This makes it possible to efficiently respond to customers who speak different languages, analyze customer sentiment in real time, and immediately provide appropriate responses, thereby improving customer satisfaction.

[1914] A "data source" is an external or internal source from which information is obtained.

[1915] "Means for periodically collecting information" are technological means for collecting data on the market at regular intervals.

[1916] "Means of analyzing information" refers to the technical means used to analyze collected data and extract meaning and trends.

[1917] "Means for predicting market trends" are technical means for predicting future market movements from analysis results.

[1918] A "user interface" is a screen or input device that allows a user to interact with a system.

[1919] A "translation tool" is a technical tool for converting an utterance in one language into another language.

[1920] "Means for emotion analysis" refers to a technical means for analyzing emotions from the content of statements and recognizing emotions such as positive and negative.

[1921] "Display means" refers to the technical means for visually presenting analysis results, translation results, etc. to the user.

[1922] "Customer response" refers to the activities of store staff to communicate with customers.

[1923] The system for implementing the present invention mainly comprises a server, a terminal, and a user. The server processes and analyzes data, the terminal provides a user interface, and the user operates the system.

[1924] Server Functions and Operations

[1925] 1. Information gathering

[1926] The server periodically collects market information from data sources, such as news APIs, corporate research reports, and public databases, and stores the information in an internal database. This allows you to always have access to the latest market information.

[1927] 2. Data Analysis

[1928] The server uses natural language processing (NLP) and text mining to analyze the collected data. For example, it extracts frequently occurring keywords from collected articles to understand market interest. This makes it possible to quickly detect changes in market trends.

[1929] 3. Generate a predictive model

[1930] The server generates a model to predict market trends based on the analysis results. Using past data, the machine learning algorithm is trained to predict future market trends. For example, predicting market size trends for the next quarter can help formulate future strategies.

[1931] 4. Real-time translation

[1932] The server translates comments made during meetings or customer interactions in real time. For example, Japanese comments can be translated into English and instantly displayed to English-speaking staff.

[1933] 5. Sentiment analysis

[1934] The server analyzes the speaker's sentiment based on the content of the comment. For example, it can classify a comment such as "This product is not very good" as negative and provide appropriate feedback.

[1935] Device features and operations

[1936] 1. Providing a user interface

[1937] The terminal provides a dashboard where users can visually check analysis and forecast results. Graphs and charts of market trends are generated and displayed to users, allowing them to intuitively grasp the information.

[1938] 2. Real-time display

[1939] The device instantly displays the translation results and sentiment analysis results sent from the server. For example, during a meeting or customer service, when a comment is translated and displayed, sentiment analysis results are also displayed at the same time.

[1940] User operations

[1941] 1. Viewing Information

[1942] Users can check market trends and analysis results in real time through their devices, and quickly grasp current market trends by looking at charts on the dashboard.

[1943] 2. Meeting progress management

[1944] Users can use the system to efficiently manage the progress of meetings and client interactions, check whether the agenda is being followed and make adjustments as necessary. For example, they can be notified if the system deviates from the agenda.

[1945] 3. Multilingual support

[1946] Even when multiple languages ​​are used during meetings or customer interactions, users can use the system's real-time translation function to understand what is being said in different languages. For example, an English-speaking user can see what is being said in Japanese translated into English in real time.

[1947] Specific examples

[1948] Technology used

[1949] Hardware: Smartphones, servers

[1950] Software: Python (textblob, googletrans, requests libraries)

[1951] Prompt Sentence Examples

[1952] If a customer says 'This product is not very good', perform sentiment analysis and output the results.

[1953] By combining these elements, it becomes possible to improve the efficiency of customer service in stores, increase customer satisfaction, and grasp market trends in real time.

[1954] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1955] Step 1:

[1956] Information gathering

[1957] The server periodically collects market information from data sources. This process retrieves the latest market data from news APIs, company research reports, public databases, etc. The input requires an API key and a search query, and the output is a dataset of news articles and reports. This data is then stored in an internal database.

[1958] Specific behavior:

[1959] 1. Send a query to the News API.

[1960] 2. Get the news article data returned as a response.

[1961] 3. The acquired data is stored in an internal database.

[1962] Step 2:

[1963] Data analysis

[1964] The server analyzes the collected data. Using natural language processing (NLP) and text mining, it extracts frequently occurring keywords from articles and understands market interest. The data collected in step 1 is required as input, and the extracted frequently occurring keywords and their frequency of appearance are obtained as output.

[1965] Specific behavior:

[1966] 1. Analyze the collected data using text mining tools.

[1967] 2. Extract frequently occurring keywords and calculate their frequency of occurrence.

[1968] 3. Compile the extracted keywords and their frequency into a report.

[1969] Step 3:

[1970] Generate predictive models

[1971] The server generates a model to predict market trends based on the analysis results. It uses past data to train a machine learning algorithm to predict future market trends. The inputs are past data and analysis results, and the output is a prediction of future market trends.

[1972] Specific behavior:

[1973] 1. Collect historical data and analysis results.

[1974] 2. Train the model using machine learning algorithms.

[1975] 3. Use the trained model to predict future market trends.

[1976] Step 4:

[1977] Real-time translation

[1978] The server translates customer utterances in real time. For example, Japanese utterances can be translated into English and instantly displayed to English-speaking staff. This process requires the customer's utterance as input and the translation result as output.

[1979] Specific behavior:

[1980] 1. Get what your customers say.

[1981] 2. Translate the speech through the translation API.

[1982] 3. The translated results are sent to the device and displayed.

[1983] Step 5:

[1984] sentiment analysis

[1985] The server performs sentiment analysis on customer comments. For example, it classifies a comment like "This product is not very good" as negative. The input is the customer's comment, and the output is the result of the sentiment analysis.

[1986] Specific behavior:

[1987] 1. Get what your customers say.

[1988] 2. Analyze the sentiment of statements using NLP technology.

[1989] 3. The results of the sentiment analysis are sent to the device and displayed.

[1990] Step 6:

[1991] Providing a user interface

[1992] The terminal provides a user interface and displays a dashboard for users to visually check the analysis results and prediction results. This process requires data sent from the server as input, and generates a dashboard that users can view as output.

[1993] Specific behavior:

[1994] 1. Receive data from the server.

[1995] 2. Generate a dashboard.

[1996] 3. Display analysis and prediction results.

[1997] Step 7:

[1998] Real-time display

[1999] The device displays translation results and sentiment analysis results in real time. Data sent from the server is required as input, and a screen that the user can view in real time is generated as output.

[2000] Specific behavior:

[2001] 1. Receive data from the server.

[2002] 2. Display on the screen in real time.

[2003] 3. Users can check the results on the spot.

[2004] Step 8:

[2005] Viewing information

[2006] Users can check market trends and analysis results in real time through their devices. This process requires dashboard data as input, and users can quickly grasp the information as output.

[2007] Specific behavior:

[2008] 1. Navigate the dashboard to find the information you need.

[2009] 2. View various graphs and charts.

[2010] 3. Filter the information as needed.

[2011] Step 9:

[2012] Meeting progress management

[2013] Users use the system to efficiently manage the progress of meetings and customer interactions. The system requires an agenda as input and provides progress notifications as output.

[2014] Specific behavior:

[2015] 1. Set the agenda.

[2016] 2. Monitor the progress of meetings and interactions.

[2017] 3. Receive notifications when you deviate from progress.

[2018] Step 10:

[2019] Multilingual support

[2020] Users can use real-time translation to understand utterances in different languages. An utterance is required as input, and a translation result is obtained as output.

[2021] Specific behavior:

[2022] 1. Get the statement.

[2023] 2. Translate the speech through the translation API.

[2024] 3. The translation results are displayed on the screen.

[2025] 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.

[2026] This invention combines a system that manages the progress of web conferences, performs real-time translation, analyzes emotions, and predicts market trends with an emotion engine that recognizes user emotions. Below, we will explain an embodiment of this system.

[2027] System Configuration

[2028] This system consists of a server, a terminal, a user, and an emotion engine. The server performs the main data processing and analysis, the terminal provides the user interface, and the user operates the system. The emotion engine recognizes and analyzes the user's emotions and feeds the results back to the system.

[2029] Server Functions and Operations

[2030] 1. Information gathering

[2031] The server periodically collects information about the web conferencing market from multiple data sources, such as news APIs, company research reports, public databases, etc. For example, once a day, the server retrieves the latest market articles from the news API and stores them in its internal database.

[2032] 2. Data Analysis

[2033] The server cleans the collected data and analyzes it using natural language processing technology and text mining. For example, the server extracts frequently appearing keywords from the collected articles to understand market interest.

[2034] 3. Generate a predictive model

[2035] The server generates a model to predict market trends based on the analysis results. It uses past data to train a machine learning algorithm to predict future market trends. For example, the server predicts the market size for the next quarter based on past data.

[2036] 4. Real-time translation

[2037] The server translates comments made during the meeting in real time and sends the translation to the terminal. For example, it translates Japanese comments into English and displays the translation results on the terminal.

[2038] 5. Sentiment analysis

[2039] The server analyzes the emotions of the speaker based on what is said during the meeting. For example, it classifies a statement such as "I'm not confident about this plan" as negative.

[2040] Device features and operations

[2041] 1. Providing a user interface

[2042] The terminal provides a dashboard that allows users to visually check the analysis and forecast results. For example, the terminal generates and displays graphs and charts of market trends to the user.

[2043] 2. Real-time display

[2044] The device instantly displays the results of real-time translation and sentiment analysis sent from the server. For example, when a comment made during a meeting is translated and displayed, the sentiment analysis results are also displayed at the same time.

[2045] Functions and operation of the Emotion Engine

[2046] 1. Emotional awareness

[2047] The emotion engine recognizes emotions by analyzing a user's tone of voice, facial recognition data, and word choice. For example, if a user is participating in a meeting through a camera, the emotion engine analyzes facial expression data to determine the user's emotion.

[2048] 2. Emotional Data Storage

[2049] The emotion engine stores the recognized emotion data, for example, the history of emotions expressed by users during a meeting, in a database for later analysis and feedback.

[2050] 3. Emotional Data Feedback

[2051] The server grasps the progress and tone of the meeting based on the emotion data obtained from the emotion engine, and dynamically adjusts the user interface. For example, the user interface displays a warning to the user if the meeting tone is biased toward a negative one.

[2052] User operations

[2053] 1. Viewing Information

[2054] Users can check market trends and analysis results in real time through their devices and simultaneously receive feedback from the emotion engine. For example, users can quickly grasp current market trends by looking at charts on the dashboard.

[2055] 2. Meeting progress management

[2056] Users use the system to efficiently manage the progress of meetings, checking whether the agenda is being followed and making adjustments as necessary. For example, users are notified when the system deviates from the agenda to focus on a sales strategy topic.

[2057] 3. Multilingual support

[2058] Even when multiple languages ​​are used during a meeting, users can use the system's real-time translation function to understand what is being said in different languages. For example, an English-speaking user can see what is being said in Japanese translated into English in real time.

[2059] 4. Use emotional feedback

[2060] Users can adjust the tone of the meeting and discussion based on feedback from the emotion engine. For example, if the meeting is heading in a negative direction, users can take measures such as actively encouraging positive opinions.

[2061] In this way, the system not only supports the efficient operation of web conferences and is a powerful tool for companies to quickly grasp market trends, but also enables more effective communication by recognizing participants' emotions and providing appropriate feedback.

[2062] The processing flow will be explained below.

[2063] Step 1:

[2064] The server periodically collects information about the web conferencing market from multiple data sources, including news APIs, company research reports, and public databases, and stores the latest information in an internal database. This process is performed automatically on a scheduled basis.

[2065] Step 2:

[2066] The server cleans the collected data by completing missing values, removing duplicate data, and removing unnecessary HTML tags and special characters from text data. This improves the quality of the data and increases the accuracy of analysis.

[2067] Step 3:

[2068] The server then uses natural language processing techniques and text mining to analyze the cleaned data, extracting key keywords and analyzing the frequency of these keywords, for example, to see if certain keywords related to market trends are increasing.

[2069] Step 4:

[2070] The server then clusters the extracted keywords and phrases using machine learning algorithms, such as the K-means clustering algorithm, to categorize the data by related topics, thereby revealing market interests.

[2071] Step 5:

[2072] The server collects historical data and uses it to train machine learning algorithms. For example, it uses the past five years of market data to generate a linear regression model to forecast market trends for the next five years. This model is then used to predict future market size and trends.

[2073] Step 6:

[2074] The server uses the trained model to predict market trends based on the analysis results. The prediction results are saved in JSON format and can be displayed through the user interface, allowing users to quickly grasp future market trends.

[2075] Step 7:

[2076] The server translates comments made during a meeting in real time. For example, if a user speaks in Japanese, it translates the comment into English in real time and sends it to the terminal. The translation result is displayed immediately, facilitating communication between participants who speak different languages.

[2077] Step 8:

[2078] The server analyzes the speaker's emotions from what is said during the meeting. The emotion engine analyzes voice tone, word choice, and facial recognition data to recognize the speaker's emotions. For example, it classifies a statement such as "I'm not confident about this plan" as negative.

[2079] Step 9:

[2080] The emotion engine stores the recognized emotion data, for example, the history of emotions expressed during a meeting, in a database for future analysis and feedback.

[2081] Step 10:

[2082] The device displays analysis results, prediction results, real-time translation, and sentiment analysis results through a user interface. For example, the device's dashboard displays market trend graphs and charts, allowing users to quickly grasp current market trends.

[2083] Step 11:

[2084] The device dynamically adjusts the content displayed in the user interface based on the emotion data acquired from the emotion engine. For example, if the tone of the meeting is biased toward negative, the user interface will display a warning to alert the user.

[2085] Step 12:

[2086] Users can view market trends and analysis results in real time through their devices, while simultaneously receiving feedback from the emotion engine, allowing them to understand the progress and tone of the meeting and make adjustments as needed.

[2087] Step 13:

[2088] Users can use the system to efficiently manage the progress of meetings, for example, by checking whether the meeting is proceeding according to the agenda and receiving notifications if the meeting deviates from the agenda, enabling smooth meeting management.

[2089] Step 14:

[2090] Users can use the system's real-time translation function to understand multilingual utterances. For example, an English-speaking user can see a Japanese utterance translated into English in real time.

[2091] In this way, this system not only improves the efficiency of web conferences and supports multiple languages, but also promotes more effective communication by using an emotion engine to recognize participants' emotions and provide appropriate feedback.

[2092] Example 2

[2093] 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."

[2094] Conventional web conferencing systems rarely offer integrated functions such as market trend forecasting, real-time translation, and sentiment analysis, making them insufficient for effective user decision-making and meeting progress. Furthermore, functions for recognizing user emotions and utilizing them in meeting progress are limited, making it difficult to respond appropriately based on participants' emotions. As a result, there are problems with reduced meeting efficiency and effectiveness.

[2095] 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.

[2096] In this invention, the server includes means for periodically collecting market information from data sources, means for analyzing the collected information, means for predicting market trends based on the analysis results, means for translating comments in real time during a conference, means for displaying the translation results on a user interface, means for analyzing the emotions of the comments, means for displaying the emotion analysis results on the user interface, means for analyzing facial recognition data and voice tone to recognize emotions, means for saving the recognized emotion data, and means for dynamically adjusting the user interface based on the emotion data. This makes it possible to efficiently manage the progress of a conference, quickly grasp market trends, and recognize users' emotions and provide appropriate feedback.

[2097] "Data Source" means an external source of information that provides information about the market.

[2098] "Means for collecting information" refers to systems and programs for periodically obtaining market information from data sources.

[2099] "Means for analyzing information" refers to systems and programs that cleanse collected data and analyze it using techniques such as natural language processing and text mining.

[2100] "Means for predicting market trends" are machine learning models and algorithms that predict future market trends based on analysis results.

[2101] "Means for translating statements made during a meeting in real time" refers to a system or program that instantly converts statements made during a meeting into a different language.

[2102] "Means for displaying the translation results on a user interface" refers to a system or program that displays the translated content on a terminal screen in real time.

[2103] A "means for analyzing the emotions of statements" is a system or program that identifies and classifies emotions based on the content of statements made during a meeting.

[2104] The "means for displaying the emotion analysis results on a user interface" refers to a system or program that displays the emotion analysis results on a terminal screen.

[2105] "Means for recognizing emotions by analyzing facial recognition data and voice tone" refers to a system or program that analyzes facial expressions and voice tone to identify a user's emotions.

[2106] The "means for storing recognized emotion data" refers to a system or program that stores analyzed emotion data in a database.

[2107] "Means for dynamically adjusting the user interface based on emotional data" refers to a system or program that changes the screen display in real time based on the user's emotional data.

[2108] This invention combines a system that manages the progress of web conferences, performs real-time translation, analyzes emotions, and predicts market trends with an emotion engine that recognizes user emotions. Below, we will explain an embodiment of this system.

[2109] System Configuration

[2110] This system consists of a server, a terminal, a user, and an emotion engine. The server performs the main data processing and analysis, the terminal provides the user interface, and the user operates the system. The emotion engine recognizes and analyzes the user's emotions and feeds the results back to the system.

[2111] Server Functions and Operations

[2112] The server performs the functions of information collection, data analysis, predictive model generation, real-time translation, and sentiment analysis, using the following software and tools:

[2113] Information gathering

[2114] The server periodically collects information about the web conferencing market from multiple data sources, such as news APIs, company research reports, public databases, etc. For example, once a day, the server retrieves the latest market articles from the news API and stores them in its internal database.

[2115] Data analysis

[2116] The server cleans the collected data and analyzes it using Python NLP libraries (NLTK, Spacy) and text mining tools. For example, the server extracts frequently occurring keywords from the collected articles to understand market interest.

[2117] Generate predictive models

[2118] The server generates a model to predict market trends based on the analysis results. It uses past data to train the model using Python machine learning libraries (scikit-learn, TensorFlow) and predicts future market trends. For example, the server predicts market size trends for the next quarter based on past data.

[2119] Real-time translation

[2120] The server uses Google's real-time translation API to translate what is said during the meeting and send it to the device. For example, it can translate Japanese comments into English and display the translation results on the device.

[2121] sentiment analysis

[2122] The server uses natural language processing technology to analyze the emotions of people speaking during meetings. For example, it classifies statements such as "I'm not confident about this plan" as negative.

[2123] Device features and operations

[2124] The terminal provides a user interface and displays analysis results, prediction results, and sentiment analysis results in real time.

[2125] Providing a user interface

[2126] The terminal provides a dashboard where users can visually check analysis and forecast results, and uses D3.js and Chart.js to generate and display graphs and charts of market trends.

[2127] Real-time display

[2128] The device instantly displays the results of real-time translation and sentiment analysis sent from the server. When speech is translated and displayed during a meeting, the sentiment analysis results are also displayed.

[2129] Functions and operation of the Emotion Engine

[2130] The emotion engine analyzes the user's voice tone and facial recognition data to recognize emotions.

[2131] Emotion recognition

[2132] The emotion engine uses OpenCV and dlib, and Google's Speech-to-Text API for voice recognition to recognize the user's emotions. For example, if a user is participating in a meeting via camera, facial expression data is analyzed to determine the user's emotions.

[2133] Storing Emotional Data

[2134] The emotion engine stores the recognized emotion data in a database (MySQL, PostgreSQL), for example, to store the history of emotions expressed during a meeting, for later analysis and feedback.

[2135] Emotional Data Feedback

[2136] The server uses the emotion data obtained from the emotion engine to grasp the progress and tone of the meeting and dynamically adjusts the user interface. For example, if the meeting tone is biased towards a negative one, it will display a warning to the user.

[2137] User operations

[2138] Users can operate the system through their terminals, view information in real time, and manage the progress of the conference.

[2139] Viewing information

[2140] Users can view market trends and analysis results in real time through their devices and receive feedback from the emotion engine. For example, they can view charts on a dashboard to understand current market trends.

[2141] Meeting progress management

[2142] Users use the system to efficiently manage the progress of meetings, check whether the agenda is being followed and make adjustments as necessary, for example, receive notifications if the agenda is deviating.

[2143] Multilingual support

[2144] Users can use the system's real-time translation feature to understand statements in different languages, for example, an English-speaking user can see a Japanese statement translated into English in real time.

[2145] Utilizing emotional feedback

[2146] Users can adjust the tone of the meeting and discussion based on feedback from the emotion engine. For example, if the meeting is heading in a negative direction, users can take measures such as actively encouraging positive opinions.

[2147] Specific examples and prompts for the generative AI model

[2148] Example 1: A user opens a dashboard and sees a graph of the latest market trends. The graph displays a 10% increase in market growth forecast for the next quarter compared to the previous year.

[2149] Example 2: During a meeting, someone says in Japanese, "We need to introduce a new product line." This is translated into English in real time and displayed as, "We need to introduce a new product line."

[2150] Example prompt 1:

[2151] "This system will tell us about the latest trends in the market."

[2152] Example prompt 2:

[2153] "Generate a model that predicts market trends for the next quarter."

[2154] Example prompt 3:

[2155] "Please translate what is being said in a meeting in real time and display the results."

[2156] As described above, this system supports efficient web conference management and is a powerful tool for companies to quickly grasp market trends. Furthermore, it recognizes participants' emotions and provides appropriate feedback, enabling more effective communication.

[2157] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2158] Step 1:

[2159] Information gathering

[2160] The server regularly collects information about the web conferencing market from multiple data sources, including news APIs, corporate research reports, and public databases.

[2161] Input: News API endpoint URL, API key

[2162] Data processing: The server uses the API key to send an HTTP request to the news API to retrieve new articles.

[2163] Output: Store the retrieved market articles in an internal database.

[2164] Specific operation: The server sets up a scheduled task to retrieve the latest information from the news API at a specific time every day and store it in a database.

[2165] Step 2:

[2166] Data analysis

[2167] The server cleans the collected data and analyzes it using natural language processing libraries (e.g., NLTK, Spacy) and text mining tools.

[2168] Input: Unparsed article data in the internal database

[2169] Data processing: Remove unnecessary information from the articles (HTML tags, spaces, etc.), tokenize the text, and extract keywords.

[2170] Output: Analysis results (keywords, phrases, etc.) are saved in a database.

[2171] Specific operation: The server runs the cleansing script to clean the raw data, and then uses NLP algorithms to extract keywords.

[2172] Step 3:

[2173] Generate predictive models

[2174] The server uses historical data to generate models that predict market trends using Python machine learning libraries (e.g., scikit-learn, TensorFlow).

[2175] Input: Analysis result database, historical market data

[2176] Data processing: Split the dataset into a training set and a test set, and apply an algorithm to train the model.

[2177] Output: A trained predictive model

[2178] Specific operation: The server periodically runs model training jobs and deploys the generated models to the prediction engine.

[2179] Step 4:

[2180] Real-time translation

[2181] The server uses Google's real-time translation API to translate what is said during the meeting and send it to the device.

[2182] Input: Audio data during the meeting

[2183] Data processing: Convert the voice data into text and call the translation API to obtain the translated text.

[2184] Output: Translation result text

[2185] Specific operation: The server performs speech recognition in real time, sends a request to the translation API, and sends the resulting translation results to the device.

[2186] Step 5:

[2187] sent...

Claims

1. A means of regularly gathering market information from data sources; a means for analyzing the collected information; and A means of forecasting market trends based on the analysis results; means for displaying the prediction results through a user interface; A system including:

2. A means to translate statements in real time during meetings, means for displaying the translation result on a user interface; The system of claim 1 further comprising:

3. A means of analyzing the sentiment of statements; means for displaying the sentiment analysis results in a user interface; The system of claim 1 further comprising:

Images