system

Abstract

We provide the system. [Solution] Means for collecting data from an information gathering device, A means of preprocessing the collected data, A means of analyzing pre-processed data using natural language processing techniques and extracting important information, A means of generating the extracted information in report format, A means of generating alerts in real time based on set conditions, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern corporate activities, in order to make quick and accurate decisions, it is necessary to efficiently collect and analyze a huge amount of information. However, business-related data covers a wide range, such as news, social media, industry reports, and internal communications within the company, and it takes time and effort to comprehensively process these manually. Therefore, it is difficult to timely grasp important market trends and competitive information, and there is a problem that the formulation of appropriate sales and marketing strategies is delayed.

Means for Solving the Problems

[0005] This invention features a function that automatically collects data from an information gathering device, preprocesses it, and removes noise. Furthermore, it provides a system that extracts important information using natural language processing technology and generates this information in report format. It also has a function that generates alerts in real time based on set conditions. As a result, users can grasp market trends and competitive information in a timely and accurate manner, enabling rapid decision-making.

[0006] An "information gathering device" is a combination of hardware and software used to acquire information from various data sources both inside and outside the company.

[0007] "Preprocessing" refers to a series of processes that remove noise from collected data and format it into a format suitable for analysis.

[0008] "Natural language processing technology" is a general term for machine learning and statistical methods used by programs to understand and process human language.

[0009] Topic modeling is a technique that extracts the semantic relationships latent in document data and classifies the data into topics.

[0010] Sentiment analysis is a technique that estimates emotional and opinion tendencies from text data and then quantifies or classifies them.

[0011] "Generating in report format" refers to the process of visualizing extracted information and representing it as a document or graph.

[0012] "A means of generating alerts in real time" refers to a function that, based on data analysis results, immediately issues notifications in response to specific conditions or events. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [[ID=*35]] [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. [[ID=*46]]

[0015] [[ID=*47]] It should be noted that in the original text, there are two consecutive tags

[0015] and which seem to be incorrect or incomplete in terms of the normal text structure. I have translated them as they are while keeping this in mind. If there is any specific context or correction needed for these tags, it would affect the overall understanding and translation accuracy.First, the terms used in the following description will be explained.

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

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

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

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

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

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

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

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

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0034] This invention is an information processing system used by companies to quickly and efficiently grasp market trends and competitive information. This system integrates an information gathering device, a data preprocessing device, a natural language processing device, a report generation device, and an alert generation device. The specific operation of each component is described below.

[0035] First, the server uses information gathering devices to periodically acquire data from various data sources related to the company. This includes news feeds, internal communication channels, and social media. This data is then sent to a preprocessor.

[0036] Next, the server cleans the data collected by the preprocessor and removes noise. Specifically, in the case of text data, it removes extraneous symbols and tags and filters out stop words. This process makes the data suitable for analysis by the natural language processing unit.

[0037] Subsequently, the server uses a natural language processing unit to extract useful information from the preprocessed data. Topic modeling identifies the main themes within the data, and sentiment analysis is performed to evaluate the emotional tone of the data. For example, consumer reactions to a new product on social media can be categorized.

[0038] The extracted information is systematized by the report generation system, and the server generates the final report. Users can receive the generated report and gain detailed insights into specific market trends and competitive information. The report can be output in formats such as PDF and HTML, and can be customized as needed.

[0039] Furthermore, the server utilizes an alert generator to monitor sudden market changes and competitor actions in real time. If certain conditions are met, it immediately sends an alert to the user. This feature allows companies to review their strategies in a timely manner and quickly take necessary actions.

[0040] For example, if a company preparing to launch a new product uses this system, the server collects consumer feedback in the market in real time and provides a report outlining the features consumers are interested in and the areas they want to improve. Furthermore, if the system detects any potential risks from competing products, an alert is immediately sent to the user, allowing for a rapid readjustment of the strategy.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server retrieves information from specified data sources via pre-configured information gathering devices. These data sources include news feeds, internal communication tools, and social media platforms. Information gathering can be done in real time or on an automated, scheduled basis.

[0044] Step 2:

[0045] The server transfers the collected raw data to a data preprocessor for preprocessing. Here, unnecessary noise and inaccurate information are filtered out, and the data is cleaned. Specifically, unnecessary symbols and duplicate information are removed from text data, and the data is formatted into a uniform format.

[0046] Step 3:

[0047] The server analyzes the cleaned data using a natural language processing unit. First, it applies topic modeling algorithms to identify key themes and patterns within the data. Then, it performs sentiment analysis to categorize the opinions and feelings contained in the data into positive, negative, and neutral categories.

[0048] Step 4:

[0049] The server uses a report generation device to assemble a report based on the analysis results from the natural language processing unit. Here, the content is documented, and data visualization (e.g., graphs and charts) is performed as needed. This ensures that the report is output in a clear and easy-to-use format.

[0050] Step 5:

[0051] Users can view the generated reports and customize them to meet specific business needs. They can filter reports based on topics of interest and priorities, and use them as presentation materials for clients or as reference materials for internal strategy meetings.

[0052] Step 6:

[0053] The server uses an alert generator to monitor market and competitor information in real time. When changes are detected in specific conditions or keywords, it quickly generates alerts and immediately notifies users. This allows for immediate response to any anomalies or opportunities.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] For companies to quickly and efficiently grasp market trends and competitive information, they need to accurately collect and analyze vast amounts of data and immediately extract crucial information. However, existing methods have limitations in terms of speed and accuracy, and are particularly poor at responding to real-time changes in the situation. As a result, companies face the challenge of not being able to obtain timely information in order to make rapid decisions.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes means for automatically collecting information from diverse data sources using information gathering means, means for cleaning and preprocessing the collected information, and means for analyzing the preprocessed information using natural language processing techniques to identify key themes and emotional tones and extract important information. This makes it possible to collect and analyze vast amounts of information quickly and accurately, respond to real-time changes in circumstances, and support accurate decision-making.

[0059] "Information gathering means" refers to devices and methods for automatically acquiring information from diverse data sources.

[0060] "Preprocessing means" refers to devices or methods for cleaning collected information and preparing it in a format suitable for analysis.

[0061] "Natural language processing techniques" are algorithms and methods for analyzing text data to identify key themes and emotional tones.

[0062] A "report format" is a means of structuring extracted information and presenting it visually or in a document.

[0063] An "alert generation means" is a device or method that detects changes in real time and provides notifications based on set conditions.

[0064] "Theme identification" is an analytical technique that identifies the main topics present within data.

[0065] "Sentiment analysis" is a technique that evaluates the emotional tone of text data and classifies it into categories such as positive, negative, and neutral.

[0066] "Customizable" means that users have the ability to modify and adjust the generated reports to suit their own needs.

[0067] The information processing system of the present invention is designed to enable companies to quickly and efficiently grasp market trends and competitive information. This system includes information gathering means, preprocessing means, natural language processing technology, report generation means, and alert generation means.

[0068] The server automatically collects information from multiple data sources, including news feeds, social media, and internal communication platforms, using various information gathering methods. In this process, it utilizes web scraping tools and public APIs to retrieve data.

[0069] The collected data is cleaned using preprocessing tools on the server. Specifically, libraries such as Python's pandas and numpy are used to remove unnecessary elements and handle missing values, and NLTK is used for filtering text data.

[0070] Next, natural language processing techniques are used, and the server performs data analysis. Topic modeling using LDA is employed to identify the main theme from the data, and sentiment analysis is performed using VADER and TextBlob to evaluate the emotional tone of the information. This derives the essential content and value of the collected information.

[0071] Subsequently, the extracted information is structured by the server using a report generation mechanism, and a report in a user-friendly format is generated. Since output is possible in PDF and HTML formats via a template engine, documentation is created in a user-friendly format.

[0072] Furthermore, the alert generation mechanism allows the server to monitor changes in specific configured conditions in real time, and immediately notify the user of an alert when an abnormal event is detected.

[0073] As a concrete example, when a company preparing to launch a product into the market uses this system, it can receive an immediate, easy-to-understand report by using a generative AI model, based on prompts such as, "Analyze consumer opinions on the new product in the market and compile the results into a report." This report is customizable by the user and can be adjusted to meet diverse needs.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server collects information from diverse data sources using various data gathering methods. Inputs include news feeds, social media, and URLs and API endpoints of internal platforms. Specifically, the server automatically extracts data using web scraping tools and API calls. The output is a set of collected raw data.

[0077] Step 2:

[0078] The server cleans the collected data using preprocessing tools. The input is a set of raw data. Specifically, it uses Python's pandas and numpy to remove unnecessary symbols and HTML tags from the data and imputes missing values. It uses NLTK to filter for stop words and converts the data into a parseable format. The output is formatted text data.

[0079] Step 3:

[0080] The server analyzes pre-processed data using natural language processing techniques. The input is formatted text data. Specifically, it performs topic modeling using LDA to identify the main themes within the data. It also performs sentiment analysis using VADER and TextBlob to quantify the emotional tone of the data. The output is theme information and sentiment scores.

[0081] Step 4:

[0082] The server creates a report based on information extracted using a report generation method. The inputs are theme information and sentiment scores. Specifically, it utilizes a template engine to systematize the information and output it as a report in PDF or HTML format. The output is a visualized report file.

[0083] Step 5:

[0084] The server uses an alert generation mechanism to monitor status changes in real time based on specific conditions. The input is real-time updated analytical data. Specifically, when the server detects a change that matches the configured conditions, it immediately sends a notification to the user. The output is an alert message, delivered via email or application notification.

[0085] (Application Example 1)

[0086] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] There is a challenge in quickly and efficiently grasping market trends and competitive information, particularly a lack of real-time information necessary for optimizing advertising campaigns. Furthermore, there is a need for advertising professionals to quickly grasp trends and appropriately adjust campaigns.

[0088] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0089] In this invention, the server includes means for collecting data from a data collection device, means for preprocessing the collected data, means for analyzing the preprocessed data using natural language processing technology and extracting important information, means for generating the extracted information in report format, means for generating alerts in real time based on set conditions, and means for analyzing market trends in real time and adjusting advertising campaigns in order to optimize marketing strategies. This enables advertisers to respond immediately to market changes and build optimal advertising strategies.

[0090] A "data acquisition device" is hardware or software used to obtain necessary data from an information source.

[0091] "Preprocessing" refers to the process of removing noise and organizing data in order to prepare collected data into an analyzable format.

[0092] "Natural language processing technology" is a technique that extracts useful meaning and information from text data, enabling topic identification and sentiment analysis.

[0093] "Generating in report format" refers to the process of visualizing extracted information and compiling it into an easily understandable format.

[0094] A "means of generating alerts" is a mechanism that creates a notification when certain conditions are met, alerting the user.

[0095] "Means for optimizing marketing strategies" refers to the process of adjusting advertising and promotional activities based on market trends to achieve effective results.

[0096] "Methods for analyzing market trends in real time" refer to methods for immediately evaluating the latest market information and rapidly detecting changes.

[0097] "Methods for adjusting an advertising campaign" refer to the process of modifying the content and delivery methods to keep the advertising strategy in an optimal state.

[0098] The system for realizing this invention mainly consists of the collaborative operation of a server, a terminal, and a user.

[0099] The server uses information gathering devices to periodically collect relevant information from diverse data sources. The data targets news feeds, social media, and other public sources, and is effectively retrieved using Python and APIs. This ensures that the latest market and competitor information is continuously updated.

[0100] The collected data is processed by a preprocessor on the server to prepare it for analysis. Specifically, Pandas is used to clean the data and remove noise. For text data, unnecessary symbols and tags are removed, and stop words are filtered out.

[0101] The server analyzes the pre-processed data using natural language processing techniques. This process utilizes tools such as NLTK and spaCy to perform topic modeling and sentiment analysis. The analysis clarifies the main themes and sentiment tendencies within the data.

[0102] The extracted information is visualized by the server's report generation system, and reports are generated in HTML or PDF format. These reports can be accessed and customized by marketing personnel using their devices.

[0103] The server also has a device that generates alerts based on set conditions. It detects market changes in real time and sends push notifications to advertisers' terminals at the appropriate time. This enables rapid adjustment of strategies.

[0104] For example, when a new product is launched, the server monitors consumer reactions to that product on social media and provides immediate competitive information as alerts. Advertisers can then quickly adjust their advertising campaigns based on this data.

[0105] The system's operation relies heavily on generative AI models. Examples of prompts include, "Analyze key trends from new market data and identify the strengths of competing products and consumer interests," and "Based on the collected data, suggest optimization strategies for advertising campaigns."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The server collects data from news feeds, social media, and other sources using an API. Input consists of URLs and queries for information sources related to the company. Output is raw text data. The collected data includes market trends and competitive information targeted by this system.

[0109] Step 2:

[0110] The server cleans the collected raw data using a preprocessor. The input is the raw data obtained in step 1. The output is clean text data from which extraneous symbols and stop words have been removed. This makes the data suitable for natural language processing. Specifically, Pandas is used to format the data.

[0111] Step 3:

[0112] The server analyzes the pre-processed data using a natural language processing unit (NLTK). The input is the clean text data obtained in step 2. The output consists of key topics and sentiment scores. NLTK and spaCy are used as natural language processing techniques to perform topic modeling and sentiment analysis. This process extracts important themes and sentiment tendencies from the data.

[0113] Step 4:

[0114] The server generates a visual report using a report generator based on the analyzed data. The input consists of key topics and sentiment scores from Step 3. The output is a report in HTML or PDF format. The report includes visualized data analysis results, serving as foundational material for users developing advertising strategies.

[0115] Step 5:

[0116] The server generates alerts in real time based on configured conditions and sends notifications to the terminal. The input consists of the analysis results from step 3 and the user-configured alert conditions. The output is a push notification to the user's terminal. This ensures that important market changes and competitor movements are immediately communicated to the user. Specifically, webhooks are used to achieve real-time notifications.

[0117] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0118] This invention relates to an information processing system that supports a company's decision-making process, and in particular, it includes an emotion engine that recognizes user emotions and adapts the way information is presented based on those emotions. This system is composed of an integrated information gathering device, a data preprocessing device, a natural language processing device, a report generation device, an alert generation device, and an emotion engine. The specific operation of each component is described below.

[0119] First, the server collects company-related information from news sources, social media, internal messaging tools, etc., through information gathering devices. This data is then cleaned by a data preprocessor to remove noise and convert it into a format suitable for analysis.

[0120] Next, the pre-processed data is sent by the server to a natural language processing unit, where it is analyzed using topic modeling and sentiment analysis. This extracts important market trends and competitive information.

[0121] The extracted information is formatted as a report by a report generation device. For example, the server generates graphical reports that summarize market trends and highlight potential crisis factors. Furthermore, the generated reports can be customized according to user requests, and their content can be adjusted based on specific indicators or areas of interest.

[0122] Furthermore, the emotion engine, a key feature of this invention, operates on a server and recognizes the user's emotional state by analyzing the user's operation history and input data. This emotional information is used to adjust how reports are presented and when alerts are generated. For example, if a user is stressed, the report content can be simplified, and alert notifications can be suppressed or postponed.

[0123] The emotion engine also obtains real-time feedback from users and optimizes the alert generation process. Such capabilities enable companies to respond quickly to rapid market changes and competitive landscapes while reducing the psychological burden on users.

[0124] For example, in the case of a company planning a new market acquisition campaign, the server utilizes an emotion engine to detect the marketing manager's emotional state and optimize how the analysis results are presented. In particular, if high stress levels are detected, the report can be summarized and presented with a narrower selection of strategic options to support the manager's decision-making.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The server collects data from the internet and the internal network using information gathering devices. At this stage, it continuously retrieves news feeds, social media data, and internal messaging data using APIs.

[0128] Step 2:

[0129] The server cleans the data collected by the data preprocessor, removing unnecessary information and noise. Specifically, it removes HTML tags and non-ASCII characters from text data and filters out stop words.

[0130] Step 3:

[0131] The server analyzes pre-processed data via a natural language processing unit. Topic modeling is used to identify key themes, and sentiment analysis determines the emotional tendencies of the data. Based on these results, the server extracts market trends and competitive information.

[0132] Step 4:

[0133] The server integrates the analysis results obtained from the report generation device into a report format. Here, it generates graphs and charts to make the information visually easy to understand and highlights important data points.

[0134] Step 5:

[0135] Users receive the generated reports on their devices and customize them as needed. They can edit and filter the report content according to their interests and work priorities.

[0136] Step 6:

[0137] The server uses an emotion engine to analyze the user's operation history and input data to recognize the user's emotions. Based on the emotional state, it dynamically adjusts how reports are displayed and the frequency of alerts.

[0138] Step 7:

[0139] The server uses an alert generator to send real-time alerts to the user under configured conditions. Based on the user's emotional state, it prioritizes which alerts to send and adjusts the timing of notifications to reduce stress.

[0140] Step 8:

[0141] Users review alerts and reports received on their devices and select the actions necessary for decision-making. Based on the information provided by the emotion engine, they can quickly determine the optimal strategy.

[0142] (Example 2)

[0143] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0144] In today's information society, companies need to make quick and accurate critical decisions from vast amounts of data. However, efficiently extracting necessary information from information overload and adjusting it according to the user's situation is not easy. In particular, it is necessary to present appropriate information while considering the user's emotions. As a result, the problem is that information overload and misunderstandings can lead to delayed or inefficient decision-making.

[0145] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0146] In this invention, the server includes means for collecting data from information sources using information gathering means, means for processing the data to remove noise and convert it into a format suitable for analysis, and means for analyzing the processed data using natural language processing technology to extract important market information. This makes it possible to provide users with appropriate and optimized information based on their emotions, thereby improving the quality of decision-making.

[0147] "Information gathering means" refers to a device or process for collecting relevant data from an information source.

[0148] "Processing means" refers to a function that digitally processes the collected data to remove noise and convert it into a format suitable for analysis.

[0149] "Natural language processing technology" refers to techniques that analyze text data and extract its internal structure and meaning, and specifically include topic modeling and sentiment analysis.

[0150] A "document format creation method" is a function that organizes extracted information and generates a document to provide it in a format that is easy for users to understand.

[0151] "Emotion recognition means" refers to a technology or device for detecting a user's emotional state and adjusting the method of presenting information or generating warnings based on that state.

[0152] A "warning generation mechanism" is a function that notifies the user of a warning in real time when set conditions are met.

[0153] "User" refers to a person or organization that receives the system's output and makes decisions based on that information.

[0154] This invention is an information processing system that supports corporate decision-making, and in particular aims to recognize the emotions of users and optimize the way information is presented based on those emotions. The system is configured as follows:

[0155] The server uses information gathering tools to collect data from sources such as news feeds, social media platforms, and internal messaging systems. This step typically involves using humanoid web scraping tools or APIs. The collected data is stored as raw data.

[0156] Next, the server preprocesses the collected raw data using data processing tools. Specifically, it removes unnecessary noise and missing values ​​and standardizes the data. This process is often performed using data processing libraries such as Pandas or NumPy.

[0157] The preprocessed data is then analyzed by the server using natural language processing techniques. Here, topic modeling techniques (e.g., Latent Dirichlet Allocation) and sentiment analysis (e.g., VADER) are used to extract important information and sentiment trends from the data. This process is performed using natural language processing libraries such as NLTK and Spacy.

[0158] Based on the extracted information, the server generates a document-format report. The report includes visual graphs and summary text, designed for easy user understanding. Libraries such as Matplotlib and ReportLab are used for report generation.

[0159] Furthermore, the server uses emotion recognition to analyze the user's operation history and input data to recognize the user's emotional state. This recognition information is reflected in and optimized for how information is presented and when warnings are generated. Specifically, if the user is experiencing stress, the report can be simplified and warning notifications can be postponed.

[0160] For example, when a company is trying to acquire a new market, the server can use an emotion engine to detect the emotional state of the marketer and optimize the presentation of analysis results. For instance, it can support the marketer's decision-making by providing information based on prompts to a generative AI model, such as "Explain how a company's emotion engine influences the decision-making process."

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] The server collects data from news feeds, social media, internal messaging systems, and other sources using information gathering methods. At this stage, the input is the various information sources to be collected, and the output is a raw dataset. Specifically, it uses web scraping techniques and APIs to periodically check each information source for new data and automatically extracts the necessary data.

[0164] Step 2:

[0165] The server preprocesses the collected raw data using data processing tools. The input is a raw dataset, and the output is clean and structured data. This processing uses dataframe libraries such as Pandas to remove duplicate data and adjust the format. Specifically, it removes HTML tags and standardizes date formats.

[0166] Step 3:

[0167] The server analyzes pre-processed data using natural language processing techniques. The input is structured data, and the output is important topics and their sentiment analysis results. In this step, NLTK and Spacy are used to perform topic modeling and sentiment analysis of the text, extracting highly relevant topics and positive / negative sentiments.

[0168] Step 4:

[0169] The server generates a document using a report generation tool based on the analysis results. The input is the analysis results, and the output is a visual summary report. Graphs are created using tools such as Matplotlib, and then assembled into a PDF report using ReportLab. Specifically, it creates a concise summary of important topics and saves it as a report along with the visualized data.

[0170] Step 5:

[0171] The server analyzes the user's emotional state using emotion recognition tools. Inputs are the user's operation history and input data, while outputs are information about the user's emotional state. A machine learning model is used to estimate emotions based on past user behavior data. Specifically, stress levels are evaluated from the user's click history and search keywords.

[0172] Step 6:

[0173] Users receive generated reports and alerts to aid in decision-making. The input is the final report and alert presented to the user, and the output is the improvement in decision-making. The server adjusts how reports are presented and the importance of alerts based on the user's emotional state. For example, if the user is under high stress, the report is made more concise and alerts are delayed to reduce the burden.

[0174] (Application Example 2)

[0175] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0176] The challenge in a company's decision-making process is to reduce the psychological burden on users and support more effective decision-making by appropriately recognizing their emotions and adjusting the way information is presented based on those emotions. Furthermore, there is a need to understand the emotional state of customers in physical stores in real time and provide appropriate customer service based on that understanding.

[0177] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0178] In this invention, the server includes means for acquiring information from information gathering means, means for preprocessing the acquired information, and means for analyzing the preprocessed information using language processing technology and extracting important information. This allows for adjusting the method of presenting information based on the user's emotional state, enabling customer service tailored to the emotional state of visitors in physical stores.

[0179] "Information gathering means" refers to the function that a system uses to acquire data from external sources.

[0180] "Preprocessing" refers to the act of performing initial processing to convert collected information into a format suitable for analysis.

[0181] "Language processing technology" is a technique that analyzes natural language text and extracts meaning and emotion from the information.

[0182] A "report format" is a method of organizing and presenting extracted information visually or in writing.

[0183] A "means for generating an immediate warning" refers to a function that quickly issues a warning when certain conditions are met.

[0184] "Emotional state" refers to the state that represents the psychological reactions and emotions of users or customers.

[0185] "Means of adjusting the method of information presentation" refers to the ability to change the content and format of information presented according to the user's emotional state.

[0186] In an embodiment of this invention, a server constructs a system equipped with information gathering means, preprocessing means, and language processing technology. First, the server uses the information gathering means to acquire company-related information from external sources. This information includes news, social media, customer feedback, etc. The acquired information is cleaned through the preprocessing means and converted into a format suitable for analysis. By removing noise and unnecessary parts, the data is ready for analysis.

[0187] Next, the pre-processed data is analyzed using natural language processing techniques. This process involves thematic modeling and sentiment analysis to extract market trends and customer emotional states from the information. For sentiment analysis, an emotion engine operates to recognize the user's emotional state in real time, determining their psychological state based on user input and past operation history.

[0188] The server organizes the extracted information into a report format and presents it to the user's terminal. The way information is presented is automatically adjusted according to the user's emotional state. For example, if the user is feeling stressed, the information can be summarized concisely and presented in a more easily understandable format. Furthermore, if the customer is using a device such as a robot or smart glasses, emotionally-based recommendations are provided in real time.

[0189] For example, a store employee wearing smart glasses can understand the customer's emotional state and strive to provide calm and attentive service. This function leads to improved customer satisfaction and more efficient service delivery.

[0190] An example of a prompt message could be: "If the customer is deemed interested, the staff should calmly provide customer service and recommend offering a tasting." This enables user-centric interaction.

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The server acquires information from news sources and social media using information gathering methods. The input is publicly available data obtained through the network, and the output is raw, unprocessed data. In this process, APIs and scraping techniques are used to efficiently collect information.

[0194] Step 2:

[0195] The server cleans the raw data obtained using preprocessing tools. The input to this process is the raw data obtained in step 1, and the output is formatted data with noise removed. Specifically, this process includes text normalization, correction of typos, and standardization of formatting.

[0196] Step 3:

[0197] The server applies language processing techniques to the formatted data and performs thematic modeling and sentiment analysis. The input is the formatted data obtained in step 2, and the output is thematic information and data on the user's emotional state extracted through the analysis. In this step, a machine learning model is used to classify the sentiment categories.

[0198] Step 4:

[0199] The server organizes the extracted information into a report format and presents it to the user's terminal. The input is the subject information and emotional state data from the analysis in step 3, and the output is a visually organized report document. The appropriate method of presenting the information is selected according to the user's emotions.

[0200] Step 5:

[0201] The user terminal provides appropriate recommendations and guidance based on the user's emotional state identified by the emotion engine. The input is emotional state data from step 3, and the output is situation-appropriate actions and self-improvement advice provided to the user. Specific actions include immediate notifications to the user and information display on the screen.

[0202] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0203] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0204] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0208] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0209] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0210] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0211] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0212] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0213] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0214] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0215] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0216] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0217] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0218] This invention is an information processing system used by companies to quickly and efficiently grasp market trends and competitive information. This system integrates an information gathering device, a data preprocessing device, a natural language processing device, a report generation device, and an alert generation device. The specific operation of each component is described below.

[0219] First, the server uses information gathering devices to periodically acquire data from various data sources related to the company. This includes news feeds, internal communication channels, and social media. This data is then sent to a preprocessor.

[0220] Next, the server cleans the data collected by the preprocessor and removes noise. Specifically, in the case of text data, it removes extraneous symbols and tags and filters out stop words. This process makes the data suitable for analysis by the natural language processing unit.

[0221] Subsequently, the server uses a natural language processing unit to extract useful information from the preprocessed data. Topic modeling identifies the main themes within the data, and sentiment analysis is performed to evaluate the emotional tone of the data. For example, consumer reactions to a new product on social media can be categorized.

[0222] The extracted information is systematized by the report generation system, and the server generates the final report. Users can receive the generated report and gain detailed insights into specific market trends and competitive information. The report can be output in formats such as PDF and HTML, and can be customized as needed.

[0223] Furthermore, the server utilizes an alert generator to monitor sudden market changes and competitor actions in real time. If certain conditions are met, it immediately sends an alert to the user. This feature allows companies to review their strategies in a timely manner and quickly take necessary actions.

[0224] For example, if a company preparing to launch a new product uses this system, the server collects consumer feedback in the market in real time and provides a report outlining the features consumers are interested in and the areas they want to improve. Furthermore, if the system detects any potential risks from competing products, an alert is immediately sent to the user, allowing for a rapid readjustment of the strategy.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The server retrieves information from specified data sources via pre-configured information gathering devices. These data sources include news feeds, internal communication tools, and social media platforms. Information gathering can be done in real time or on an automated, scheduled basis.

[0228] Step 2:

[0229] The server transfers the collected raw data to a data preprocessor for preprocessing. Here, unnecessary noise and inaccurate information are filtered out, and the data is cleaned. Specifically, unnecessary symbols and duplicate information are removed from text data, and the data is formatted into a uniform format.

[0230] Step 3:

[0231] The server analyzes the cleaned data using a natural language processing unit. First, it applies topic modeling algorithms to identify key themes and patterns within the data. Then, it performs sentiment analysis to categorize the opinions and feelings contained in the data into positive, negative, and neutral categories.

[0232] Step 4:

[0233] The server uses a report generation device to assemble a report based on the analysis results from the natural language processing unit. Here, the content is documented, and data visualization (e.g., graphs and charts) is performed as needed. This ensures that the report is output in a clear and easy-to-use format.

[0234] Step 5:

[0235] Users can view the generated reports and customize them to meet specific business needs. They can filter reports based on topics of interest and priorities, and use them as presentation materials for clients or as reference materials for internal strategy meetings.

[0236] Step 6:

[0237] The server uses an alert generator to monitor market and competitor information in real time. When changes are detected in specific conditions or keywords, it quickly generates alerts and immediately notifies users. This allows for immediate response to any anomalies or opportunities.

[0238] (Example 1)

[0239] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0240] For companies to quickly and efficiently grasp market trends and competitive information, they need to accurately collect and analyze vast amounts of data and immediately extract crucial information. However, existing methods have limitations in terms of speed and accuracy, and are particularly poor at responding to real-time changes in the situation. As a result, companies face the challenge of not being able to obtain timely information in order to make rapid decisions.

[0241] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0242] In this invention, the server includes means for automatically collecting information from diverse data sources using information gathering means, means for cleaning and preprocessing the collected information, and means for analyzing the preprocessed information using natural language processing techniques to identify key themes and emotional tones and extract important information. This makes it possible to collect and analyze vast amounts of information quickly and accurately, respond to real-time changes in circumstances, and support accurate decision-making.

[0243] "Information gathering means" refers to devices and methods for automatically acquiring information from diverse data sources.

[0244] "Preprocessing means" refers to devices or methods for cleaning collected information and preparing it in a format suitable for analysis.

[0245] "Natural language processing techniques" are algorithms and methods for analyzing text data to identify key themes and emotional tones.

[0246] A "report format" is a means of structuring extracted information and presenting it visually or in a document.

[0247] An "alert generation means" is a device or method that detects changes in real time and provides notifications based on set conditions.

[0248] "Theme identification" is an analytical technique that identifies the main topics present within data.

[0249] "Sentiment analysis" is a technique that evaluates the emotional tone of text data and classifies it into categories such as positive, negative, and neutral.

[0250] "Customizable" means that users have the ability to modify and adjust the generated reports to suit their own needs.

[0251] The information processing system of the present invention is designed to enable companies to quickly and efficiently grasp market trends and competitive information. This system includes information gathering means, preprocessing means, natural language processing technology, report generation means, and alert generation means.

[0252] The server automatically collects information from multiple data sources, including news feeds, social media, and internal communication platforms, using various information gathering methods. In this process, it utilizes web scraping tools and public APIs to retrieve data.

[0253] The collected data is cleaned using preprocessing tools on the server. Specifically, libraries such as Python's pandas and numpy are used to remove unnecessary elements and handle missing values, and NLTK is used for filtering text data.

[0254] Next, natural language processing techniques are used, and the server performs data analysis. Topic modeling using LDA is employed to identify the main theme from the data, and sentiment analysis is performed using VADER and TextBlob to evaluate the emotional tone of the information. This derives the essential content and value of the collected information.

[0255] Subsequently, the extracted information is structured by the server using a report generation mechanism, and a report in a user-friendly format is generated. Since output is possible in PDF and HTML formats via a template engine, documentation is created in a user-friendly format.

[0256] Furthermore, the alert generation mechanism allows the server to monitor changes in specific configured conditions in real time, and immediately notify the user of an alert when an abnormal event is detected.

[0257] As a concrete example, when a company preparing to launch a product into the market uses this system, it can receive an immediate, easy-to-understand report by using a generative AI model, based on prompts such as, "Analyze consumer opinions on the new product in the market and compile the results into a report." This report is customizable by the user and can be adjusted to meet diverse needs.

[0258] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0259] Step 1:

[0260] The server collects information from diverse data sources using various data gathering methods. Inputs include news feeds, social media, and URLs and API endpoints of internal platforms. Specifically, the server automatically extracts data using web scraping tools and API calls. The output is a set of collected raw data.

[0261] Step 2:

[0262] The server cleans the collected data using preprocessing tools. The input is a set of raw data. Specifically, it uses Python's pandas and numpy to remove unnecessary symbols and HTML tags from the data and imputes missing values. It uses NLTK to filter for stop words and converts the data into a parseable format. The output is formatted text data.

[0263] Step 3:

[0264] The server analyzes pre-processed data using natural language processing techniques. The input is formatted text data. Specifically, it performs topic modeling using LDA to identify the main themes within the data. It also performs sentiment analysis using VADER and TextBlob to quantify the emotional tone of the data. The output is theme information and sentiment scores.

[0265] Step 4:

[0266] The server creates a report based on information extracted using a report generation method. The inputs are theme information and sentiment scores. Specifically, it utilizes a template engine to systematize the information and output it as a report in PDF or HTML format. The output is a visualized report file.

[0267] Step 5:

[0268] The server uses an alert generation mechanism to monitor status changes in real time based on specific conditions. The input is real-time updated analytical data. Specifically, when the server detects a change that matches the configured conditions, it immediately sends a notification to the user. The output is an alert message, delivered via email or application notification.

[0269] (Application Example 1)

[0270] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0271] There is a challenge in quickly and efficiently grasping market trends and competitive information, particularly a lack of real-time information necessary for optimizing advertising campaigns. Furthermore, there is a need for advertising professionals to quickly grasp trends and appropriately adjust campaigns.

[0272] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0273] In this invention, the server includes means for collecting data from a data collection device, means for preprocessing the collected data, means for analyzing the preprocessed data using natural language processing technology and extracting important information, means for generating the extracted information in report format, means for generating alerts in real time based on set conditions, and means for analyzing market trends in real time and adjusting advertising campaigns in order to optimize marketing strategies. This enables advertisers to respond immediately to market changes and build optimal advertising strategies.

[0274] A "data acquisition device" is hardware or software used to obtain necessary data from an information source.

[0275] "Preprocessing" refers to the process of removing noise and organizing data in order to prepare collected data into an analyzable format.

[0276] "Natural language processing technology" is a technique that extracts useful meaning and information from text data, enabling topic identification and sentiment analysis.

[0277] "Generating in report format" refers to the process of visualizing extracted information and compiling it into an easily understandable format.

[0278] A "means of generating alerts" is a mechanism that creates a notification when certain conditions are met, alerting the user.

[0279] "Means for optimizing marketing strategies" refers to the process of adjusting advertising and promotional activities based on market trends to achieve effective results.

[0280] "Methods for analyzing market trends in real time" refer to methods for immediately evaluating the latest market information and rapidly detecting changes.

[0281] "Means for adjusting an advertising campaign" is a process of modifying the content and distribution method to keep the advertising strategy in an optimal state.

[0282] The system for realizing this invention is mainly composed of the collaborative operations of a server, a terminal, and a user.

[0283] The server uses an information collection device to regularly collect relevant information from various data sources. The data targets news feeds, social media, and other public information sources, and is effectively obtained using Python and APIs. As a result, the latest market and competitive information is sequentially updated.

[0284] The collected data is prepared in an analyzable format by a preprocessing device within the server. Specifically, Pandas is used to clean the data and remove noise. For text data, unnecessary symbols and tags are removed, and stop words are filtered.

[0285] The server analyzes the preprocessed data by leveraging natural language processing techniques. In this process, tools such as NLTK and spaCy are used to perform topic modeling and sentiment analysis. Through the analysis, the main themes and emotional trends within the data are clarified.

[0286] The extracted information is visualized by the report generation device of the server, and reports are generated in HTML or PDF format. This report can be accessed by the terminals used by marketing staff and can also be customized.

[0287] The server further has a device that generates alerts based on set conditions. It detects changes in the market in real-time and sends push notifications to the terminals of advertising staff at appropriate times. This enables rapid adjustment of strategies.

[0288] For example, when a new product is launched, the server monitors consumer reactions to that product on social media and provides immediate competitive information as alerts. Advertisers can then quickly adjust their advertising campaigns based on this data.

[0289] The system's operation relies heavily on generative AI models. Examples of prompts include, "Analyze key trends from new market data and identify the strengths of competing products and consumer interests," and "Based on the collected data, suggest optimization strategies for advertising campaigns."

[0290] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0291] Step 1:

[0292] The server collects data from news feeds, social media, and other sources using an API. Input consists of URLs and queries for information sources related to the company. Output is raw text data. The collected data includes market trends and competitive information targeted by this system.

[0293] Step 2:

[0294] The server cleans the collected raw data using a preprocessor. The input is the raw data obtained in step 1. The output is clean text data from which extraneous symbols and stop words have been removed. This makes the data suitable for natural language processing. Specifically, Pandas is used to format the data.

[0295] Step 3:

[0296] The server analyzes the pre-processed data using a natural language processing unit (NLTK). The input is the clean text data obtained in step 2. The output consists of key topics and sentiment scores. NLTK and spaCy are used as natural language processing techniques to perform topic modeling and sentiment analysis. This process extracts important themes and sentiment tendencies from the data.

[0297] Step 4:

[0298] The server generates a visual report using a report generator based on the analyzed data. The input consists of key topics and sentiment scores from Step 3. The output is a report in HTML or PDF format. The report includes visualized data analysis results, serving as foundational material for users developing advertising strategies.

[0299] Step 5:

[0300] The server generates alerts in real time based on configured conditions and sends notifications to the terminal. The input consists of the analysis results from step 3 and the user-configured alert conditions. The output is a push notification to the user's terminal. This ensures that important market changes and competitor movements are immediately communicated to the user. Specifically, webhooks are used to achieve real-time notifications.

[0301] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0302] This invention relates to an information processing system that supports a company's decision-making process, and in particular, it includes an emotion engine that recognizes user emotions and adapts the way information is presented based on those emotions. This system is composed of an integrated information gathering device, a data preprocessing device, a natural language processing device, a report generation device, an alert generation device, and an emotion engine. The specific operation of each component is described below.

[0303] First, the server collects information related to the company from news, social media, in-house messaging tools, etc. through an information collection device. This data is cleaned by a data preprocessing device and converted into a form suitable for analysis by removing noise.

[0304] Next, the preprocessed data is sent by the server to a natural language processing device, and the data is analyzed using topic modeling and sentiment analysis. As a result, important market trends and competitive information are extracted.

[0305] The extracted information is formalized as a report by a report generation device. For example, the server generates a graphical report highlighting summaries of market trends and potential crisis factors. Also, the generated report can be customized according to the user's desires, and the content can be adjusted based on specific indicators or areas of interest.

[0306] Furthermore, the emotion engine, which is a feature of the present invention, operates on the server to recognize the user's emotional state by analyzing the user's operation history and input data. This emotion information is used to adjust the presentation method of the report and the generation timing of alerts. For example, when the user is in a stressed state, the report content can be simplified, and alert notifications can be suppressed or postponed.

[0307] The emotion engine also obtains real-time feedback from the user and optimizes the alert generation process. With such a function, the company can quickly respond to rapid changes in the market and competitive situations while reducing the user's psychological burden.

[0308] For example, in the case of a company planning a new market acquisition campaign, the server utilizes an emotion engine to detect the marketing manager's emotional state and optimize how the analysis results are presented. In particular, if high stress levels are detected, the report can be summarized and presented with a narrower selection of strategic options to support the manager's decision-making.

[0309] The following describes the processing flow.

[0310] Step 1:

[0311] The server collects data from the internet and the internal network using information gathering devices. At this stage, it continuously retrieves news feeds, social media data, and internal messaging data using APIs.

[0312] Step 2:

[0313] The server cleans the data collected by the data preprocessor, removing unnecessary information and noise. Specifically, it removes HTML tags and non-ASCII characters from text data and filters out stop words.

[0314] Step 3:

[0315] The server analyzes pre-processed data via a natural language processing unit. Topic modeling is used to identify key themes, and sentiment analysis determines the emotional tendencies of the data. Based on these results, the server extracts market trends and competitive information.

[0316] Step 4:

[0317] The server integrates the analysis results obtained from the report generation device into a report format. Here, it generates graphs and charts to make the information visually easy to understand and highlights important data points.

[0318] Step 5:

[0319] Users receive the generated reports on their devices and customize them as needed. They can edit and filter the report content according to their interests and work priorities.

[0320] Step 6:

[0321] The server uses an emotion engine to analyze the user's operation history and input data to recognize the user's emotions. Based on the emotional state, it dynamically adjusts how reports are displayed and the frequency of alerts.

[0322] Step 7:

[0323] The server uses an alert generator to send real-time alerts to the user under configured conditions. Based on the user's emotional state, it prioritizes which alerts to send and adjusts the timing of notifications to reduce stress.

[0324] Step 8:

[0325] Users review alerts and reports received on their devices and select the actions necessary for decision-making. Based on the information provided by the emotion engine, they can quickly determine the optimal strategy.

[0326] (Example 2)

[0327] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0328] In today's information society, companies need to make quick and accurate critical decisions from vast amounts of data. However, efficiently extracting necessary information from information overload and adjusting it according to the user's situation is not easy. In particular, it is necessary to present appropriate information while considering the user's emotions. As a result, the problem is that information overload and misunderstandings can lead to delayed or inefficient decision-making.

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

[0330] In this invention, the server includes means for collecting data from information sources using information gathering means, means for processing the data to remove noise and convert it into a format suitable for analysis, and means for analyzing the processed data using natural language processing technology to extract important market information. This makes it possible to provide users with appropriate and optimized information based on their emotions, thereby improving the quality of decision-making.

[0331] "Information gathering means" refers to a device or process for collecting relevant data from an information source.

[0332] "Processing means" refers to a function that digitally processes the collected data to remove noise and convert it into a format suitable for analysis.

[0333] "Natural language processing technology" refers to techniques that analyze text data and extract its internal structure and meaning, and specifically include topic modeling and sentiment analysis.

[0334] A "document format creation method" is a function that organizes extracted information and generates a document to provide it in a format that is easy for users to understand.

[0335] "Emotion recognition means" refers to a technology or device for detecting a user's emotional state and adjusting the method of presenting information or generating warnings based on that state.

[0336] A "warning generation mechanism" is a function that notifies the user of a warning in real time when set conditions are met.

[0337] "User" refers to a person or organization that receives the system's output and makes decisions based on that information.

[0338] This invention is an information processing system that supports corporate decision-making, and in particular aims to recognize the emotions of users and optimize the way information is presented based on those emotions. The system is configured as follows:

[0339] The server uses information gathering tools to collect data from sources such as news feeds, social media platforms, and internal messaging systems. This step typically involves using humanoid web scraping tools or APIs. The collected data is stored as raw data.

[0340] Next, the server preprocesses the collected raw data using data processing tools. Specifically, it removes unnecessary noise and missing values ​​and standardizes the data. This process is often performed using data processing libraries such as Pandas or NumPy.

[0341] The preprocessed data is then analyzed by the server using natural language processing techniques. Here, topic modeling techniques (e.g., Latent Dirichlet Allocation) and sentiment analysis (e.g., VADER) are used to extract important information and sentiment trends from the data. This process is performed using natural language processing libraries such as NLTK and Spacy.

[0342] Based on the extracted information, the server generates a document-format report. The report includes visual graphs and summary text, designed for easy user understanding. Libraries such as Matplotlib and ReportLab are used for report generation.

[0343] Furthermore, the server uses emotion recognition to analyze the user's operation history and input data to recognize the user's emotional state. This recognition information is reflected in and optimized for how information is presented and when warnings are generated. Specifically, if the user is experiencing stress, the report can be simplified and warning notifications can be postponed.

[0344] For example, when a company is trying to acquire a new market, the server can use an emotion engine to detect the emotional state of the marketer and optimize the presentation of analysis results. For instance, it can support the marketer's decision-making by providing information based on prompts to a generative AI model, such as "Explain how a company's emotion engine influences the decision-making process."

[0345] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0346] Step 1:

[0347] The server collects data from news feeds, social media, internal messaging systems, and other sources using information gathering methods. At this stage, the input is the various information sources to be collected, and the output is a raw dataset. Specifically, it uses web scraping techniques and APIs to periodically check each information source for new data and automatically extracts the necessary data.

[0348] Step 2:

[0349] The server preprocesses the collected raw data using data processing tools. The input is a raw dataset, and the output is clean and structured data. This processing uses dataframe libraries such as Pandas to remove duplicate data and adjust the format. Specifically, it removes HTML tags and standardizes date formats.

[0350] Step 3:

[0351] The server analyzes pre-processed data using natural language processing techniques. The input is structured data, and the output is important topics and their sentiment analysis results. In this step, NLTK and Spacy are used to perform topic modeling and sentiment analysis of the text, extracting highly relevant topics and positive / negative sentiments.

[0352] Step 4:

[0353] The server generates a document using a report generation tool based on the analysis results. The input is the analysis results, and the output is a visual summary report. Graphs are created using tools such as Matplotlib, and then assembled into a PDF report using ReportLab. Specifically, it creates a concise summary of important topics and saves it as a report along with the visualized data.

[0354] Step 5:

[0355] The server analyzes the user's emotional state using emotion recognition tools. Inputs are the user's operation history and input data, while outputs are information about the user's emotional state. A machine learning model is used to estimate emotions based on past user behavior data. Specifically, stress levels are evaluated from the user's click history and search keywords.

[0356] Step 6:

[0357] Users receive generated reports and alerts to aid in decision-making. The input is the final report and alert presented to the user, and the output is the improvement in decision-making. The server adjusts how reports are presented and the importance of alerts based on the user's emotional state. For example, if the user is under high stress, the report is made more concise and alerts are delayed to reduce the burden.

[0358] (Application Example 2)

[0359] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0360] The challenge in a company's decision-making process is to reduce the psychological burden on users and support more effective decision-making by appropriately recognizing their emotions and adjusting the way information is presented based on those emotions. Furthermore, there is a need to understand the emotional state of customers in physical stores in real time and provide appropriate customer service based on that understanding.

[0361] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0362] In this invention, the server includes means for acquiring information from information gathering means, means for preprocessing the acquired information, and means for analyzing the preprocessed information using language processing technology and extracting important information. This allows for adjusting the method of presenting information based on the user's emotional state, enabling customer service tailored to the emotional state of visitors in physical stores.

[0363] "Information gathering means" refers to the function that a system uses to acquire data from external sources.

[0364] "Preprocessing" refers to the act of performing initial processing to convert collected information into a format suitable for analysis.

[0365] "Language processing technology" is a technique that analyzes natural language text and extracts meaning and emotion from the information.

[0366] A "report format" is a method of organizing and presenting extracted information visually or in writing.

[0367] A "means for generating an immediate warning" refers to a function that quickly issues a warning when certain conditions are met.

[0368] "Emotional state" refers to the state that represents the psychological reactions and emotions of users or customers.

[0369] "Means of adjusting the method of information presentation" refers to the ability to change the content and format of information presented according to the user's emotional state.

[0370] In an embodiment of this invention, a server constructs a system equipped with information gathering means, preprocessing means, and language processing technology. First, the server uses the information gathering means to acquire company-related information from external sources. This information includes news, social media, customer feedback, etc. The acquired information is cleaned through the preprocessing means and converted into a format suitable for analysis. By removing noise and unnecessary parts, the data is ready for analysis.

[0371] Next, the pre-processed data is analyzed using natural language processing techniques. This process involves thematic modeling and sentiment analysis to extract market trends and customer emotional states from the information. For sentiment analysis, an emotion engine operates to recognize the user's emotional state in real time, determining their psychological state based on user input and past operation history.

[0372] The server organizes the extracted information into a report format and presents it to the user's terminal. The way information is presented is automatically adjusted according to the user's emotional state. For example, if the user is feeling stressed, the information can be summarized concisely and presented in a more easily understandable format. Furthermore, if the customer is using a device such as a robot or smart glasses, emotionally-based recommendations are provided in real time.

[0373] For example, a store employee wearing smart glasses can understand the customer's emotional state and strive to provide calm and attentive service. This function leads to improved customer satisfaction and more efficient service delivery.

[0374] An example of a prompt message could be: "If the customer is deemed interested, the staff should calmly provide customer service and recommend offering a tasting." This enables user-centric interaction.

[0375] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0376] Step 1:

[0377] The server acquires information from news sources and social media using information gathering methods. The input is publicly available data obtained through the network, and the output is raw, unprocessed data. In this process, APIs and scraping techniques are used to efficiently collect information.

[0378] Step 2:

[0379] The server cleans the raw data obtained using preprocessing tools. The input to this process is the raw data obtained in step 1, and the output is formatted data with noise removed. Specifically, this process includes text normalization, correction of typos, and standardization of formatting.

[0380] Step 3:

[0381] The server applies language processing techniques to the formatted data and performs thematic modeling and sentiment analysis. The input is the formatted data obtained in step 2, and the output is thematic information and data on the user's emotional state extracted through the analysis. In this step, a machine learning model is used to classify the sentiment categories.

[0382] Step 4:

[0383] The server organizes the extracted information into a report format and presents it to the user's terminal. The input is the subject information and emotional state data from the analysis in step 3, and the output is a visually organized report document. The appropriate method of presenting the information is selected according to the user's emotions.

[0384] Step 5:

[0385] The user terminal provides appropriate recommendations and guidance based on the user's emotional state identified by the emotion engine. The input is emotional state data from step 3, and the output is situation-appropriate actions and self-improvement advice provided to the user. Specific actions include immediate notifications to the user and information display on the screen.

[0386] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0387] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0388] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0389] [Third Embodiment]

[0390] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0391] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0392] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0393] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0394] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0395] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0396] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0397] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0398] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0399] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0400] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0401] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0402] This invention is an information processing system used by companies to quickly and efficiently grasp market trends and competitive information. This system integrates an information gathering device, a data preprocessing device, a natural language processing device, a report generation device, and an alert generation device. The specific operation of each component is described below.

[0403] First, the server uses information gathering devices to periodically acquire data from various data sources related to the company. This includes news feeds, internal communication channels, and social media. This data is then sent to a preprocessor.

[0404] Next, the server cleans the data collected by the preprocessor and removes noise. Specifically, in the case of text data, it removes extraneous symbols and tags and filters out stop words. This process makes the data suitable for analysis by the natural language processing unit.

[0405] Subsequently, the server uses a natural language processing unit to extract useful information from the preprocessed data. Topic modeling identifies the main themes within the data, and sentiment analysis is performed to evaluate the emotional tone of the data. For example, consumer reactions to a new product on social media can be categorized.

[0406] The extracted information is systematized by the report generation system, and the server generates the final report. Users can receive the generated report and gain detailed insights into specific market trends and competitive information. The report can be output in formats such as PDF and HTML, and can be customized as needed.

[0407] Furthermore, the server utilizes an alert generator to monitor sudden market changes and competitor actions in real time. If certain conditions are met, it immediately sends an alert to the user. This feature allows companies to review their strategies in a timely manner and quickly take necessary actions.

[0408] For example, if a company preparing to launch a new product uses this system, the server collects consumer feedback in the market in real time and provides a report outlining the features consumers are interested in and the areas they want to improve. Furthermore, if the system detects any potential risks from competing products, an alert is immediately sent to the user, allowing for a rapid readjustment of the strategy.

[0409] The following describes the processing flow.

[0410] Step 1:

[0411] The server retrieves information from specified data sources via pre-configured information gathering devices. These data sources include news feeds, internal communication tools, and social media platforms. Information gathering can be done in real time or on an automated, scheduled basis.

[0412] Step 2:

[0413] The server transfers the collected raw data to a data preprocessor for preprocessing. Here, unnecessary noise and inaccurate information are filtered out, and the data is cleaned. Specifically, unnecessary symbols and duplicate information are removed from text data, and the data is formatted into a uniform format.

[0414] Step 3:

[0415] The server analyzes the cleaned data using a natural language processing unit. First, it applies topic modeling algorithms to identify key themes and patterns within the data. Then, it performs sentiment analysis to categorize the opinions and feelings contained in the data into positive, negative, and neutral categories.

[0416] Step 4:

[0417] The server uses a report generation device to assemble a report based on the analysis results from the natural language processing unit. Here, the content is documented, and data visualization (e.g., graphs and charts) is performed as needed. This ensures that the report is output in a clear and easy-to-use format.

[0418] Step 5:

[0419] Users can view the generated reports and customize them to meet specific business needs. They can filter reports based on topics of interest and priorities, and use them as presentation materials for clients or as reference materials for internal strategy meetings.

[0420] Step 6:

[0421] The server uses an alert generator to monitor market and competitor information in real time. When changes are detected in specific conditions or keywords, it quickly generates alerts and immediately notifies users. This allows for immediate response to any anomalies or opportunities.

[0422] (Example 1)

[0423] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0424] For companies to quickly and efficiently grasp market trends and competitive information, they need to accurately collect and analyze vast amounts of data and immediately extract crucial information. However, existing methods have limitations in terms of speed and accuracy, and are particularly poor at responding to real-time changes in the situation. As a result, companies face the challenge of not being able to obtain timely information in order to make rapid decisions.

[0425] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0426] In this invention, the server includes means for automatically collecting information from diverse data sources using information gathering means, means for cleaning and preprocessing the collected information, and means for analyzing the preprocessed information using natural language processing techniques to identify key themes and emotional tones and extract important information. This makes it possible to collect and analyze vast amounts of information quickly and accurately, respond to real-time changes in circumstances, and support accurate decision-making.

[0427] "Information gathering means" refers to devices and methods for automatically acquiring information from diverse data sources.

[0428] "Preprocessing means" refers to devices or methods for cleaning collected information and preparing it in a format suitable for analysis.

[0429] "Natural language processing techniques" are algorithms and methods for analyzing text data to identify key themes and emotional tones.

[0430] A "report format" is a means of structuring extracted information and presenting it visually or in a document.

[0431] An "alert generation means" is a device or method that detects changes in real time and provides notifications based on set conditions.

[0432] "Theme identification" is an analytical technique that identifies the main topics present within data.

[0433] "Sentiment analysis" is a technique that evaluates the emotional tone of text data and classifies it into categories such as positive, negative, and neutral.

[0434] "Customizable" means that users have the ability to modify and adjust the generated reports to suit their own needs.

[0435] The information processing system of the present invention is designed to enable companies to quickly and efficiently grasp market trends and competitive information. This system includes information gathering means, preprocessing means, natural language processing technology, report generation means, and alert generation means.

[0436] The server automatically collects information from multiple data sources, including news feeds, social media, and internal communication platforms, using various information gathering methods. In this process, it utilizes web scraping tools and public APIs to retrieve data.

[0437] The collected data is cleaned using preprocessing tools on the server. Specifically, libraries such as Python's pandas and numpy are used to remove unnecessary elements and handle missing values, and NLTK is used for filtering text data.

[0438] Next, natural language processing techniques are used, and the server performs data analysis. Topic modeling using LDA is employed to identify the main theme from the data, and sentiment analysis is performed using VADER and TextBlob to evaluate the emotional tone of the information. This derives the essential content and value of the collected information.

[0439] Subsequently, the extracted information is structured by the server using a report generation mechanism, and a report in a user-friendly format is generated. Since output is possible in PDF and HTML formats via a template engine, documentation is created in a user-friendly format.

[0440] Furthermore, the alert generation mechanism allows the server to monitor changes in specific configured conditions in real time, and immediately notify the user of an alert when an abnormal event is detected.

[0441] As a concrete example, when a company preparing to launch a product into the market uses this system, it can receive an immediate, easy-to-understand report by using a generative AI model, based on prompts such as, "Analyze consumer opinions on the new product in the market and compile the results into a report." This report is customizable by the user and can be adjusted to meet diverse needs.

[0442] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0443] Step 1:

[0444] The server collects information from diverse data sources using various data gathering methods. Inputs include news feeds, social media, and URLs and API endpoints of internal platforms. Specifically, the server automatically extracts data using web scraping tools and API calls. The output is a set of collected raw data.

[0445] Step 2:

[0446] The server cleans the collected data using preprocessing tools. The input is a set of raw data. Specifically, it uses Python's pandas and numpy to remove unnecessary symbols and HTML tags from the data and imputes missing values. It uses NLTK to filter for stop words and converts the data into a parseable format. The output is formatted text data.

[0447] Step 3:

[0448] The server analyzes pre-processed data using natural language processing techniques. The input is formatted text data. Specifically, it performs topic modeling using LDA to identify the main themes within the data. It also performs sentiment analysis using VADER and TextBlob to quantify the emotional tone of the data. The output is theme information and sentiment scores.

[0449] Step 4:

[0450] The server creates a report based on information extracted using a report generation method. The inputs are theme information and sentiment scores. Specifically, it utilizes a template engine to systematize the information and output it as a report in PDF or HTML format. The output is a visualized report file.

[0451] Step 5:

[0452] The server uses an alert generation mechanism to monitor status changes in real time based on specific conditions. The input is real-time updated analytical data. Specifically, when the server detects a change that matches the configured conditions, it immediately sends a notification to the user. The output is an alert message, delivered via email or application notification.

[0453] (Application Example 1)

[0454] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0455] There is a challenge in quickly and efficiently grasping market trends and competitive information, particularly a lack of real-time information necessary for optimizing advertising campaigns. Furthermore, there is a need for advertising professionals to quickly grasp trends and appropriately adjust campaigns.

[0456] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0457] In this invention, the server includes means for collecting data from a data collection device, means for preprocessing the collected data, means for analyzing the preprocessed data using natural language processing technology and extracting important information, means for generating the extracted information in report format, means for generating alerts in real time based on set conditions, and means for analyzing market trends in real time and adjusting advertising campaigns in order to optimize marketing strategies. This enables advertisers to respond immediately to market changes and build optimal advertising strategies.

[0458] A "data acquisition device" is hardware or software used to obtain necessary data from an information source.

[0459] "Preprocessing" refers to the process of removing noise and organizing data in order to prepare collected data into an analyzable format.

[0460] "Natural language processing technology" is a technique that extracts useful meaning and information from text data, enabling topic identification and sentiment analysis.

[0461] "Generating in report format" refers to the process of visualizing extracted information and compiling it into an easily understandable format.

[0462] A "means of generating alerts" is a mechanism that creates a notification when certain conditions are met, alerting the user.

[0463] "Means for optimizing marketing strategies" refers to the process of adjusting advertising and promotional activities based on market trends to achieve effective results.

[0464] "Methods for analyzing market trends in real time" refer to methods for immediately evaluating the latest market information and rapidly detecting changes.

[0465] "Methods for adjusting an advertising campaign" refer to the process of modifying the content and delivery methods to keep the advertising strategy in an optimal state.

[0466] The system for realizing this invention mainly consists of the collaborative operation of a server, a terminal, and a user.

[0467] The server uses information gathering devices to periodically collect relevant information from diverse data sources. The data targets news feeds, social media, and other public sources, and is effectively retrieved using Python and APIs. This ensures that the latest market and competitor information is continuously updated.

[0468] The collected data is processed by a preprocessor on the server to prepare it for analysis. Specifically, Pandas is used to clean the data and remove noise. For text data, unnecessary symbols and tags are removed, and stop words are filtered out.

[0469] The server analyzes the pre-processed data using natural language processing techniques. This process utilizes tools such as NLTK and spaCy to perform topic modeling and sentiment analysis. The analysis clarifies the main themes and sentiment tendencies within the data.

[0470] The extracted information is visualized by the server's report generation system, and reports are generated in HTML or PDF format. These reports can be accessed and customized by marketing personnel using their devices.

[0471] The server also has a device that generates alerts based on set conditions. It detects market changes in real time and sends push notifications to advertisers' terminals at the appropriate time. This enables rapid adjustment of strategies.

[0472] For example, when a new product is launched, the server monitors consumer reactions to that product on social media and provides immediate competitive information as alerts. Advertisers can then quickly adjust their advertising campaigns based on this data.

[0473] The system's operation relies heavily on generative AI models. Examples of prompts include, "Analyze key trends from new market data and identify the strengths of competing products and consumer interests," and "Based on the collected data, suggest optimization strategies for advertising campaigns."

[0474] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0475] Step 1:

[0476] The server collects data from news feeds, social media, and other sources using an API. Input consists of URLs and queries for information sources related to the company. Output is raw text data. The collected data includes market trends and competitive information targeted by this system.

[0477] Step 2:

[0478] The server cleans the collected raw data using a preprocessor. The input is the raw data obtained in step 1. The output is clean text data from which extraneous symbols and stop words have been removed. This makes the data suitable for natural language processing. Specifically, Pandas is used to format the data.

[0479] Step 3:

[0480] The server analyzes the pre-processed data using a natural language processing unit (NLTK). The input is the clean text data obtained in step 2. The output consists of key topics and sentiment scores. NLTK and spaCy are used as natural language processing techniques to perform topic modeling and sentiment analysis. This process extracts important themes and sentiment tendencies from the data.

[0481] Step 4:

[0482] The server generates a visual report using a report generator based on the analyzed data. The input consists of key topics and sentiment scores from Step 3. The output is a report in HTML or PDF format. The report includes visualized data analysis results, serving as foundational material for users developing advertising strategies.

[0483] Step 5:

[0484] The server generates alerts in real time based on configured conditions and sends notifications to the terminal. The input consists of the analysis results from step 3 and the user-configured alert conditions. The output is a push notification to the user's terminal. This ensures that important market changes and competitor movements are immediately communicated to the user. Specifically, webhooks are used to achieve real-time notifications.

[0485] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0486] This invention relates to an information processing system that supports a company's decision-making process, and in particular, it includes an emotion engine that recognizes user emotions and adapts the way information is presented based on those emotions. This system is composed of an integrated information gathering device, a data preprocessing device, a natural language processing device, a report generation device, an alert generation device, and an emotion engine. The specific operation of each component is described below.

[0487] First, the server collects company-related information from news sources, social media, internal messaging tools, etc., through information gathering devices. This data is then cleaned by a data preprocessor to remove noise and convert it into a format suitable for analysis.

[0488] Next, the pre-processed data is sent by the server to a natural language processing unit, where it is analyzed using topic modeling and sentiment analysis. This extracts important market trends and competitive information.

[0489] The extracted information is formatted as a report by a report generation device. For example, the server generates graphical reports that summarize market trends and highlight potential crisis factors. Furthermore, the generated reports can be customized according to user requests, and their content can be adjusted based on specific indicators or areas of interest.

[0490] Furthermore, the emotion engine, a key feature of this invention, operates on a server and recognizes the user's emotional state by analyzing the user's operation history and input data. This emotional information is used to adjust how reports are presented and when alerts are generated. For example, if a user is stressed, the report content can be simplified, and alert notifications can be suppressed or postponed.

[0491] The emotion engine also obtains real-time feedback from users and optimizes the alert generation process. Such capabilities enable companies to respond quickly to rapid market changes and competitive landscapes while reducing the psychological burden on users.

[0492] For example, in the case of a company planning a new market acquisition campaign, the server utilizes an emotion engine to detect the marketing manager's emotional state and optimize how the analysis results are presented. In particular, if high stress levels are detected, the report can be summarized and presented with a narrower selection of strategic options to support the manager's decision-making.

[0493] The following describes the processing flow.

[0494] Step 1:

[0495] The server collects data from the internet and the internal network using information gathering devices. At this stage, it continuously retrieves news feeds, social media data, and internal messaging data using APIs.

[0496] Step 2:

[0497] The server cleans the data collected by the data preprocessor, removing unnecessary information and noise. Specifically, it removes HTML tags and non-ASCII characters from text data and filters out stop words.

[0498] Step 3:

[0499] The server analyzes pre-processed data via a natural language processing unit. Topic modeling is used to identify key themes, and sentiment analysis determines the emotional tendencies of the data. Based on these results, the server extracts market trends and competitive information.

[0500] Step 4:

[0501] The server integrates the analysis results obtained from the report generation device into a report format. Here, it generates graphs and charts to make the information visually easy to understand and highlights important data points.

[0502] Step 5:

[0503] Users receive the generated reports on their devices and customize them as needed. They can edit and filter the report content according to their interests and work priorities.

[0504] Step 6:

[0505] The server uses an emotion engine to analyze the user's operation history and input data to recognize the user's emotions. Based on the emotional state, it dynamically adjusts how reports are displayed and the frequency of alerts.

[0506] Step 7:

[0507] The server uses an alert generator to send real-time alerts to the user under configured conditions. Based on the user's emotional state, it prioritizes which alerts to send and adjusts the timing of notifications to reduce stress.

[0508] Step 8:

[0509] Users review alerts and reports received on their devices and select the actions necessary for decision-making. Based on the information provided by the emotion engine, they can quickly determine the optimal strategy.

[0510] (Example 2)

[0511] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0512] In today's information society, companies need to make quick and accurate critical decisions from vast amounts of data. However, efficiently extracting necessary information from information overload and adjusting it according to the user's situation is not easy. In particular, it is necessary to present appropriate information while considering the user's emotions. As a result, the problem is that information overload and misunderstandings can lead to delayed or inefficient decision-making.

[0513] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0514] In this invention, the server includes means for collecting data from information sources using information gathering means, means for processing the data to remove noise and convert it into a format suitable for analysis, and means for analyzing the processed data using natural language processing technology to extract important market information. This makes it possible to provide users with appropriate and optimized information based on their emotions, thereby improving the quality of decision-making.

[0515] "Information gathering means" refers to a device or process for collecting relevant data from an information source.

[0516] "Processing means" refers to a function that digitally processes the collected data to remove noise and convert it into a format suitable for analysis.

[0517] "Natural language processing technology" refers to techniques that analyze text data and extract its internal structure and meaning, and specifically include topic modeling and sentiment analysis.

[0518] A "document format creation method" is a function that organizes extracted information and generates a document to provide it in a format that is easy for users to understand.

[0519] "Emotion recognition means" refers to a technology or device for detecting a user's emotional state and adjusting the method of presenting information or generating warnings based on that state.

[0520] A "warning generation mechanism" is a function that notifies the user of a warning in real time when set conditions are met.

[0521] "User" refers to a person or organization that receives the system's output and makes decisions based on that information.

[0522] This invention is an information processing system that supports corporate decision-making, and in particular aims to recognize the emotions of users and optimize the way information is presented based on those emotions. The system is configured as follows:

[0523] The server uses information gathering tools to collect data from sources such as news feeds, social media platforms, and internal messaging systems. This step typically involves using humanoid web scraping tools or APIs. The collected data is stored as raw data.

[0524] Next, the server preprocesses the collected raw data using data processing tools. Specifically, it removes unnecessary noise and missing values ​​and standardizes the data. This process is often performed using data processing libraries such as Pandas or NumPy.

[0525] The preprocessed data is then analyzed by the server using natural language processing techniques. Here, topic modeling techniques (e.g., Latent Dirichlet Allocation) and sentiment analysis (e.g., VADER) are used to extract important information and sentiment trends from the data. This process is performed using natural language processing libraries such as NLTK and Spacy.

[0526] Based on the extracted information, the server generates a document-format report. The report includes visual graphs and summary text, designed for easy user understanding. Libraries such as Matplotlib and ReportLab are used for report generation.

[0527] Furthermore, the server uses emotion recognition to analyze the user's operation history and input data to recognize the user's emotional state. This recognition information is reflected in and optimized for how information is presented and when warnings are generated. Specifically, if the user is experiencing stress, the report can be simplified and warning notifications can be postponed.

[0528] For example, when a company is trying to acquire a new market, the server can use an emotion engine to detect the emotional state of the marketer and optimize the presentation of analysis results. For instance, it can support the marketer's decision-making by providing information based on prompts to a generative AI model, such as "Explain how a company's emotion engine influences the decision-making process."

[0529] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0530] Step 1:

[0531] The server collects data from news feeds, social media, internal messaging systems, and other sources using information gathering methods. At this stage, the input is the various information sources to be collected, and the output is a raw dataset. Specifically, it uses web scraping techniques and APIs to periodically check each information source for new data and automatically extracts the necessary data.

[0532] Step 2:

[0533] The server preprocesses the collected raw data using data processing tools. The input is a raw dataset, and the output is clean and structured data. This processing uses dataframe libraries such as Pandas to remove duplicate data and adjust the format. Specifically, it removes HTML tags and standardizes date formats.

[0534] Step 3:

[0535] The server analyzes pre-processed data using natural language processing techniques. The input is structured data, and the output is important topics and their sentiment analysis results. In this step, NLTK and Spacy are used to perform topic modeling and sentiment analysis of the text, extracting highly relevant topics and positive / negative sentiments.

[0536] Step 4:

[0537] The server generates a document using a report generation tool based on the analysis results. The input is the analysis results, and the output is a visual summary report. Graphs are created using tools such as Matplotlib, and then assembled into a PDF report using ReportLab. Specifically, it creates a concise summary of important topics and saves it as a report along with the visualized data.

[0538] Step 5:

[0539] The server analyzes the user's emotional state using emotion recognition tools. Inputs are the user's operation history and input data, while outputs are information about the user's emotional state. A machine learning model is used to estimate emotions based on past user behavior data. Specifically, stress levels are evaluated from the user's click history and search keywords.

[0540] Step 6:

[0541] Users receive generated reports and alerts to aid in decision-making. The input is the final report and alert presented to the user, and the output is the improvement in decision-making. The server adjusts how reports are presented and the importance of alerts based on the user's emotional state. For example, if the user is under high stress, the report is made more concise and alerts are delayed to reduce the burden.

[0542] (Application Example 2)

[0543] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0544] The challenge in a company's decision-making process is to reduce the psychological burden on users and support more effective decision-making by appropriately recognizing their emotions and adjusting the way information is presented based on those emotions. Furthermore, there is a need to understand the emotional state of customers in physical stores in real time and provide appropriate customer service based on that understanding.

[0545] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0546] In this invention, the server includes means for acquiring information from information gathering means, means for preprocessing the acquired information, and means for analyzing the preprocessed information using language processing technology and extracting important information. This allows for adjusting the method of presenting information based on the user's emotional state, enabling customer service tailored to the emotional state of visitors in physical stores.

[0547] "Information gathering means" refers to the function that a system uses to acquire data from external sources.

[0548] "Preprocessing" refers to the act of performing initial processing to convert collected information into a format suitable for analysis.

[0549] "Language processing technology" is a technique that analyzes natural language text and extracts meaning and emotion from the information.

[0550] A "report format" is a method of organizing and presenting extracted information visually or in writing.

[0551] A "means for generating an immediate warning" refers to a function that quickly issues a warning when certain conditions are met.

[0552] "Emotional state" refers to the state that represents the psychological reactions and emotions of users or customers.

[0553] "Means of adjusting the method of information presentation" refers to the ability to change the content and format of information presented according to the user's emotional state.

[0554] In an embodiment of this invention, a server constructs a system equipped with information gathering means, preprocessing means, and language processing technology. First, the server uses the information gathering means to acquire company-related information from external sources. This information includes news, social media, customer feedback, etc. The acquired information is cleaned through the preprocessing means and converted into a format suitable for analysis. By removing noise and unnecessary parts, the data is ready for analysis.

[0555] Next, the pre-processed data is analyzed using natural language processing techniques. This process involves thematic modeling and sentiment analysis to extract market trends and customer emotional states from the information. For sentiment analysis, an emotion engine operates to recognize the user's emotional state in real time, determining their psychological state based on user input and past operation history.

[0556] The server organizes the extracted information into a report format and presents it to the user's terminal. The way information is presented is automatically adjusted according to the user's emotional state. For example, if the user is feeling stressed, the information can be summarized concisely and presented in a more easily understandable format. Furthermore, if the customer is using a device such as a robot or smart glasses, emotionally-based recommendations are provided in real time.

[0557] For example, a store employee wearing smart glasses can understand the customer's emotional state and strive to provide calm and attentive service. This function leads to improved customer satisfaction and more efficient service delivery.

[0558] An example of a prompt message could be: "If the customer is deemed interested, the staff should calmly provide customer service and recommend offering a tasting." This enables user-centric interaction.

[0559] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0560] Step 1:

[0561] The server acquires information from news sources and social media using information gathering methods. The input is publicly available data obtained through the network, and the output is raw, unprocessed data. In this process, APIs and scraping techniques are used to efficiently collect information.

[0562] Step 2:

[0563] The server cleans the raw data obtained using preprocessing tools. The input to this process is the raw data obtained in step 1, and the output is formatted data with noise removed. Specifically, this process includes text normalization, correction of typos, and standardization of formatting.

[0564] Step 3:

[0565] The server applies language processing techniques to the formatted data and performs thematic modeling and sentiment analysis. The input is the formatted data obtained in step 2, and the output is thematic information and data on the user's emotional state extracted through the analysis. In this step, a machine learning model is used to classify the sentiment categories.

[0566] Step 4:

[0567] The server organizes the extracted information into a report format and presents it to the user's terminal. The input is the subject information and emotional state data from the analysis in step 3, and the output is a visually organized report document. The appropriate method of presenting the information is selected according to the user's emotions.

[0568] Step 5:

[0569] The user terminal provides appropriate recommendations and guidance based on the user's emotional state identified by the emotion engine. The input is emotional state data from step 3, and the output is situation-appropriate actions and self-improvement advice provided to the user. Specific actions include immediate notifications to the user and information display on the screen.

[0570] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0571] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0572] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0573] [Fourth Embodiment]

[0574] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0575] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0576] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0577] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0578] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0579] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0580] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0581] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0582] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0583] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0584] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0585] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0586] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0587] This invention is an information processing system used by companies to quickly and efficiently grasp market trends and competitive information. This system integrates an information gathering device, a data preprocessing device, a natural language processing device, a report generation device, and an alert generation device. The specific operation of each component is described below.

[0588] First, the server uses information gathering devices to periodically acquire data from various data sources related to the company. This includes news feeds, internal communication channels, and social media. This data is then sent to a preprocessor.

[0589] Next, the server cleans the data collected by the preprocessor and removes noise. Specifically, in the case of text data, it removes extraneous symbols and tags and filters out stop words. This process makes the data suitable for analysis by the natural language processing unit.

[0590] Subsequently, the server uses a natural language processing unit to extract useful information from the preprocessed data. Topic modeling identifies the main themes within the data, and sentiment analysis is performed to evaluate the emotional tone of the data. For example, consumer reactions to a new product on social media can be categorized.

[0591] The extracted information is systematized by the report generation system, and the server generates the final report. Users can receive the generated report and gain detailed insights into specific market trends and competitive information. The report can be output in formats such as PDF and HTML, and can be customized as needed.

[0592] Furthermore, the server utilizes an alert generator to monitor sudden market changes and competitor actions in real time. If certain conditions are met, it immediately sends an alert to the user. This feature allows companies to review their strategies in a timely manner and quickly take necessary actions.

[0593] For example, if a company preparing to launch a new product uses this system, the server collects consumer feedback in the market in real time and provides a report outlining the features consumers are interested in and the areas they want to improve. Furthermore, if the system detects any potential risks from competing products, an alert is immediately sent to the user, allowing for a rapid readjustment of the strategy.

[0594] The following describes the processing flow.

[0595] Step 1:

[0596] The server retrieves information from specified data sources via pre-configured information gathering devices. These data sources include news feeds, internal communication tools, and social media platforms. Information gathering can be done in real time or on an automated, scheduled basis.

[0597] Step 2:

[0598] The server transfers the collected raw data to a data preprocessor for preprocessing. Here, unnecessary noise and inaccurate information are filtered out, and the data is cleaned. Specifically, unnecessary symbols and duplicate information are removed from text data, and the data is formatted into a uniform format.

[0599] Step 3:

[0600] The server analyzes the cleaned data using a natural language processing unit. First, it applies topic modeling algorithms to identify key themes and patterns within the data. Then, it performs sentiment analysis to categorize the opinions and feelings contained in the data into positive, negative, and neutral categories.

[0601] Step 4:

[0602] The server uses a report generation device to assemble a report based on the analysis results from the natural language processing unit. Here, the content is documented, and data visualization (e.g., graphs and charts) is performed as needed. This ensures that the report is output in a clear and easy-to-use format.

[0603] Step 5:

[0604] Users can view the generated reports and customize them to meet specific business needs. They can filter reports based on topics of interest and priorities, and use them as presentation materials for clients or as reference materials for internal strategy meetings.

[0605] Step 6:

[0606] The server uses an alert generator to monitor market and competitor information in real time. When changes are detected in specific conditions or keywords, it quickly generates alerts and immediately notifies users. This allows for immediate response to any anomalies or opportunities.

[0607] (Example 1)

[0608] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0609] For companies to quickly and efficiently grasp market trends and competitive information, they need to accurately collect and analyze vast amounts of data and immediately extract crucial information. However, existing methods have limitations in terms of speed and accuracy, and are particularly poor at responding to real-time changes in the situation. As a result, companies face the challenge of not being able to obtain timely information in order to make rapid decisions.

[0610] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0611] In this invention, the server includes means for automatically collecting information from diverse data sources using information gathering means, means for cleaning and preprocessing the collected information, and means for analyzing the preprocessed information using natural language processing techniques to identify key themes and emotional tones and extract important information. This makes it possible to collect and analyze vast amounts of information quickly and accurately, respond to real-time changes in circumstances, and support accurate decision-making.

[0612] "Information gathering means" refers to devices and methods for automatically acquiring information from diverse data sources.

[0613] "Preprocessing means" refers to devices or methods for cleaning collected information and preparing it in a format suitable for analysis.

[0614] "Natural language processing techniques" are algorithms and methods for analyzing text data to identify key themes and emotional tones.

[0615] A "report format" is a means of structuring extracted information and presenting it visually or in a document.

[0616] An "alert generation means" is a device or method that detects changes in real time and provides notifications based on set conditions.

[0617] "Theme identification" is an analytical technique that identifies the main topics present within data.

[0618] "Sentiment analysis" is a technique that evaluates the emotional tone of text data and classifies it into categories such as positive, negative, and neutral.

[0619] "Customizable" means that users have the ability to modify and adjust the generated reports to suit their own needs.

[0620] The information processing system of the present invention is designed to enable companies to quickly and efficiently grasp market trends and competitive information. This system includes information gathering means, preprocessing means, natural language processing technology, report generation means, and alert generation means.

[0621] The server automatically collects information from multiple data sources, including news feeds, social media, and internal communication platforms, using various information gathering methods. In this process, it utilizes web scraping tools and public APIs to retrieve data.

[0622] The collected data is cleaned using preprocessing tools on the server. Specifically, libraries such as Python's pandas and numpy are used to remove unnecessary elements and handle missing values, and NLTK is used for filtering text data.

[0623] Next, natural language processing techniques are used, and the server performs data analysis. Topic modeling using LDA is employed to identify the main theme from the data, and sentiment analysis is performed using VADER and TextBlob to evaluate the emotional tone of the information. This derives the essential content and value of the collected information.

[0624] Subsequently, the extracted information is structured by the server using a report generation mechanism, and a report in a user-friendly format is generated. Since output is possible in PDF and HTML formats via a template engine, documentation is created in a user-friendly format.

[0625] Furthermore, the alert generation mechanism allows the server to monitor changes in specific configured conditions in real time, and immediately notify the user of an alert when an abnormal event is detected.

[0626] As a concrete example, when a company preparing to launch a product into the market uses this system, it can receive an immediate, easy-to-understand report by using a generative AI model, based on prompts such as, "Analyze consumer opinions on the new product in the market and compile the results into a report." This report is customizable by the user and can be adjusted to meet diverse needs.

[0627] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0628] Step 1:

[0629] The server collects information from diverse data sources using various data gathering methods. Inputs include news feeds, social media, and URLs and API endpoints of internal platforms. Specifically, the server automatically extracts data using web scraping tools and API calls. The output is a set of collected raw data.

[0630] Step 2:

[0631] The server cleans the collected data using preprocessing tools. The input is a set of raw data. Specifically, it uses Python's pandas and numpy to remove unnecessary symbols and HTML tags from the data and imputes missing values. It uses NLTK to filter for stop words and converts the data into a parseable format. The output is formatted text data.

[0632] Step 3:

[0633] The server analyzes pre-processed data using natural language processing techniques. The input is formatted text data. Specifically, it performs topic modeling using LDA to identify the main themes within the data. It also performs sentiment analysis using VADER and TextBlob to quantify the emotional tone of the data. The output is theme information and sentiment scores.

[0634] Step 4:

[0635] The server creates a report based on information extracted using a report generation method. The inputs are theme information and sentiment scores. Specifically, it utilizes a template engine to systematize the information and output it as a report in PDF or HTML format. The output is a visualized report file.

[0636] Step 5:

[0637] The server uses an alert generation mechanism to monitor status changes in real time based on specific conditions. The input is real-time updated analytical data. Specifically, when the server detects a change that matches the configured conditions, it immediately sends a notification to the user. The output is an alert message, delivered via email or application notification.

[0638] (Application Example 1)

[0639] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0640] There is a challenge in quickly and efficiently grasping market trends and competitive information, particularly a lack of real-time information necessary for optimizing advertising campaigns. Furthermore, there is a need for advertising professionals to quickly grasp trends and appropriately adjust campaigns.

[0641] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0642] In this invention, the server includes means for collecting data from a data collection device, means for preprocessing the collected data, means for analyzing the preprocessed data using natural language processing technology and extracting important information, means for generating the extracted information in report format, means for generating alerts in real time based on set conditions, and means for analyzing market trends in real time and adjusting advertising campaigns in order to optimize marketing strategies. This enables advertisers to respond immediately to market changes and build optimal advertising strategies.

[0643] A "data acquisition device" is hardware or software used to obtain necessary data from an information source.

[0644] "Preprocessing" refers to the process of removing noise and organizing data in order to prepare collected data into an analyzable format.

[0645] "Natural language processing technology" is a technique that extracts useful meaning and information from text data, enabling topic identification and sentiment analysis.

[0646] "Generating in report format" refers to the process of visualizing extracted information and compiling it into an easily understandable format.

[0647] A "means of generating alerts" is a mechanism that creates a notification when certain conditions are met, alerting the user.

[0648] "Means for optimizing marketing strategies" refers to the process of adjusting advertising and promotional activities based on market trends to achieve effective results.

[0649] "Methods for analyzing market trends in real time" refer to methods for immediately evaluating the latest market information and rapidly detecting changes.

[0650] "Methods for adjusting an advertising campaign" refer to the process of modifying the content and delivery methods to keep the advertising strategy in an optimal state.

[0651] The system for realizing this invention mainly consists of the collaborative operation of a server, a terminal, and a user.

[0652] The server uses information gathering devices to periodically collect relevant information from diverse data sources. The data targets news feeds, social media, and other public sources, and is effectively retrieved using Python and APIs. This ensures that the latest market and competitor information is continuously updated.

[0653] The collected data is processed by a preprocessor on the server to prepare it for analysis. Specifically, Pandas is used to clean the data and remove noise. For text data, unnecessary symbols and tags are removed, and stop words are filtered out.

[0654] The server analyzes the pre-processed data using natural language processing techniques. This process utilizes tools such as NLTK and spaCy to perform topic modeling and sentiment analysis. The analysis clarifies the main themes and sentiment tendencies within the data.

[0655] The extracted information is visualized by the server's report generation system, and reports are generated in HTML or PDF format. These reports can be accessed and customized by marketing personnel using their devices.

[0656] The server also has a device that generates alerts based on set conditions. It detects market changes in real time and sends push notifications to advertisers' terminals at the appropriate time. This enables rapid adjustment of strategies.

[0657] For example, when a new product is launched, the server monitors consumer reactions to that product on social media and provides immediate competitive information as alerts. Advertisers can then quickly adjust their advertising campaigns based on this data.

[0658] The system's operation relies heavily on generative AI models. Examples of prompts include, "Analyze key trends from new market data and identify the strengths of competing products and consumer interests," and "Based on the collected data, suggest optimization strategies for advertising campaigns."

[0659] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0660] Step 1:

[0661] The server collects data from news feeds, social media, and other sources using an API. Input consists of URLs and queries for information sources related to the company. Output is raw text data. The collected data includes market trends and competitive information targeted by this system.

[0662] Step 2:

[0663] The server cleans the collected raw data using a preprocessor. The input is the raw data obtained in step 1. The output is clean text data from which extraneous symbols and stop words have been removed. This makes the data suitable for natural language processing. Specifically, Pandas is used to format the data.

[0664] Step 3:

[0665] The server analyzes the pre-processed data using a natural language processing unit (NLTK). The input is the clean text data obtained in step 2. The output consists of key topics and sentiment scores. NLTK and spaCy are used as natural language processing techniques to perform topic modeling and sentiment analysis. This process extracts important themes and sentiment tendencies from the data.

[0666] Step 4:

[0667] The server generates a visual report using a report generator based on the analyzed data. The input consists of key topics and sentiment scores from Step 3. The output is a report in HTML or PDF format. The report includes visualized data analysis results, serving as foundational material for users developing advertising strategies.

[0668] Step 5:

[0669] The server generates alerts in real time based on configured conditions and sends notifications to the terminal. The input consists of the analysis results from step 3 and the user-configured alert conditions. The output is a push notification to the user's terminal. This ensures that important market changes and competitor movements are immediately communicated to the user. Specifically, webhooks are used to achieve real-time notifications.

[0670] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0671] This invention relates to an information processing system that supports a company's decision-making process, and in particular, it includes an emotion engine that recognizes user emotions and adapts the way information is presented based on those emotions. This system is composed of an integrated information gathering device, a data preprocessing device, a natural language processing device, a report generation device, an alert generation device, and an emotion engine. The specific operation of each component is described below.

[0672] First, the server collects company-related information from news sources, social media, internal messaging tools, etc., through information gathering devices. This data is then cleaned by a data preprocessor to remove noise and convert it into a format suitable for analysis.

[0673] Next, the pre-processed data is sent by the server to a natural language processing unit, where it is analyzed using topic modeling and sentiment analysis. This extracts important market trends and competitive information.

[0674] The extracted information is formatted as a report by a report generation device. For example, the server generates graphical reports that summarize market trends and highlight potential crisis factors. Furthermore, the generated reports can be customized according to user requests, and their content can be adjusted based on specific indicators or areas of interest.

[0675] Furthermore, the emotion engine, a key feature of this invention, operates on a server and recognizes the user's emotional state by analyzing the user's operation history and input data. This emotional information is used to adjust how reports are presented and when alerts are generated. For example, if a user is stressed, the report content can be simplified, and alert notifications can be suppressed or postponed.

[0676] The emotion engine also obtains real-time feedback from users and optimizes the alert generation process. Such capabilities enable companies to respond quickly to rapid market changes and competitive landscapes while reducing the psychological burden on users.

[0677] For example, in the case of a company planning a new market acquisition campaign, the server utilizes an emotion engine to detect the marketing manager's emotional state and optimize how the analysis results are presented. In particular, if high stress levels are detected, the report can be summarized and presented with a narrower selection of strategic options to support the manager's decision-making.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] The server collects data from the internet and the internal network using information gathering devices. At this stage, it continuously retrieves news feeds, social media data, and internal messaging data using APIs.

[0681] Step 2:

[0682] The server cleans the data collected by the data preprocessor, removing unnecessary information and noise. Specifically, it removes HTML tags and non-ASCII characters from text data and filters out stop words.

[0683] Step 3:

[0684] The server analyzes pre-processed data via a natural language processing unit. Topic modeling is used to identify key themes, and sentiment analysis determines the emotional tendencies of the data. Based on these results, the server extracts market trends and competitive information.

[0685] Step 4:

[0686] The server integrates the analysis results obtained from the report generation device into a report format. Here, it generates graphs and charts to make the information visually easy to understand and highlights important data points.

[0687] Step 5:

[0688] Users receive the generated reports on their devices and customize them as needed. They can edit and filter the report content according to their interests and work priorities.

[0689] Step 6:

[0690] The server uses an emotion engine to analyze the user's operation history and input data to recognize the user's emotions. Based on the emotional state, it dynamically adjusts how reports are displayed and the frequency of alerts.

[0691] Step 7:

[0692] The server uses an alert generator to send real-time alerts to the user under configured conditions. Based on the user's emotional state, it prioritizes which alerts to send and adjusts the timing of notifications to reduce stress.

[0693] Step 8:

[0694] Users review alerts and reports received on their devices and select the actions necessary for decision-making. Based on the information provided by the emotion engine, they can quickly determine the optimal strategy.

[0695] (Example 2)

[0696] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0697] In today's information society, companies need to make quick and accurate critical decisions from vast amounts of data. However, efficiently extracting necessary information from information overload and adjusting it according to the user's situation is not easy. In particular, it is necessary to present appropriate information while considering the user's emotions. As a result, the problem is that information overload and misunderstandings can lead to delayed or inefficient decision-making.

[0698] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0699] In this invention, the server includes means for collecting data from information sources using information gathering means, means for processing the data to remove noise and convert it into a format suitable for analysis, and means for analyzing the processed data using natural language processing technology to extract important market information. This makes it possible to provide users with appropriate and optimized information based on their emotions, thereby improving the quality of decision-making.

[0700] "Information gathering means" refers to a device or process for collecting relevant data from an information source.

[0701] "Processing means" refers to a function that digitally processes the collected data to remove noise and convert it into a format suitable for analysis.

[0702] "Natural language processing technology" refers to techniques that analyze text data and extract its internal structure and meaning, and specifically include topic modeling and sentiment analysis.

[0703] A "document format creation method" is a function that organizes extracted information and generates a document to provide it in a format that is easy for users to understand.

[0704] "Emotion recognition means" refers to a technology or device for detecting a user's emotional state and adjusting the method of presenting information or generating warnings based on that state.

[0705] A "warning generation mechanism" is a function that notifies the user of a warning in real time when set conditions are met.

[0706] "User" refers to a person or organization that receives the system's output and makes decisions based on that information.

[0707] This invention is an information processing system that supports corporate decision-making, and in particular aims to recognize the emotions of users and optimize the way information is presented based on those emotions. The system is configured as follows:

[0708] The server uses information gathering tools to collect data from sources such as news feeds, social media platforms, and internal messaging systems. This step typically involves using humanoid web scraping tools or APIs. The collected data is stored as raw data.

[0709] Next, the server preprocesses the collected raw data using data processing tools. Specifically, it removes unnecessary noise and missing values ​​and standardizes the data. This process is often performed using data processing libraries such as Pandas or NumPy.

[0710] The preprocessed data is then analyzed by the server using natural language processing techniques. Here, topic modeling techniques (e.g., Latent Dirichlet Allocation) and sentiment analysis (e.g., VADER) are used to extract important information and sentiment trends from the data. This process is performed using natural language processing libraries such as NLTK and Spacy.

[0711] Based on the extracted information, the server generates a document-format report. The report includes visual graphs and summary text, designed for easy user understanding. Libraries such as Matplotlib and ReportLab are used for report generation.

[0712] Furthermore, the server uses emotion recognition to analyze the user's operation history and input data to recognize the user's emotional state. This recognition information is reflected in and optimized for how information is presented and when warnings are generated. Specifically, if the user is experiencing stress, the report can be simplified and warning notifications can be postponed.

[0713] For example, when a company is trying to acquire a new market, the server can use an emotion engine to detect the emotional state of the marketer and optimize the presentation of analysis results. For instance, it can support the marketer's decision-making by providing information based on prompts to a generative AI model, such as "Explain how a company's emotion engine influences the decision-making process."

[0714] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0715] Step 1:

[0716] The server collects data from news feeds, social media, internal messaging systems, and other sources using information gathering methods. At this stage, the input is the various information sources to be collected, and the output is a raw dataset. Specifically, it uses web scraping techniques and APIs to periodically check each information source for new data and automatically extracts the necessary data.

[0717] Step 2:

[0718] The server preprocesses the collected raw data using data processing tools. The input is a raw dataset, and the output is clean and structured data. This processing uses dataframe libraries such as Pandas to remove duplicate data and adjust the format. Specifically, it removes HTML tags and standardizes date formats.

[0719] Step 3:

[0720] The server analyzes pre-processed data using natural language processing techniques. The input is structured data, and the output is important topics and their sentiment analysis results. In this step, NLTK and Spacy are used to perform topic modeling and sentiment analysis of the text, extracting highly relevant topics and positive / negative sentiments.

[0721] Step 4:

[0722] The server generates a document using a report generation tool based on the analysis results. The input is the analysis results, and the output is a visual summary report. Graphs are created using tools such as Matplotlib, and then assembled into a PDF report using ReportLab. Specifically, it creates a concise summary of important topics and saves it as a report along with the visualized data.

[0723] Step 5:

[0724] The server analyzes the user's emotional state using emotion recognition tools. Inputs are the user's operation history and input data, while outputs are information about the user's emotional state. A machine learning model is used to estimate emotions based on past user behavior data. Specifically, stress levels are evaluated from the user's click history and search keywords.

[0725] Step 6:

[0726] Users receive generated reports and alerts to aid in decision-making. The input is the final report and alert presented to the user, and the output is the improvement in decision-making. The server adjusts how reports are presented and the importance of alerts based on the user's emotional state. For example, if the user is under high stress, the report is made more concise and alerts are delayed to reduce the burden.

[0727] (Application Example 2)

[0728] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0729] The challenge in a company's decision-making process is to reduce the psychological burden on users and support more effective decision-making by appropriately recognizing their emotions and adjusting the way information is presented based on those emotions. Furthermore, there is a need to understand the emotional state of customers in physical stores in real time and provide appropriate customer service based on that understanding.

[0730] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0731] In this invention, the server includes means for acquiring information from information gathering means, means for preprocessing the acquired information, and means for analyzing the preprocessed information using language processing technology and extracting important information. This allows for adjusting the method of presenting information based on the user's emotional state, enabling customer service tailored to the emotional state of visitors in physical stores.

[0732] "Information gathering means" refers to the function that a system uses to acquire data from external sources.

[0733] "Preprocessing" refers to the act of performing initial processing to convert collected information into a format suitable for analysis.

[0734] "Language processing technology" is a technique that analyzes natural language text and extracts meaning and emotion from the information.

[0735] A "report format" is a method of organizing and presenting extracted information visually or in writing.

[0736] A "means for generating an immediate warning" refers to a function that quickly issues a warning when certain conditions are met.

[0737] "Emotional state" refers to the state that represents the psychological reactions and emotions of users or customers.

[0738] "Means of adjusting the method of information presentation" refers to the ability to change the content and format of information presented according to the user's emotional state.

[0739] In an embodiment of this invention, a server constructs a system equipped with information gathering means, preprocessing means, and language processing technology. First, the server uses the information gathering means to acquire company-related information from external sources. This information includes news, social media, customer feedback, etc. The acquired information is cleaned through the preprocessing means and converted into a format suitable for analysis. By removing noise and unnecessary parts, the data is ready for analysis.

[0740] Next, the pre-processed data is analyzed using natural language processing techniques. This process involves thematic modeling and sentiment analysis to extract market trends and customer emotional states from the information. For sentiment analysis, an emotion engine operates to recognize the user's emotional state in real time, determining their psychological state based on user input and past operation history.

[0741] The server organizes the extracted information into a report format and presents it to the user's terminal. The way information is presented is automatically adjusted according to the user's emotional state. For example, if the user is feeling stressed, the information can be summarized concisely and presented in a more easily understandable format. Furthermore, if the customer is using a device such as a robot or smart glasses, emotionally-based recommendations are provided in real time.

[0742] For example, a store employee wearing smart glasses can understand the customer's emotional state and strive to provide calm and attentive service. This function leads to improved customer satisfaction and more efficient service delivery.

[0743] An example of a prompt message could be: "If the customer is deemed interested, the staff should calmly provide customer service and recommend offering a tasting." This enables user-centric interaction.

[0744] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0745] Step 1:

[0746] The server acquires information from news sources and social media using information gathering methods. The input is publicly available data obtained through the network, and the output is raw, unprocessed data. In this process, APIs and scraping techniques are used to efficiently collect information.

[0747] Step 2:

[0748] The server cleans the raw data obtained using preprocessing tools. The input to this process is the raw data obtained in step 1, and the output is formatted data with noise removed. Specifically, this process includes text normalization, correction of typos, and standardization of formatting.

[0749] Step 3:

[0750] The server applies language processing techniques to the formatted data and performs thematic modeling and sentiment analysis. The input is the formatted data obtained in step 2, and the output is thematic information and data on the user's emotional state extracted through the analysis. In this step, a machine learning model is used to classify the sentiment categories.

[0751] Step 4:

[0752] The server organizes the extracted information into a report format and presents it to the user's terminal. The input is the subject information and emotional state data from the analysis in step 3, and the output is a visually organized report document. The appropriate method of presenting the information is selected according to the user's emotions.

[0753] Step 5:

[0754] The user terminal provides appropriate recommendations and guidance based on the user's emotional state identified by the emotion engine. The input is emotional state data from step 3, and the output is situation-appropriate actions and self-improvement advice provided to the user. Specific actions include immediate notifications to the user and information display on the screen.

[0755] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0756] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0757] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0758] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0759] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0760] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0761] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0762] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0763] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0764] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0765] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0766] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0767] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0768] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0769] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0770] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0771] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0772] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0773] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0774] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0775] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0776] The following is further disclosed regarding the embodiments described above.

[0777] (Claim 1)

[0778] Means for collecting data from an information gathering device,

[0779] A means of preprocessing the collected data,

[0780] A means of analyzing pre-processed data using natural language processing techniques and extracting important information,

[0781] A means of generating the extracted information in report format,

[0782] A means of generating alerts in real time based on set conditions,

[0783] A system that includes this.

[0784] (Claim 2)

[0785] The system according to claim 1, wherein the natural language processing technique includes topic modeling and sentiment analysis.

[0786] (Claim 3)

[0787] The system according to claim 1, wherein the generated report can be customized by the user.

[0788] "Example 1"

[0789] (Claim 1)

[0790] A means of automatically collecting information from various data sources using information gathering means,

[0791] Means for cleaning and pre-processing the collected information,

[0792] A means of analyzing pre-processed information using natural language processing techniques to identify key themes and emotional tones, and to extract important information,

[0793] A means of structuring the extracted information, generating it in report format, and outputting it,

[0794] A means of detecting changes in real time and generating alerts based on set conditions,

[0795] A system that includes this.

[0796] (Claim 2)

[0797] The system according to claim 1, wherein the natural language processing technology includes theme identification and sentiment analysis.

[0798] (Claim 3)

[0799] The system according to claim 1, wherein the generated report can be customized by the user.

[0800] "Application Example 1"

[0801] (Claim 1)

[0802] Means for collecting data from a data collection device,

[0803] A means of preprocessing the collected data,

[0804] A means of analyzing pre-processed data using natural language processing techniques and extracting important information,

[0805] A means of generating the extracted information in report format,

[0806] A means of generating alerts in real time based on set conditions,

[0807] To optimize marketing strategies, we need means to analyze market trends in real time and adjust advertising campaigns accordingly.

[0808] A system that includes this.

[0809] (Claim 2)

[0810] The system according to claim 1, wherein the natural language processing technique includes topic modeling and sentiment analysis.

[0811] (Claim 3)

[0812] The system according to claim 1, further comprising a means to allow users to customize the generated reports and to provide information to advertisers in real time via smartphone.

[0813] "Example 2 of combining an emotion engine"

[0814] (Claim 1)

[0815] Means of collecting data from information sources using information gathering means,

[0816] A means for processing the aforementioned data to remove noise and convert it into a format suitable for analysis,

[0817] A means for analyzing the processed data using natural language processing technology and extracting important market information,

[0818] A means of creating the extracted information in document format,

[0819] An emotion recognition means for adjusting the aforementioned document based on the user's emotional state,

[0820] A means for generating warnings in real time based on set conditions,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, wherein the natural language processing technology includes topic modeling and sentiment analysis.

[0824] (Claim 3)

[0825] The system according to claim 1, which allows users to individually adjust the generated documents.

[0826] "Application example 2 when combining with an emotional engine"

[0827] (Claim 1)

[0828] Means of obtaining information from information gathering means,

[0829] Means for preprocessing acquired information,

[0830] A means for analyzing pre-processed information using language processing techniques and extracting important information,

[0831] A means for generating the extracted information in a report format,

[0832] A means for immediately generating a warning based on set conditions,

[0833] A means of recognizing the user's emotional state and adjusting the way information is presented based on that information,

[0834] A system that includes this.

[0835] (Claim 2)

[0836] The system according to claim 1, wherein the language processing technique includes subject modeling and sentiment analysis.

[0837] (Claim 3)

[0838] The system according to claim 1, wherein the generated report is customizable by the user, and the presentation method is dynamically adjusted based on the user's emotional state. [Explanation of symbols]

[0839] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting data from an information gathering device, A means of preprocessing the collected data, A means of analyzing pre-processed data using natural language processing techniques and extracting important information, A means of generating the extracted information in report format, A means of generating alerts in real time based on set conditions, A system that includes this.

2. The system according to claim 1, wherein the natural language processing technique includes topic modeling and sentiment analysis.

3. The system according to claim 1, wherein the generated report can be customized by the user.

Images