system

Abstract

Provide a system. A data collection means for collecting impressions and opinions from local users; A natural language processing method to extract keywords and emotions from collected data and classify and analyze them into specific categories. a visualization means for visualizing the analysis results; an information providing means for providing the visualized information to a user; A system including:

Description

[Technical Field]

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

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

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

[0004] It is important for winter sports enthusiasts and ski resort operators to obtain accurate and timely information about local weather and ski resort conditions. However, current information collection methods lack the means to efficiently collect and analyze the impressions and opinions of individual users, resulting in a lack of reliability and real-time information. The present invention aims to solve these problems by providing a system that automatically collects and analyzes the impressions and opinions of local users and provides accurate, real-time information about weather conditions and ski resort conditions. [Means for solving the problem]

[0005] The system of the present invention comprises the following means:

[0006] 1. Data collection methods to gather feedback and opinions from local users;

[0007] 2. Natural language processing means to extract keywords and emotions from collected data and classify and analyze them into specific categories;

[0008] 3. Visualization tools for visualizing the analysis results;

[0009] 4. An information provision means for providing visualized information to users.

[0010] The device collects posts from local users from a specified URL, and the server stores the collected data. The server then analyzes the data using a natural language processing algorithm, classifying it by category and performing sentiment analysis. The analysis results are visualized in graphs and dashboard format, which users can view on their device. This configuration creates a system that can efficiently provide accurate, real-time information on local weather conditions and ski resort conditions.

[0011] "Local users" are those who visit ski resorts and winter sports facilities and post their experiences and impressions online.

[0012] "Impressions and opinions" are text-based posts by local users about the ski resort and weather conditions.

[0013] "Data collection means" refers to technology or devices for automatically collecting posts from local users on the Internet.

[0014] "Natural language processing tools" are algorithms and software that extract keywords and emotions from collected text data and analyze each post.

[0015] "Visualization means" refers to functions and tools for displaying analysis results in visual formats such as graphs and dashboards.

[0016] "Information providing means" refers to a system or device that displays the analysis results in a format that is easy for the user to understand and provides the necessary information.

[0017] "Keywords" are important words related to the weather and ski resort conditions in users' impressions and opinions.

[0018] "Emotion" refers to the positive or negative emotional expression contained in the user's postings.

[0019] A "category" is a classification item for classifying user posts, and includes, for example, snow conditions, temperature, wind speed, and the like.

[0020] "Analysis results" are the classification and analysis results of keywords and emotions obtained by natural language processing means.

[0021] "Graphs and dashboards" are charts and information panels that visually display analysis results to users. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0024] First, the terms used in the following description will be explained.

[0025] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0026] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0027] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0028] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0029] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0033] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0034] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0035] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0036] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0037] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0040] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0041] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0042] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0043] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions. The system is mainly composed of four main elements: data collection means, natural language processing means, visualization means, and information provision means.

[0044] Data collection methods

[0045] To gather the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. Specifically, the device collects user posts from online review sites and social networking services (SNS). In this case, the device sends an HTTP request and receives HTML data as a response. For example, if a local user's review says, "The snow was amazing today!", this text data is obtained.

[0046] Natural language processing tools

[0047] The server analyzes the collected data. It uses natural language processing (NLP) algorithms to extract keywords and sentiment from the collected text data and classify them into specific categories, such as "snow sentiment (positive)" and "temperature sentiment (negative)." TextBlob and other NLP tools are used to calculate a sentiment score for each post, which is then stored in a database along with the keywords.

[0048] Visualization means

[0049] The server then visualizes the data in graphs or dashboards based on the analysis results. For example, if there are many positive comments about snow conditions, the server calculates the average sentiment score for that category and displays it in the form of a bar graph or pie chart. This allows the device to provide information to users in a visually easy-to-understand format.

[0050] Information provision means

[0051] Users access the system via their terminals to obtain the information they need. For example, if a user enters a query such as "What are the conditions at the ski resort today?", the terminal retrieves the latest analysis results from the server and provides the user with an answer such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Visualized graphs and dashboards are also displayed to the user, allowing them to visually check more detailed information.

[0052] Specific examples

[0053] Below is a specific example. When a user visits a ski resort, they post on social media that "the snow was deep today and it was easy to ski." The device collects these posts, and the server uses natural language processing to extract keywords related to "snow" and "positive" emotions. As a result, the server records the "snow conditions are very good" in the database and reflects this in a graph using visualization tools. The next time the user checks the "ski resort conditions," this information is displayed on the device, and they can use it as a reference for when to visit next.

[0054] As described above, the system of the present invention effectively collects and analyzes the impressions and opinions of local users and provides accurate, real-time information on weather conditions and ski resort conditions.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The device collects local user impressions and opinions from a specified URL. The device sends an HTTP request and receives HTML data as a response. For example, when collecting posts from a social networking site or review site, the device accesses the required URL and downloads the data.

[0058] Step 2:

[0059] The server analyzes the HTML data it has retrieved. Using an HTML parser such as BeautifulSoup, the server extracts the necessary text information (post content). Specifically, it searches for specific HTML tags and extracts the user posts contained therein in text format.

[0060] Step 3:

[0061] The server runs the extracted text data through a natural language processing (NLP) algorithm. Using a library such as TextBlob, the server extracts keywords and sentiment scores from each post. For example, from a post saying "The snow was amazing," the server extracts the keyword "snow" and a "positive" sentiment score.

[0062] Step 4:

[0063] The server classifies each post into a specific category (e.g., snow conditions, temperature, wind speed) based on the extracted keywords and sentiment score. The server stores these results in a database. For example, if there are many posts about "snow" and the sentiment score is positive, it will be recorded as "good snow conditions."

[0064] Step 5:

[0065] The server calculates the average sentiment score for each category based on the accumulated data. Using the calculated scores, the server visualizes the data in visual formats such as bar graphs and pie charts. The results are created as image files or interactive dashboards.

[0066] Step 6:

[0067] A user accesses the system using a terminal and requests the required information. For example, the user types a query such as "What are the ski conditions like today?"

[0068] Step 7:

[0069] The device sends a query to the server to obtain the latest analysis results, and the server searches for the relevant information from the stored data and provides it to the device.

[0070] Step 8:

[0071] Based on the calculations and visualizations obtained by the device, the device displays specific information to the user, such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm," and also displays graphs and dashboards when available.

[0072] This allows users to get accurate, real-time information about local weather conditions and ski resort conditions.

[0073] Example 1

[0074] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0075] There is a need to efficiently collect impressions and opinions from local users, accurately analyze them, and provide information in real time. However, conventional systems have limited the scope of data collection and have issues with analysis accuracy. Furthermore, they lack sufficient visualization methods to make the collected data easier to understand visually, and methods for effectively providing information to users. The present invention aims to solve these issues and provide more accurate and convenient information.

[0076] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0077] In this invention, the server includes data collection means for collecting impressions and opinions from local users, natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, visualization means for visually displaying the analysis results, information provision means for providing the visualized information to the user, preprocessing means for preprocessing the data collected by the terminal, and process flow handling means for controlling the flow of program processing. This makes it possible to comprehensively collect a variety of opinions from local users, analyze and visualize them with high accuracy, and effectively provide information to the user.

[0078] "Data collection methods" refers to the technology and equipment used to collect impressions and opinions of local users from the Internet. Specifically, this includes web scraping technology.

[0079] "Natural language processing means" refers to the technology and algorithms used to extract keywords and emotions from collected text data and classify and analyze them into specific categories.

[0080] "Visualization means" refers to techniques and tools for visually displaying analysis results, including means for providing data in the form of graphs, dashboards, etc.

[0081] "Information provision means" refers to the technology and interface for providing visualized information to users.

[0082] "Preprocessing means" refers to techniques such as data cleaning and tokenization to convert data collected by the terminal into an analyzable format.

[0083] "Processing flow handling means" refers to the techniques and methods for controlling and regulating the processing flow of a program from data collection to information provision.

[0084] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions. This system consists of six main components: data collection means, natural language processing means, visualization means, information provision means, preprocessing means, and processing flow handling means.

[0085] Data collection methods

[0086] To collect the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. Specifically, data is collected from social media and review sites using the Python library Beautiful Soup and Selenium. The device sends an HTTP request to receive the HTML data of the webpage, which is then analyzed to extract text data. For example, if a user posts on social media, "The snow was amazing today!", that text data is collected.

[0087] Pretreatment means

[0088] The device preprocesses the text data it receives to make it analyzable. Specifically, it removes unnecessary tags and special characters, tokenizes the text, and splits it into words. This process improves the quality of the data and prepares it for accurate analysis.

[0089] Natural language processing tools

[0090] The server analyzes the collected text data. Specifically, it uses Python's natural language processing libraries, TextBlob and NLTK, to extract keywords and sentiment from the text. The server then uses these keywords and sentiment scores to classify the data into specific categories. For example, the server extracts the keyword "snow" and positive sentiment from a post that says, "The snow was amazing today!" This information is then stored in a database.

[0091] Visualization means

[0092] The server visually displays the analysis results. Using Python visualization libraries Matplotlib and Plotly, sentiment scores and keyword frequency are displayed in graphs and dashboards. This allows users to view information in a visually easy-to-understand format. For example, if there are many positive comments about snow, the data can be displayed in a bar graph or pie chart.

[0093] Information provision means

[0094] Users access the system via their terminals to obtain the necessary information. When a user enters a query into their terminal, such as "What are the conditions at the ski resort today?", the terminal sends the request to the server. The server returns the latest analysis results, and the user receives information such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm."

[0095] Specific examples

[0096] For example, when a user visits a ski resort, they post on social media that "the snow was deep today and easy to ski on." The device collects these posts, and the server uses natural language processing to extract keywords and positive emotions related to "snow." As a result, the information that "the snow conditions are very good" is recorded in the database. This information is reflected in a graph using visualization tools, and the next time the user checks the "ski resort conditions," they can visually confirm this information on their device and use it as a reference for when to visit next.

[0097] Example prompt sentence:

[0098] "How are the ski conditions today?"

[0099] Please tell me the snow conditions at the ski resort.

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] The device sends an HTTP request to a specified URL to collect impressions and opinions from local users. The input is the URL to be collected, and the output is the HTML data of the web page. Specifically, the HTTP request is made using the requests library.

[0103] Step 2:

[0104] The Beautiful Soup library is used to parse the HTML data received by the device. The input is the HTML data obtained in step 1, and the output is text data containing impressions and opinions. Specifically, Beautiful Soup parses the HTML data and extracts text data from the specified tags and classes.

[0105] Step 3:

[0106] The text data extracted by the terminal is preprocessed and converted into an analyzable format. The input is the text data extracted in step 2, and the output is the cleaned text data. Specific operations include removing special characters and trimming spaces.

[0107] Step 4:

[0108] The terminal tokenizes the preprocessed data and splits it into words. The input is the cleaned text data obtained in step 3, and the output is the tokenized text data. Specifically, tokenization is performed using the NLTK library.

[0109] Step 5:

[0110] The server performs natural language processing to extract keywords and sentiment from the tokenized text data. The input is the tokenized text data obtained in step 4, and the output is keywords and sentiment scores. Specifically, sentiment analysis is performed using the TextBlob library to extract keywords.

[0111] Step 6:

[0112] The server saves the extracted keywords and sentiment scores in a database. The input is the keywords and sentiment scores obtained in step 5, and the output is the results saved in the database. Specifically, it writes the results to the database using SQLAlchemy.

[0113] Step 7:

[0114] The server visualizes the data based on the analysis results stored in the database. The input is the analysis results stored in the database, and the output is visual data in the form of graphs or dashboards. Specifically, the data is displayed visually using Matplotlib or Plotly.

[0115] Step 8:

[0116] A user accesses the system via a terminal and enters a query. The input is the query entered by the user, and the output is an answer based on the analysis results. Specifically, the user's query is sent to the server, which retrieves the latest analysis results from the database and returns them.

[0117] Step 9:

[0118] The terminal provides the user with the analysis results received from the server. The input is the analysis results returned from the server, and the output is the information provided to the user. Specifically, the results are formatted and displayed in a user-friendly format.

[0119] The above processing steps realize a system that efficiently collects opinions and impressions from local users, analyzes them with high accuracy, and provides information in real time.

[0120] (Application example 1)

[0121] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0122] Modern food delivery services require a method for efficiently collecting and analyzing user feedback on the quality of food and delivery in real time. Conventional systems often collect and analyze reviews manually, making it difficult to provide accurate and timely information. This makes it difficult for users to select a service based on the most up-to-date information, and it is also difficult for service providers to properly understand customer satisfaction. Therefore, there is a need to develop a system that automatically collects and analyzes reviews of food delivery services and provides information to users in an easy-to-understand manner.

[0123] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0124] In this invention, the server includes a data collection means for collecting opinions from local users, a natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, a visualization means for visualizing the analysis results, and an information provision means for providing the visualized information to users. This allows users to easily obtain the latest review information by combining the means for collecting and analyzing reviews about food and delivery with the means for generating information about food and delivery services based on the analyzed reviews.

[0125] "Data collection means" refers to means for collecting opinions from local users.

[0126] "Natural language processing means" is a means of extracting keywords and emotions from collected data and classifying and analyzing them into specific categories.

[0127] "Visualization means" refers to a means for displaying analysis results in the form of graphs or dashboards.

[0128] The "information providing means" is a means for providing visualized information to a user.

[0129] "Reviews" are impressions and opinions written by users about the quality of food and delivery of food delivery services.

[0130] "Analysis" is the act of processing collected data and extracting meaningful information.

[0131] "Food" refers to food and drink delivered by a food delivery service.

[0132] "Delivery" refers to the act of delivering ordered food to a designated location in a food delivery service.

[0133] "Services" refers to the overall assistance and support provided in food delivery.

[0134] A "natural language processing algorithm" is an algorithm for extracting linguistic features from text data.

[0135] "Web scraping" is a technique for automatically collecting specific information from websites.

[0136] The system of this invention collects and analyzes user reviews of food delivery services and provides real-time information about the quality of food and delivery. The system is mainly composed of four main components: data collection means, natural language processing means, visualization means, and information provision means.

[0137] Data collection methods

[0138] The server uses web scraping technology to collect local user reviews from the Internet. The server sends an HTTP request and receives HTML data as a response. For example, a user might post about a food delivery service, saying, "The food was hot and delicious, but the delivery was late." The server collects this post.

[0139] Natural language processing tools

[0140] The server analyzes the collected reviews. It uses natural language processing algorithms to extract keywords and sentiment from the text data. Specifically, it uses TextBlob and other NLP tools to calculate a sentiment score for each post and store it in a database along with keywords. For example, reviews are categorized as "Cooking (positive)" or "Delivery (negative)."

[0141] Visualization means

[0142] The server visualizes the data based on the analysis results. The analyzed data is displayed in graphs and dashboards, providing information in a visually easy-to-understand format for users. For example, it allows users to visually see at a glance which dishes have many positive reviews and which delivery items have many negative reviews.

[0143] Information provision means

[0144] Users access the system via their devices to obtain the information they need. For example, if a user enters a query such as "How was the food delivery service today?", the server retrieves the latest analysis results and provides detailed information via the device, such as "The food was highly rated, but the delivery was a little late." Graphs and dashboards are also displayed to help users gain a deeper understanding.

[0145] Specific examples

[0146] Suppose a user posts on social media, "How was today's dinner delivery service?" and the post states, "The food was hot and delicious, but the delivery was late." The server collects these posts and uses natural language processing to extract emotions related to "food (positive)" and "delivery (negative)." The analysis results are then displayed in a graph using visualization tools, which are then displayed to the user via their device.

[0147] Example prompts to input to a generative AI model:

[0148] Analyze the sentiment of the reviews below.

[0149] Review: The food was hot and delicious, but the delivery was late.

[0150] As a result, this system allows users to easily obtain the latest review information for food delivery services, providing reference information for users when selecting a service and enabling service providers to quickly receive feedback to improve customer satisfaction.

[0151] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0152] Step 1:

[0153] The server uses web scraping technology to collect local user reviews from the Internet. The server sends an HTTP request and analyzes the HTML data received as a response to extract the review text data.

[0154] Input: URL of online review site or social media

[0155] Output: Text list of reviews

[0156] What happens: The server accesses the specified URL, retrieves the HTML page, and uses a library such as BeautifulSoup to extract the reviews and save them as text data in a list.

[0157] Step 2:

[0158] The server analyzes the collected reviews using natural language processing (NLP) techniques, such as TextBlob and other NLP tools, to extract keywords and sentiment scores from the text data.

[0159] Input: The list of reviews in text format collected in Step 1

[0160] Output: A list of keywords and sentiment scores

[0161] Specific operation: It uses TextBlob to analyze each review and calculate the sentiment score, and at the same time, extracts important keywords and stores them in the database together with the sentiment score.

[0162] Step 3:

[0163] The server uses visualization tools to display the analysis results in the form of graphs or dashboards, for example, visually representing the number of positive / negative reviews or the frequency of specific keywords.

[0164] Input: List of keywords and sentiment scores extracted in step 2

[0165] Output: Visualized data in the form of graphs and dashboards

[0166] Specific operations: Using libraries such as matplotlib and D3.js, the frequency of keywords and sentiment scores are aggregated, and data is generated to display them in the form of bar graphs, pie charts, etc.

[0167] Step 4:

[0168] Users access the system via their terminals and obtain the necessary information. Analysis results and visualized information are provided to the user via the terminals. For example, in response to a query such as "How was the food delivery service today?", the terminal displays information based on the analysis results to the user.

[0169] Input: User query (e.g., "How was the food delivery service today?")

[0170] Output: Information based on the analysis results (e.g., "The food is highly rated, but delivery is often delayed")

[0171] Specific operation: When a user inputs a query into the system from a terminal, the server searches the latest analysis results, retrieves the relevant information, sends the retrieved information to the terminal, and displays it in a form that can be visually confirmed by the user.

[0172] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0173] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions, and also combines an emotion engine that recognizes user emotions. The system is mainly composed of five main elements: a data collection means, a natural language processing means, an emotion engine, a visualization means, and an information provision means.

[0174] Data collection methods

[0175] To gather the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. The device collects user posts from online review sites and social media. In doing so, the device sends an HTTP request and receives HTML data as a response. For example, a user post such as "The snow was amazing today!" may be obtained.

[0176] Natural language processing tools

[0177] The server analyzes the collected data. It uses natural language processing (NLP) algorithms to extract keywords from the text data. For example, it extracts the keyword "snow" from a post that says "The snow was amazing."

[0178] Emotion Engine

[0179] The server applies a sentiment engine to the collected text data to recognize emotions. The sentiment engine uses an algorithm to classify positive, negative, and neutral sentiments and calculates a sentiment score for each post. For example, a post saying "The snow was great today" would be recognized as having a positive sentiment score.

[0180] Visualization means

[0181] The server then uses the analysis results to visualize the data in graphs and dashboards. The server calculates the average sentiment score for each category and creates bar graphs, pie charts, and other visualizations to visualize the results. For example, if the snow conditions receive a lot of positive feedback, that category will be displayed as highly rated.

[0182] Information provision means

[0183] Users access the system via their terminal and request the information they need. For example, if a user types, "What are the conditions at the ski resort today?", the terminal retrieves the latest analysis results from the server and provides the user with an answer such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Visualized graphs and dashboards are also displayed to the user, allowing them to visually confirm specific information.

[0184] As a concrete example, consider the case where a user visits a ski resort and posts on social media, "It was windy and cold today, but the snow conditions were perfect." The device collects these posts, and the server analyzes them using natural language processing and an emotion engine. Keywords such as "wind," "temperature," and "snow" are extracted from the post, and an emotion score for each is calculated. As a result, the emotion for "wind" is classified as negative, the emotion for "temperature" as negative, and the emotion for "snow conditions" as positive. The results of this analysis are reflected in a graph, and the next time the user checks the "ski resort conditions," this information is provided via the device, making it useful for the user's next visit.

[0185] As described above, the system of the present invention effectively collects and analyzes the impressions and opinions of local users and provides accurate, real-time information on weather conditions and ski resort conditions. By combining it with an emotion engine, more accurate analysis results based on user emotions can be obtained.

[0186] The processing flow will be explained below.

[0187] Step 1:

[0188] The device sends an HTTP request to a specified URL to collect impressions and opinions from local users. The device accesses review sites and social media pages on the Internet and retrieves HTML data.

[0189] Step 2:

[0190] The server analyzes the HTML data received from the device. The server uses an HTML parser such as BeautifulSoup to search for specific tags within the page and extract the required text information (post content). For example, Extract the text inside the tag.

[0191] Step 3:

[0192] The server runs the extracted text data through a natural language processing (NLP) algorithm, extracts keywords from the text data, and sends them to the emotion engine. Specifically, it uses TextBlob or a similar library to analyze keywords and sentence structure within the text.

[0193] Step 4:

[0194] The server uses an emotion engine to recognize emotions from the extracted text data. The emotion engine uses an algorithm to classify emotions into positive, negative, and neutral, and calculates an emotion score for each post. For example, a post saying "The snow was amazing today" would be classified as having a positive emotion score.

[0195] Step 5:

[0196] The server classifies each post into a specific category (e.g., snow conditions, temperature, wind) based on the sentiment score and keywords obtained from the sentiment engine. This context-based classification is then stored in a database. For example, the keyword "snow" with a positive sentiment score would be classified as "snow conditions."

[0197] Step 6:

[0198] The server calculates the average sentiment score based on the accumulated data. The server aggregates the sentiment scores for each category and calculates the overall average. For example, if there are multiple posts in the same category, the sentiment scores are averaged.

[0199] Step 7:

[0200] The server visualizes the analysis results, generating information to display the data in formats such as bar graphs and pie charts. A visualization tool is used to create graphs and dashboards that visually represent the calculated average sentiment scores.

[0201] Step 8:

[0202] A user accesses the system using a terminal and requests specific information. The user types a query into the terminal, such as "What are the ski resort conditions today?"

[0203] Step 9:

[0204] The device sends the user's query to the server, which searches and retrieves the latest analysis results from the database and generates information corresponding to the request.

[0205] Step 10:

[0206] The device displays the analysis results it receives from the server to the user. For example, the device provides information in text format such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Generated graphs and dashboards are also displayed, allowing the user to check the details through visual information.

[0207] Examples:

[0208] After visiting a ski resort, a user posts on social media, "Today was windy and cold, but the snow conditions were perfect." The device collects these posts, and the server analyzes them using natural language processing and an emotion engine. A positive emotion score is assigned to the "snow conditions," and negative emotion scores are assigned to the "wind" and "temperature," and the results are stored in a database. The next time the user checks the "ski resort conditions," this information is provided via the device. The user is shown specific information such as "The snow conditions were good, but the temperature and wind were not so good." This information can be used as a reference when considering their next visit.

[0209] Example 2

[0210] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0211] Currently, there is no system that can collect and analyze accurate and useful information about weather and ski resort conditions from numerous reviews and social media posts in real time and provide it to users. Furthermore, existing systems are unable to properly analyze user emotions, which often limits the usefulness of the information. There is a need to develop a system that can quickly and appropriately provide users with the information they need.

[0212] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an information collection means for collecting impressions and opinions from local users, a natural language processing means for extracting keywords and emotions from the collected information and classifying and analyzing them into specific categories, an emotion analysis means for calculating an emotion score based on the analysis results, a display means for visually displaying the data, and an information provision means for providing the analysis results including the visualized information to the user. This makes it possible to quickly collect various opinions and impressions from local users and provide accurate information on weather conditions and ski resort conditions in real time. Furthermore, analyzing users' emotions improves the usefulness and accuracy of the information.

[0213] "Information gathering means" refers to technology for obtaining impressions and opinions from local users from specific websites and social networking sites on the Internet.

[0214] "Natural language processing means" is a means for extracting keywords and emotions from collected information and classifying and analyzing them into specific categories.

[0215] The "sentiment analysis means" is an algorithm for calculating and analyzing the sentiment score (positive, negative, neutral) for the collected text data.

[0216] "Display means" refers to software or devices for visualizing analysis results in the form of graphs or dashboards.

[0217] The "information providing means" refers to a method or system for providing the analysis results, including visualized information, to a user.

[0218] "Data collection technology" refers to technology for obtaining information from the Internet, such as review sites and social media.

[0219] A "natural language processing algorithm" is an algorithm used to extract keywords and emotions from text data.

[0220] An "emotion score" is a numerical representation of the emotions in the collected text data, classified as positive, negative, or neutral.

[0221] A "graph" is a diagram such as a bar graph or pie chart that visually displays the analysis results.

[0222] A "dashboard" is an integrated visualization tool that displays multiple analysis results so that they can be viewed at a glance.

[0223] A "user request" is a user's inquiry or request for information from the system.

[0224] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions, and also combines an emotion engine that recognizes user emotions. The system is mainly composed of five main elements: information collection means, natural language processing means, emotion analysis means, display means, and information provision means.

[0225] Hardware and software used

[0226] 1. Information collection methods:

[0227] The device retrieves data from the specified URL using web scraping technology.

[0228] Software used: Python's requests library and BeautifulSoup library are used.

[0229] Example: A user posts, "The snow was absolutely amazing today!"

[0230] 2. Natural Language Processing Tools:

[0231] The server analyzes the collected data.

[0232] Software used: The spaCy library is used to extract keywords from text data.

[0233] Example: Get the keyword "snow" from the post "The snow was amazing."

[0234] 3. Emotion analysis means:

[0235] The server applies an emotion engine to the collected text data to recognize emotions.

[0236] Software used: The NLTK library is used to calculate sentiment scores.

[0237] Example: A post saying "The snow was amazing today" is recognized as having a positive sentiment score.

[0238] 4. Display means:

[0239] Based on the analysis results, the server visualizes the data in the form of graphs and dashboards.

[0240] Software used: Uses matplotlib and seaborn libraries.

[0241] Example: If a category receives a lot of positive feedback about snow conditions, it will be displayed as highly rated.

[0242] 5. Information provision method:

[0243] A user accesses the system via a terminal and requests the required information.

[0244] Example: When a user types, "What are the conditions at the ski resort today?", the device retrieves the latest analysis results from the server and provides the user with an answer such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm."

[0245] Prompt Sentence Examples

[0246] Here is an example of a prompt to input to the generative AI model:

[0247] "Please explain in detail the steps to collect user posts through web scraping."

[0248] "Please tell me the specific method for extracting keywords using a natural language processing algorithm."

[0249] "Please explain in detail how the emotion engine calculates the emotion score."

[0250] "Please explain the visualization method and generation procedure for the collected data."

[0251] "How do you generate a response to a user's information request?"

[0252] As described above, the system of the present invention executes each process in detail, from information collection to analysis, emotion recognition, visualization, and information provision, and provides useful information to users in real time. This makes it possible to provide specific and useful weather information and ski resort condition information based on the user's emotions.

[0253] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0254] Program processing flow

[0255] Step 1: Start collecting data

[0256] The device sends an HTTP request to the URL of the specified review site or social media site.

[0257] Specific operation: Uses Python's requests library to access specific review sites and social media pages.

[0258] Input: URL of review site or social media

[0259] Output: HTML data response

[0260] Step 2: Parse the response

[0261] The terminal analyzes the HTML data received as a response.

[0262] What it does: Uses the BeautifulSoup library to parse the HTML document and extract the post content.

[0263] Input: HTML data

[0264] Output: User submitted data

[0265] Step 3: Save data

[0266] The device temporarily stores the extracted posting data.

[0267] Specific operation: Save the extracted text data in a file in JSON format.

[0268] Input: User submitted data

[0269] Output: JSON file

[0270] Step 4: Loading Data

[0271] The server reads the saved JSON file.

[0272] Specific operation: Uses Python's json library to read the file and extract the text data to be analyzed.

[0273] Input: JSON file

[0274] Output: Text data

[0275] Step 5: Applying natural language processing algorithms

[0276] The server uses natural language processing (NLP) algorithms to extract keywords from the text data.

[0277] Specific behavior: Extract specific keywords using the spaCy library.

[0278] Input: Text data

[0279] Output: Extracted keywords

[0280] Step 6: Save your keywords

[0281] The server saves the extracted keywords as a new dataset.

[0282] Specific operation: Save the extracted keywords to a file in CSV format.

[0283] Input: Extracted keywords

[0284] Output: CSV file

[0285] Step 7: Applying the Emotion Engine

[0286] The server applies an emotion engine to the keywords extracted by NLP.

[0287] Specific operation: Uses the NLTK library to calculate the sentiment score (positive, negative, neutral) for each keyword.

[0288] Input: Keyword data

[0289] Output: Sentiment score

[0290] Step 8: Storing sentiment scores

[0291] The server adds the calculated sentiment scores to the dataset.

[0292] Specific behavior: Save the new emotion score in JSON format.

[0293] Input: Sentiment score

[0294] Output: JSON file of data with sentiment scores

[0295] Step 9: Loading Data

[0296] The server loads the dataset with the saved sentiment scores.

[0297] Specific operation: Read data using Python's pandas library.

[0298] Input: JSON file of data with sentiment scores

[0299] Output: Data frame to be analyzed

[0300] Step 10: Generate visualization

[0301] Based on the analysis results, the server visualizes the data in the form of graphs and dashboards.

[0302] Specific operation: Generate bar graphs and pie charts using the matplotlib and seaborn libraries.

[0303] Input: Data to be analyzed

[0304] Output: Visualized graph

[0305] Step 11: Save the visualization

[0306] The server stores the generated visualization results.

[0307] Specific operation: Save the graph image file in PNG format on the server.

[0308] Input: A visualized graph

[0309] Output: PNG file

[0310] Step 12: Receiving a User Request

[0311] The terminal receives an information request from a user.

[0312] What happens: A user enters a natural language query such as "What are the ski conditions like today?"

[0313] Input: User request

[0314] Output: Request data

[0315] Step 13: Database Query

[0316] The server retrieves the latest analysis results from the database based on the user's request.

[0317] Specific behavior: Retrieves the latest information from the database using an SQL query.

[0318] Input: User request data

[0319] Output: Latest analysis results

[0320] Step 14: Response Generation

[0321] The server generates a response to the request.

[0322] Specific behavior: Based on the acquired data, an answer is created using a natural language generation (NLG) model.

[0323] Input: Latest analysis result data

[0324] Output: The generated response

[0325] Step 15: Provide information

[0326] The terminal provides the generated response and visualization results to the user.

[0327] Specific behavior: Display the generated text and graphs on a web page or mobile app interface.

[0328] Input: Generated response, visualized graph

[0329] Output: Information provided to the user

[0330] Through these steps, the system is able to provide accurate and useful information about weather conditions and ski resort conditions based on real-time opinions and feedback from local users.

[0331] (Application example 2)

[0332] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0333] While there are existing systems that efficiently collect, analyze, and visualize the impressions and opinions of local users, they lack the functionality to provide highlights of specific events based on the emotional data associated with the event, making it difficult to provide viewers with personalized highlights in real time during and after the event.

[0334] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0335] In this invention, the server includes a data collection means for collecting impressions and opinions from local users, a natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, a visualization means for visualizing the analysis results, an information provision means for providing the visualized information to users, and a means for providing highlights of the event based on the extracted emotion data, thereby enabling personalized highlights to be provided to viewers in real time.

[0336] A "local user" is a user who provides information related to a particular location or event.

[0337] "Means for collecting impressions and opinions" refers to means for collecting impressions and opinions from users over the Internet.

[0338] "Natural language processing means" is a means of analyzing collected text data, extracting keywords and emotions, and classifying and analyzing them into specific categories.

[0339] "Visualization means" refers to a means for visually displaying the analysis results in the form of graphs or dashboards.

[0340] The "information providing means" is a means for providing visualized information to a user.

[0341] The "means for providing event highlights" is a means for providing the user with highlights and important scenes of a particular event based on the extracted emotion data.

[0342] "Data collection means" refers to means for collecting the impressions and opinions of local users, particularly using web scraping technology.

[0343] A "natural language processing algorithm" is an algorithm used to extract keywords and emotions from text data.

[0344] An "emotion engine" is an algorithm that recognizes and classifies emotions from collected text data.

[0345] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides event highlights. It mainly consists of a data collection means, a natural language processing means, an emotion engine, a visualization means, an information provision means, and a means for providing event highlights.

[0346] Data collection methods

[0347] The server retrieves data from online review sites and social media sites to gather impressions and opinions from local users. Specifically, it uses HTTP requests to gather the necessary information from specified URLs using web scraping technology. For example, it retrieves user posts such as "I saw a lot of great goals today!"

[0348] Natural language processing tools

[0349] The server analyzes the collected data. Natural language processing algorithms are used for this analysis. Keywords and emotions are extracted from the text data, and they are classified and analyzed into specific categories. For example, the keyword "goal" is extracted from a post titled "Great goal," and the emotion score is determined to be positive.

[0350] Emotion Engine

[0351] The server applies an emotion engine to the collected text data to recognize emotions. Specifically, it uses an algorithm that classifies emotions into positive, negative, and neutral, and calculates an emotion score for each post. For example, a post saying, "I saw a lot of great goals today!" would be recognized as having a positive emotion score.

[0352] Visualization means

[0353] The server visualizes the analysis results. The analyzed data is displayed in graphs and dashboards. For example, the average sentiment score for each category is visualized in a bar graph or pie chart. For example, if a goal receives many positive comments, that category is displayed as highly rated.

[0354] Information provision means

[0355] Users can access the system via their device and request the information they need. For example, if a user types, "I want to see the highlights of today's game," the device will retrieve the latest analysis results from the server and provide the user with "highlights of goal scenes that received a lot of positive feedback." In addition, visualized graphs and dashboards are also displayed to the user, allowing them to visually confirm specific information.

[0356] A way to provide highlights of the event

[0357] The server then provides users with highlights and important scenes from a specific event based on the extracted emotion data. For example, it provides users with personalized highlight videos based on goal scenes that garnered very positive feedback or scenes that generated a large amount of negative feedback.

[0358] Specific examples

[0359] For example, if a user posts on social media during a sporting event, "I saw a lot of great goals today!", this post will be recorded as a positive emotion. If another user comments, "The referee's decisions were terrible," this will be classified as a negative emotion. The data collected and analyzed in this way will be used to create highlight videos in real time.

[0360] Example prompts to input to the generative AI model

[0361] Analyze the post "I saw a lot of great goals today!" and output a positive sentiment score.

[0362] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0363] Step 1:

[0364] Data collection

[0365] The device retrieves data from online review sites and social networking sites to collect impressions and opinions from local users. This process uses an HTTP request to retrieve the HTML data of a webpage from a specified URL, and then analyzes it to extract the required text information (impressions and opinions). The input is the URL and HTTP request, and the output is the extracted text data.

[0366] Step 2:

[0367] Natural Language Processing

[0368] The server analyzes the collected text data. In this step, natural language processing algorithms are used to extract keywords and sentiment from the text data and classify each into a specific category. The input is text data, and the output is analyzed data containing keywords and sentiment scores. Specifically, a text analysis library is used to extract nouns and adjectives and perform sentiment analysis.

[0369] Step 3:

[0370] Emotion engine applied

[0371] The server applies an emotion engine based on the analyzed data to calculate an emotion score for each post. The emotion score is classified as positive, negative, or neutral and is output. Specifically, the results of natural language processing are input into an emotion recognition algorithm to score each emotion.

[0372] Step 4:

[0373] Data Visualization

[0374] The server visualizes the sentiment scores and keyword data. This process uses a visualization tool to display the data in graph or dashboard format. The input is the sentiment scores and keyword data, and the output is a visually easy-to-understand graph or dashboard. Specifically, graph drawing libraries such as matplotlib and Plotly are used.

[0375] Step 5:

[0376] Providing information

[0377] Users access the system via a terminal and request the information they need. The server retrieves the latest analysis results and provides real-time event information and highlights to the user. The input is the user request, and the output is the analysis results and visualized data. Specifically, the system searches for appropriate information in response to the user request and displays it through a GUI.

[0378] Step 6:

[0379] Event highlights provided

[0380] The server provides users with highlights and important scenes from specific events based on the extracted emotion data. This process prioritizes scenes with high emotion scores and edits those video clips to create a highlight video. The inputs are emotion scores and event data, and the output is a highlight video. Specifically, video editing software is used to automatically edit video clips based on the emotion scores.

[0381] Example prompts to input to the generative AI model

[0382] Analyze the post "I saw a lot of great goals today!" and output a positive sentiment score.

[0383] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0384] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0385] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0386] [Second embodiment]

[0387] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0388] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0389] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0390] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0391] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0392] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0393] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0394] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0395] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0396] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0397] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0398] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0399] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions. The system is mainly composed of four main elements: data collection means, natural language processing means, visualization means, and information provision means.

[0400] Data collection methods

[0401] To gather the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. Specifically, the device collects user posts from online review sites and social networking services (SNS). In this case, the device sends an HTTP request and receives HTML data as a response. For example, if a local user's review says, "The snow was amazing today!", this text data is obtained.

[0402] Natural language processing tools

[0403] The server analyzes the collected data. It uses natural language processing (NLP) algorithms to extract keywords and sentiment from the collected text data and classify them into specific categories, such as "snow sentiment (positive)" and "temperature sentiment (negative)." TextBlob and other NLP tools are used to calculate a sentiment score for each post, which is then stored in a database along with the keywords.

[0404] Visualization means

[0405] The server then visualizes the data in graphs or dashboards based on the analysis results. For example, if there are many positive comments about snow conditions, the server calculates the average sentiment score for that category and displays it in the form of a bar graph or pie chart. This allows the device to provide information to users in a visually easy-to-understand format.

[0406] Information provision means

[0407] Users access the system via their terminals to obtain the information they need. For example, if a user enters a query such as "What are the conditions at the ski resort today?", the terminal retrieves the latest analysis results from the server and provides the user with an answer such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Visualized graphs and dashboards are also displayed to the user, allowing them to visually check more detailed information.

[0408] Specific examples

[0409] Below is a specific example. When a user visits a ski resort, they post on social media that "the snow was deep today and it was easy to ski." The device collects these posts, and the server uses natural language processing to extract keywords related to "snow" and "positive" emotions. As a result, the server records the "snow conditions are very good" in the database and reflects this in a graph using visualization tools. The next time the user checks the "ski resort conditions," this information is displayed on the device, and they can use it as a reference for when to visit next.

[0410] As described above, the system of the present invention effectively collects and analyzes the impressions and opinions of local users and provides accurate, real-time information on weather conditions and ski resort conditions.

[0411] The processing flow will be explained below.

[0412] Step 1:

[0413] The device collects local user impressions and opinions from a specified URL. The device sends an HTTP request and receives HTML data as a response. For example, when collecting posts from a social networking site or review site, the device accesses the required URL and downloads the data.

[0414] Step 2:

[0415] The server analyzes the HTML data it has retrieved. Using an HTML parser such as BeautifulSoup, the server extracts the necessary text information (post content). Specifically, it searches for specific HTML tags and extracts the user posts contained therein in text format.

[0416] Step 3:

[0417] The server runs the extracted text data through a natural language processing (NLP) algorithm. Using a library such as TextBlob, the server extracts keywords and sentiment scores from each post. For example, from a post saying "The snow was amazing," the server extracts the keyword "snow" and a "positive" sentiment score.

[0418] Step 4:

[0419] The server classifies each post into a specific category (e.g., snow conditions, temperature, wind speed) based on the extracted keywords and sentiment score. The server stores these results in a database. For example, if there are many posts about "snow" and the sentiment score is positive, it will be recorded as "good snow conditions."

[0420] Step 5:

[0421] The server calculates the average sentiment score for each category based on the accumulated data. Using the calculated scores, the server visualizes the data in visual formats such as bar graphs and pie charts. The results are created as image files or interactive dashboards.

[0422] Step 6:

[0423] A user accesses the system using a terminal and requests the required information. For example, the user types a query such as "What are the ski conditions like today?"

[0424] Step 7:

[0425] The device sends a query to the server to obtain the latest analysis results, and the server searches for the relevant information from the stored data and provides it to the device.

[0426] Step 8:

[0427] Based on the calculations and visualizations obtained by the device, the device displays specific information to the user, such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm," and also displays graphs and dashboards when available.

[0428] This allows users to get accurate, real-time information about local weather conditions and ski resort conditions.

[0429] Example 1

[0430] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0431] There is a need to efficiently collect impressions and opinions from local users, accurately analyze them, and provide information in real time. However, conventional systems have limited the scope of data collection and have issues with analysis accuracy. Furthermore, they lack sufficient visualization methods to make the collected data easier to understand visually, and methods for effectively providing information to users. The present invention aims to solve these issues and provide more accurate and convenient information.

[0432] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0433] In this invention, the server includes data collection means for collecting impressions and opinions from local users, natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, visualization means for visually displaying the analysis results, information provision means for providing the visualized information to the user, preprocessing means for preprocessing the data collected by the terminal, and process flow handling means for controlling the flow of program processing. This makes it possible to comprehensively collect a variety of opinions from local users, analyze and visualize them with high accuracy, and effectively provide information to the user.

[0434] "Data collection methods" refers to the technology and equipment used to collect impressions and opinions of local users from the Internet. Specifically, this includes web scraping technology.

[0435] "Natural language processing means" refers to the technology and algorithms used to extract keywords and emotions from collected text data and classify and analyze them into specific categories.

[0436] "Visualization means" refers to techniques and tools for visually displaying analysis results, including means for providing data in the form of graphs, dashboards, etc.

[0437] "Information provision means" refers to the technology and interface for providing visualized information to users.

[0438] "Preprocessing means" refers to techniques such as data cleaning and tokenization to convert data collected by the terminal into an analyzable format.

[0439] "Processing flow handling means" refers to the techniques and methods for controlling and regulating the processing flow of a program from data collection to information provision.

[0440] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions. This system consists of six main components: data collection means, natural language processing means, visualization means, information provision means, preprocessing means, and processing flow handling means.

[0441] Data collection methods

[0442] To collect the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. Specifically, data is collected from social media and review sites using the Python library Beautiful Soup and Selenium. The device sends an HTTP request to receive the HTML data of the webpage, which is then analyzed to extract text data. For example, if a user posts on social media, "The snow was amazing today!", that text data is collected.

[0443] Pretreatment means

[0444] The device preprocesses the text data it receives to make it analyzable. Specifically, it removes unnecessary tags and special characters, tokenizes the text, and splits it into words. This process improves the quality of the data and prepares it for accurate analysis.

[0445] Natural language processing tools

[0446] The server analyzes the collected text data. Specifically, it uses Python's natural language processing libraries, TextBlob and NLTK, to extract keywords and sentiment from the text. The server then uses these keywords and sentiment scores to classify the data into specific categories. For example, the server extracts the keyword "snow" and positive sentiment from a post that says, "The snow was amazing today!" This information is then stored in a database.

[0447] Visualization means

[0448] The server visually displays the analysis results. Using Python visualization libraries Matplotlib and Plotly, sentiment scores and keyword frequency are displayed in graphs and dashboards. This allows users to view information in a visually easy-to-understand format. For example, if there are many positive comments about snow, the data can be displayed in a bar graph or pie chart.

[0449] Information provision means

[0450] Users access the system via their terminals to obtain the necessary information. When a user enters a query into their terminal, such as "What are the conditions at the ski resort today?", the terminal sends the request to the server. The server returns the latest analysis results, and the user receives information such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm."

[0451] Specific examples

[0452] For example, when a user visits a ski resort, they post on social media that "the snow was deep today and easy to ski on." The device collects these posts, and the server uses natural language processing to extract keywords and positive emotions related to "snow." As a result, the information that "the snow conditions are very good" is recorded in the database. This information is reflected in a graph using visualization tools, and the next time the user checks the "ski resort conditions," they can visually confirm this information on their device and use it as a reference for when to visit next.

[0453] Example prompt sentence:

[0454] "How are the ski conditions today?"

[0455] Please tell me the snow conditions at the ski resort.

[0456] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0457] Step 1:

[0458] The device sends an HTTP request to a specified URL to collect impressions and opinions from local users. The input is the URL to be collected, and the output is the HTML data of the web page. Specifically, the HTTP request is made using the requests library.

[0459] Step 2:

[0460] The Beautiful Soup library is used to parse the HTML data received by the device. The input is the HTML data obtained in step 1, and the output is text data containing impressions and opinions. Specifically, Beautiful Soup parses the HTML data and extracts text data from the specified tags and classes.

[0461] Step 3:

[0462] The text data extracted by the terminal is preprocessed and converted into an analyzable format. The input is the text data extracted in step 2, and the output is the cleaned text data. Specific operations include removing special characters and trimming spaces.

[0463] Step 4:

[0464] The terminal tokenizes the preprocessed data and splits it into words. The input is the cleaned text data obtained in step 3, and the output is the tokenized text data. Specifically, tokenization is performed using the NLTK library.

[0465] Step 5:

[0466] The server performs natural language processing to extract keywords and sentiment from the tokenized text data. The input is the tokenized text data obtained in step 4, and the output is keywords and sentiment scores. Specifically, sentiment analysis is performed using the TextBlob library to extract keywords.

[0467] Step 6:

[0468] The server saves the extracted keywords and sentiment scores in a database. The input is the keywords and sentiment scores obtained in step 5, and the output is the results saved in the database. Specifically, it writes the results to the database using SQLAlchemy.

[0469] Step 7:

[0470] The server visualizes the data based on the analysis results stored in the database. The input is the analysis results stored in the database, and the output is visual data in the form of graphs or dashboards. Specifically, the data is displayed visually using Matplotlib or Plotly.

[0471] Step 8:

[0472] A user accesses the system via a terminal and enters a query. The input is the query entered by the user, and the output is an answer based on the analysis results. Specifically, the user's query is sent to the server, which retrieves the latest analysis results from the database and returns them.

[0473] Step 9:

[0474] The terminal provides the user with the analysis results received from the server. The input is the analysis results returned from the server, and the output is the information provided to the user. Specifically, the results are formatted and displayed in a user-friendly format.

[0475] The above processing steps realize a system that efficiently collects opinions and impressions from local users, analyzes them with high accuracy, and provides information in real time.

[0476] (Application example 1)

[0477] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0478] Modern food delivery services require a method for efficiently collecting and analyzing user feedback on the quality of food and delivery in real time. Conventional systems often collect and analyze reviews manually, making it difficult to provide accurate and timely information. This makes it difficult for users to select a service based on the most up-to-date information, and it is also difficult for service providers to properly understand customer satisfaction. Therefore, there is a need to develop a system that automatically collects and analyzes reviews of food delivery services and provides information to users in an easy-to-understand manner.

[0479] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0480] In this invention, the server includes a data collection means for collecting opinions from local users, a natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, a visualization means for visualizing the analysis results, and an information provision means for providing the visualized information to users. This allows users to easily obtain the latest review information by combining the means for collecting and analyzing reviews about food and delivery with the means for generating information about food and delivery services based on the analyzed reviews.

[0481] "Data collection means" refers to means for collecting opinions from local users.

[0482] "Natural language processing means" is a means of extracting keywords and emotions from collected data and classifying and analyzing them into specific categories.

[0483] "Visualization means" refers to a means for displaying analysis results in the form of graphs or dashboards.

[0484] The "information providing means" is a means for providing visualized information to a user.

[0485] "Reviews" are impressions and opinions written by users about the quality of food and delivery of food delivery services.

[0486] "Analysis" is the act of processing collected data and extracting meaningful information.

[0487] "Food" refers to food and drink delivered by a food delivery service.

[0488] "Delivery" refers to the act of delivering ordered food to a designated location in a food delivery service.

[0489] "Services" refers to the overall assistance and support provided in food delivery.

[0490] A "natural language processing algorithm" is an algorithm for extracting linguistic features from text data.

[0491] "Web scraping" is a technique for automatically collecting specific information from websites.

[0492] The system of this invention collects and analyzes user reviews of food delivery services and provides real-time information about the quality of food and delivery. The system is mainly composed of four main components: data collection means, natural language processing means, visualization means, and information provision means.

[0493] Data collection methods

[0494] The server uses web scraping technology to collect local user reviews from the Internet. The server sends an HTTP request and receives HTML data as a response. For example, a user might post about a food delivery service, saying, "The food was hot and delicious, but the delivery was late." The server collects this post.

[0495] Natural language processing tools

[0496] The server analyzes the collected reviews. It uses natural language processing algorithms to extract keywords and sentiment from the text data. Specifically, it uses TextBlob and other NLP tools to calculate a sentiment score for each post and store it in a database along with keywords. For example, reviews are categorized as "Cooking (positive)" or "Delivery (negative)."

[0497] Visualization means

[0498] The server visualizes the data based on the analysis results. The analyzed data is displayed in graphs and dashboards, providing information in a visually easy-to-understand format for users. For example, it allows users to visually see at a glance which dishes have many positive reviews and which delivery items have many negative reviews.

[0499] Information provision means

[0500] Users access the system via their devices to obtain the information they need. For example, if a user enters a query such as "How was the food delivery service today?", the server retrieves the latest analysis results and provides detailed information via the device, such as "The food was highly rated, but the delivery was a little late." Graphs and dashboards are also displayed to help users gain a deeper understanding.

[0501] Specific examples

[0502] Suppose a user posts on social media, "How was today's dinner delivery service?" and the post states, "The food was hot and delicious, but the delivery was late." The server collects these posts and uses natural language processing to extract emotions related to "food (positive)" and "delivery (negative)." The analysis results are then displayed in a graph using visualization tools, which are then displayed to the user via their device.

[0503] Example prompts to input to a generative AI model:

[0504] Analyze the sentiment of the reviews below.

[0505] Review: The food was hot and delicious, but the delivery was late.

[0506] As a result, this system allows users to easily obtain the latest review information for food delivery services, providing reference information for users when selecting a service and enabling service providers to quickly receive feedback to improve customer satisfaction.

[0507] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0508] Step 1:

[0509] The server uses web scraping technology to collect local user reviews from the Internet. The server sends an HTTP request and analyzes the HTML data received as a response to extract the review text data.

[0510] Input: URL of online review site or social media

[0511] Output: Text list of reviews

[0512] What happens: The server accesses the specified URL, retrieves the HTML page, and uses a library such as BeautifulSoup to extract the reviews and save them as text data in a list.

[0513] Step 2:

[0514] The server analyzes the collected reviews using natural language processing (NLP) techniques, such as TextBlob and other NLP tools, to extract keywords and sentiment scores from the text data.

[0515] Input: The list of reviews in text format collected in Step 1

[0516] Output: A list of keywords and sentiment scores

[0517] Specific operation: It uses TextBlob to analyze each review and calculate the sentiment score, and at the same time, extracts important keywords and stores them in the database together with the sentiment score.

[0518] Step 3:

[0519] The server uses visualization tools to display the analysis results in the form of graphs or dashboards, for example, visually representing the number of positive / negative reviews or the frequency of specific keywords.

[0520] Input: List of keywords and sentiment scores extracted in step 2

[0521] Output: Visualized data in the form of graphs and dashboards

[0522] Specific operations: Using libraries such as matplotlib and D3.js, the frequency of keywords and sentiment scores are aggregated, and data is generated to display them in the form of bar graphs, pie charts, etc.

[0523] Step 4:

[0524] Users access the system via their terminals and obtain the necessary information. Analysis results and visualized information are provided to the user via the terminals. For example, in response to a query such as "How was the food delivery service today?", the terminal displays information based on the analysis results to the user.

[0525] Input: User query (e.g., "How was the food delivery service today?")

[0526] Output: Information based on the analysis results (e.g., "The food is highly rated, but delivery is often delayed")

[0527] Specific operation: When a user inputs a query into the system from a terminal, the server searches the latest analysis results, retrieves the relevant information, sends the retrieved information to the terminal, and displays it in a form that can be visually confirmed by the user.

[0528] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0529] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions, and also combines an emotion engine that recognizes user emotions. The system is mainly composed of five main elements: a data collection means, a natural language processing means, an emotion engine, a visualization means, and an information provision means.

[0530] Data collection methods

[0531] To gather the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. The device collects user posts from online review sites and social media. In doing so, the device sends an HTTP request and receives HTML data as a response. For example, a user post such as "The snow was amazing today!" may be obtained.

[0532] Natural language processing tools

[0533] The server analyzes the collected data. It uses natural language processing (NLP) algorithms to extract keywords from the text data. For example, it extracts the keyword "snow" from a post that says "The snow was amazing."

[0534] Emotion Engine

[0535] The server applies a sentiment engine to the collected text data to recognize emotions. The sentiment engine uses an algorithm to classify positive, negative, and neutral sentiments and calculates a sentiment score for each post. For example, a post saying "The snow was great today" would be recognized as having a positive sentiment score.

[0536] Visualization means

[0537] The server then uses the analysis results to visualize the data in graphs and dashboards. The server calculates the average sentiment score for each category and creates bar graphs, pie charts, and other visualizations to visualize the results. For example, if the snow conditions receive a lot of positive feedback, that category will be displayed as highly rated.

[0538] Information provision means

[0539] Users access the system via their terminal and request the information they need. For example, if a user types, "What are the conditions at the ski resort today?", the terminal retrieves the latest analysis results from the server and provides the user with an answer such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Visualized graphs and dashboards are also displayed to the user, allowing them to visually confirm specific information.

[0540] As a concrete example, consider the case where a user visits a ski resort and posts on social media, "It was windy and cold today, but the snow conditions were perfect." The device collects these posts, and the server analyzes them using natural language processing and an emotion engine. Keywords such as "wind," "temperature," and "snow" are extracted from the post, and an emotion score for each is calculated. As a result, the emotion for "wind" is classified as negative, the emotion for "temperature" as negative, and the emotion for "snow conditions" as positive. The results of this analysis are reflected in a graph, and the next time the user checks the "ski resort conditions," this information is provided via the device, making it useful for the user's next visit.

[0541] As described above, the system of the present invention effectively collects and analyzes the impressions and opinions of local users and provides accurate, real-time information on weather conditions and ski resort conditions. By combining it with an emotion engine, more accurate analysis results based on user emotions can be obtained.

[0542] The processing flow will be explained below.

[0543] Step 1:

[0544] The device sends an HTTP request to a specified URL to collect impressions and opinions from local users. The device accesses review sites and social media pages on the Internet and retrieves HTML data.

[0545] Step 2:

[0546] The server analyzes the HTML data received from the device. The server uses an HTML parser such as BeautifulSoup to search for specific tags within the page and extract the required text information (post content). For example, Extract the text inside the tag.

[0547] Step 3:

[0548] The server runs the extracted text data through a natural language processing (NLP) algorithm, extracts keywords from the text data, and sends them to the emotion engine. Specifically, it uses TextBlob or a similar library to analyze keywords and sentence structure within the text.

[0549] Step 4:

[0550] The server uses an emotion engine to recognize emotions from the extracted text data. The emotion engine uses an algorithm to classify emotions into positive, negative, and neutral, and calculates an emotion score for each post. For example, a post saying "The snow was amazing today" would be classified as having a positive emotion score.

[0551] Step 5:

[0552] The server classifies each post into a specific category (e.g., snow conditions, temperature, wind) based on the sentiment score and keywords obtained from the sentiment engine. This context-based classification is then stored in a database. For example, the keyword "snow" with a positive sentiment score would be classified as "snow conditions."

[0553] Step 6:

[0554] The server calculates the average sentiment score based on the accumulated data. The server aggregates the sentiment scores for each category and calculates the overall average. For example, if there are multiple posts in the same category, the sentiment scores are averaged.

[0555] Step 7:

[0556] The server visualizes the analysis results, generating information to display the data in formats such as bar graphs and pie charts. A visualization tool is used to create graphs and dashboards that visually represent the calculated average sentiment scores.

[0557] Step 8:

[0558] A user accesses the system using a terminal and requests specific information. The user types a query into the terminal, such as "What are the ski resort conditions today?"

[0559] Step 9:

[0560] The device sends the user's query to the server, which searches and retrieves the latest analysis results from the database and generates information corresponding to the request.

[0561] Step 10:

[0562] The device displays the analysis results it receives from the server to the user. For example, the device provides information in text format such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Generated graphs and dashboards are also displayed, allowing the user to check the details through visual information.

[0563] Examples:

[0564] After visiting a ski resort, a user posts on social media, "Today was windy and cold, but the snow conditions were perfect." The device collects these posts, and the server analyzes them using natural language processing and an emotion engine. A positive emotion score is assigned to the "snow conditions," and negative emotion scores are assigned to the "wind" and "temperature," and the results are stored in a database. The next time the user checks the "ski resort conditions," this information is provided via the device. The user is shown specific information such as "The snow conditions were good, but the temperature and wind were not so good." This information can be used as a reference when considering their next visit.

[0565] Example 2

[0566] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0567] Currently, there is no system that can collect and analyze accurate and useful information about weather and ski resort conditions from numerous reviews and social media posts in real time and provide it to users. Furthermore, existing systems are unable to properly analyze user emotions, which often limits the usefulness of the information. There is a need to develop a system that can quickly and appropriately provide users with the information they need.

[0568] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an information collection means for collecting impressions and opinions from local users, a natural language processing means for extracting keywords and emotions from the collected information and classifying and analyzing them into specific categories, an emotion analysis means for calculating an emotion score based on the analysis results, a display means for visually displaying the data, and an information provision means for providing the analysis results including the visualized information to the user. This makes it possible to quickly collect various opinions and impressions from local users and provide accurate information on weather conditions and ski resort conditions in real time. Furthermore, analyzing users' emotions improves the usefulness and accuracy of the information.

[0569] "Information gathering means" refers to technology for obtaining impressions and opinions from local users from specific websites and social networking sites on the Internet.

[0570] "Natural language processing means" is a means for extracting keywords and emotions from collected information and classifying and analyzing them into specific categories.

[0571] The "sentiment analysis means" is an algorithm for calculating and analyzing the sentiment score (positive, negative, neutral) for the collected text data.

[0572] "Display means" refers to software or devices for visualizing analysis results in the form of graphs or dashboards.

[0573] The "information providing means" refers to a method or system for providing the analysis results, including visualized information, to a user.

[0574] "Data collection technology" refers to technology for obtaining information from the Internet, such as review sites and social media.

[0575] A "natural language processing algorithm" is an algorithm used to extract keywords and emotions from text data.

[0576] An "emotion score" is a numerical representation of the emotions in the collected text data, classified as positive, negative, or neutral.

[0577] A "graph" is a diagram such as a bar graph or pie chart that visually displays the analysis results.

[0578] A "dashboard" is an integrated visualization tool that displays multiple analysis results so that they can be viewed at a glance.

[0579] A "user request" is a user's inquiry or request for information from the system.

[0580] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions, and also combines an emotion engine that recognizes user emotions. The system is mainly composed of five main elements: information collection means, natural language processing means, emotion analysis means, display means, and information provision means.

[0581] Hardware and software used

[0582] 1. Information collection methods:

[0583] The device retrieves data from the specified URL using web scraping technology.

[0584] Software used: Python's requests library and BeautifulSoup library are used.

[0585] Example: A user posts, "The snow was absolutely amazing today!"

[0586] 2. Natural Language Processing Tools:

[0587] The server analyzes the collected data.

[0588] Software used: The spaCy library is used to extract keywords from text data.

[0589] Example: Get the keyword "snow" from the post "The snow was amazing."

[0590] 3. Emotion analysis means:

[0591] The server applies an emotion engine to the collected text data to recognize emotions.

[0592] Software used: The NLTK library is used to calculate sentiment scores.

[0593] Example: A post saying "The snow was amazing today" is recognized as having a positive sentiment score.

[0594] 4. Display means:

[0595] Based on the analysis results, the server visualizes the data in the form of graphs and dashboards.

[0596] Software used: Uses matplotlib and seaborn libraries.

[0597] Example: If a category receives a lot of positive feedback about snow conditions, it will be displayed as highly rated.

[0598] 5. Information provision method:

[0599] A user accesses the system via a terminal and requests the required information.

[0600] Example: When a user types, "What are the conditions at the ski resort today?", the device retrieves the latest analysis results from the server and provides the user with an answer such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm."

[0601] Prompt Sentence Examples

[0602] Here is an example of a prompt to input to the generative AI model:

[0603] "Please explain in detail the steps to collect user posts through web scraping."

[0604] "Please tell me the specific method for extracting keywords using a natural language processing algorithm."

[0605] "Please explain in detail how the emotion engine calculates the emotion score."

[0606] "Please explain the visualization method and generation procedure for the collected data."

[0607] "How do you generate a response to a user's information request?"

[0608] As described above, the system of the present invention executes each process in detail, from information collection to analysis, emotion recognition, visualization, and information provision, and provides useful information to users in real time. This makes it possible to provide specific and useful weather information and ski resort condition information based on the user's emotions.

[0609] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0610] Program processing flow

[0611] Step 1: Start collecting data

[0612] The device sends an HTTP request to the URL of the specified review site or social media site.

[0613] Specific operation: Uses Python's requests library to access specific review sites and social media pages.

[0614] Input: URL of review site or social media

[0615] Output: HTML data response

[0616] Step 2: Parse the response

[0617] The terminal analyzes the HTML data received as a response.

[0618] What it does: Uses the BeautifulSoup library to parse the HTML document and extract the post content.

[0619] Input: HTML data

[0620] Output: User submitted data

[0621] Step 3: Save data

[0622] The device temporarily stores the extracted posting data.

[0623] Specific operation: Save the extracted text data in a file in JSON format.

[0624] Input: User submitted data

[0625] Output: JSON file

[0626] Step 4: Loading Data

[0627] The server reads the saved JSON file.

[0628] Specific operation: Uses Python's json library to read the file and extract the text data to be analyzed.

[0629] Input: JSON file

[0630] Output: Text data

[0631] Step 5: Applying natural language processing algorithms

[0632] The server uses natural language processing (NLP) algorithms to extract keywords from the text data.

[0633] Specific behavior: Extract specific keywords using the spaCy library.

[0634] Input: Text data

[0635] Output: Extracted keywords

[0636] Step 6: Save your keywords

[0637] The server saves the extracted keywords as a new dataset.

[0638] Specific operation: Save the extracted keywords to a file in CSV format.

[0639] Input: Extracted keywords

[0640] Output: CSV file

[0641] Step 7: Applying the Emotion Engine

[0642] The server applies an emotion engine to the keywords extracted by NLP.

[0643] Specific operation: Uses the NLTK library to calculate the sentiment score (positive, negative, neutral) for each keyword.

[0644] Input: Keyword data

[0645] Output: Sentiment score

[0646] Step 8: Storing sentiment scores

[0647] The server adds the calculated sentiment scores to the dataset.

[0648] Specific behavior: Save the new emotion score in JSON format.

[0649] Input: Sentiment score

[0650] Output: JSON file of data with sentiment scores

[0651] Step 9: Loading Data

[0652] The server loads the dataset with the saved sentiment scores.

[0653] Specific operation: Read data using Python's pandas library.

[0654] Input: JSON file of data with sentiment scores

[0655] Output: Data frame to be analyzed

[0656] Step 10: Generate visualization

[0657] Based on the analysis results, the server visualizes the data in the form of graphs and dashboards.

[0658] Specific operation: Generate bar graphs and pie charts using the matplotlib and seaborn libraries.

[0659] Input: Data to be analyzed

[0660] Output: Visualized graph

[0661] Step 11: Save the visualization

[0662] The server stores the generated visualization results.

[0663] Specific operation: Save the graph image file in PNG format on the server.

[0664] Input: A visualized graph

[0665] Output: PNG file

[0666] Step 12: Receiving a User Request

[0667] The terminal receives an information request from a user.

[0668] What happens: A user enters a natural language query such as "What are the ski conditions like today?"

[0669] Input: User request

[0670] Output: Request data

[0671] Step 13: Database Query

[0672] The server retrieves the latest analysis results from the database based on the user's request.

[0673] Specific behavior: Retrieves the latest information from the database using an SQL query.

[0674] Input: User request data

[0675] Output: Latest analysis results

[0676] Step 14: Response Generation

[0677] The server generates a response to the request.

[0678] Specific behavior: Based on the acquired data, an answer is created using a natural language generation (NLG) model.

[0679] Input: Latest analysis result data

[0680] Output: The generated response

[0681] Step 15: Provide information

[0682] The terminal provides the generated response and visualization results to the user.

[0683] Specific behavior: Display the generated text and graphs on a web page or mobile app interface.

[0684] Input: Generated response, visualized graph

[0685] Output: Information provided to the user

[0686] Through these steps, the system is able to provide accurate and useful information about weather conditions and ski resort conditions based on real-time opinions and feedback from local users.

[0687] (Application example 2)

[0688] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0689] While there are existing systems that efficiently collect, analyze, and visualize the impressions and opinions of local users, they lack the functionality to provide highlights of specific events based on the emotional data associated with the event, making it difficult to provide viewers with personalized highlights in real time during and after the event.

[0690] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0691] In this invention, the server includes a data collection means for collecting impressions and opinions from local users, a natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, a visualization means for visualizing the analysis results, an information provision means for providing the visualized information to users, and a means for providing highlights of the event based on the extracted emotion data, thereby enabling personalized highlights to be provided to viewers in real time.

[0692] A "local user" is a user who provides information related to a particular location or event.

[0693] "Means for collecting impressions and opinions" refers to means for collecting impressions and opinions from users over the Internet.

[0694] "Natural language processing means" is a means of analyzing collected text data, extracting keywords and emotions, and classifying and analyzing them into specific categories.

[0695] "Visualization means" refers to a means for visually displaying the analysis results in the form of graphs or dashboards.

[0696] The "information providing means" is a means for providing visualized information to a user.

[0697] The "means for providing event highlights" is a means for providing the user with highlights and important scenes of a particular event based on the extracted emotion data.

[0698] "Data collection means" refers to means for collecting the impressions and opinions of local users, particularly using web scraping technology.

[0699] A "natural language processing algorithm" is an algorithm used to extract keywords and emotions from text data.

[0700] An "emotion engine" is an algorithm that recognizes and classifies emotions from collected text data.

[0701] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides event highlights. It mainly consists of a data collection means, a natural language processing means, an emotion engine, a visualization means, an information provision means, and a means for providing event highlights.

[0702] Data collection methods

[0703] The server retrieves data from online review sites and social media sites to gather impressions and opinions from local users. Specifically, it uses HTTP requests to gather the necessary information from specified URLs using web scraping technology. For example, it retrieves user posts such as "I saw a lot of great goals today!"

[0704] Natural language processing tools

[0705] The server analyzes the collected data. Natural language processing algorithms are used for this analysis. Keywords and emotions are extracted from the text data, and they are classified and analyzed into specific categories. For example, the keyword "goal" is extracted from a post titled "Great goal," and the emotion score is determined to be positive.

[0706] Emotion Engine

[0707] The server applies an emotion engine to the collected text data to recognize emotions. Specifically, it uses an algorithm that classifies emotions into positive, negative, and neutral, and calculates an emotion score for each post. For example, a post saying, "I saw a lot of great goals today!" would be recognized as having a positive emotion score.

[0708] Visualization means

[0709] The server visualizes the analysis results. The analyzed data is displayed in graphs and dashboards. For example, the average sentiment score for each category is visualized in a bar graph or pie chart. For example, if a goal receives many positive comments, that category is displayed as highly rated.

[0710] Information provision means

[0711] Users can access the system via their device and request the information they need. For example, if a user types, "I want to see the highlights of today's game," the device will retrieve the latest analysis results from the server and provide the user with "highlights of goal scenes that received a lot of positive feedback." In addition, visualized graphs and dashboards are also displayed to the user, allowing them to visually confirm specific information.

[0712] A way to provide highlights of the event

[0713] The server then provides users with highlights and important scenes from a specific event based on the extracted emotion data. For example, it provides users with personalized highlight videos based on goal scenes that garnered very positive feedback or scenes that generated a large amount of negative feedback.

[0714] Specific examples

[0715] For example, if a user posts on social media during a sporting event, "I saw a lot of great goals today!", this post will be recorded as a positive emotion. If another user comments, "The referee's decisions were terrible," this will be classified as a negative emotion. The data collected and analyzed in this way will be used to create highlight videos in real time.

[0716] Example prompts to input to the generative AI model

[0717] Analyze the post "I saw a lot of great goals today!" and output a positive sentiment score.

[0718] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0719] Step 1:

[0720] Data collection

[0721] The device retrieves data from online review sites and social networking sites to collect impressions and opinions from local users. This process uses an HTTP request to retrieve the HTML data of a webpage from a specified URL, and then analyzes it to extract the required text information (impressions and opinions). The input is the URL and HTTP request, and the output is the extracted text data.

[0722] Step 2:

[0723] Natural Language Processing

[0724] The server analyzes the collected text data. In this step, natural language processing algorithms are used to extract keywords and sentiment from the text data and classify each into a specific category. The input is text data, and the output is analyzed data containing keywords and sentiment scores. Specifically, a text analysis library is used to extract nouns and adjectives and perform sentiment analysis.

[0725] Step 3:

[0726] Emotion engine applied

[0727] The server applies an emotion engine based on the analyzed data to calculate an emotion score for each post. The emotion score is classified as positive, negative, or neutral and is output. Specifically, the results of natural language processing are input into an emotion recognition algorithm to score each emotion.

[0728] Step 4:

[0729] Data Visualization

[0730] The server visualizes the sentiment scores and keyword data. This process uses a visualization tool to display the data in graph or dashboard format. The input is the sentiment scores and keyword data, and the output is a visually easy-to-understand graph or dashboard. Specifically, graph drawing libraries such as matplotlib and Plotly are used.

[0731] Step 5:

[0732] Providing information

[0733] Users access the system via a terminal and request the information they need. The server retrieves the latest analysis results and provides real-time event information and highlights to the user. The input is the user request, and the output is the analysis results and visualized data. Specifically, the system searches for appropriate information in response to the user request and displays it through a GUI.

[0734] Step 6:

[0735] Event highlights provided

[0736] The server provides users with highlights and important scenes from specific events based on the extracted emotion data. This process prioritizes scenes with high emotion scores and edits those video clips to create a highlight video. The inputs are emotion scores and event data, and the output is a highlight video. Specifically, video editing software is used to automatically edit video clips based on the emotion scores.

[0737] Example prompts to input to the generative AI model

[0738] Analyze the post "I saw a lot of great goals today!" and output a positive sentiment score.

[0739] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0740] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0741] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0742] [Third embodiment]

[0743] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0744] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0745] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0746] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0747] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0748] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0749] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0750] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0751] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0752] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0753] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0754] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0755] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions. The system is mainly composed of four main elements: data collection means, natural language processing means, visualization means, and information provision means.

[0756] Data collection methods

[0757] To gather the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. Specifically, the device collects user posts from online review sites and social networking services (SNS). In this case, the device sends an HTTP request and receives HTML data as a response. For example, if a local user's review says, "The snow was amazing today!", this text data is obtained.

[0758] Natural language processing tools

[0759] The server analyzes the collected data. It uses natural language processing (NLP) algorithms to extract keywords and sentiment from the collected text data and classify them into specific categories, such as "snow sentiment (positive)" and "temperature sentiment (negative)." TextBlob and other NLP tools are used to calculate a sentiment score for each post, which is then stored in a database along with the keywords.

[0760] Visualization means

[0761] The server then visualizes the data in graphs or dashboards based on the analysis results. For example, if there are many positive comments about snow conditions, the server calculates the average sentiment score for that category and displays it in the form of a bar graph or pie chart. This allows the device to provide information to users in a visually easy-to-understand format.

[0762] Information provision means

[0763] Users access the system via their terminals to obtain the information they need. For example, if a user enters a query such as "What are the conditions at the ski resort today?", the terminal retrieves the latest analysis results from the server and provides the user with an answer such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Visualized graphs and dashboards are also displayed to the user, allowing them to visually check more detailed information.

[0764] Specific examples

[0765] Below is a specific example. When a user visits a ski resort, they post on social media that "the snow was deep today and it was easy to ski." The device collects these posts, and the server uses natural language processing to extract keywords related to "snow" and "positive" emotions. As a result, the server records the "snow conditions are very good" in the database and reflects this in a graph using visualization tools. The next time the user checks the "ski resort conditions," this information is displayed on the device, and they can use it as a reference for when to visit next.

[0766] As described above, the system of the present invention effectively collects and analyzes the impressions and opinions of local users and provides accurate, real-time information on weather conditions and ski resort conditions.

[0767] The processing flow will be explained below.

[0768] Step 1:

[0769] The device collects local user impressions and opinions from a specified URL. The device sends an HTTP request and receives HTML data as a response. For example, when collecting posts from a social networking site or review site, the device accesses the required URL and downloads the data.

[0770] Step 2:

[0771] The server analyzes the HTML data it has retrieved. Using an HTML parser such as BeautifulSoup, the server extracts the necessary text information (post content). Specifically, it searches for specific HTML tags and extracts the user posts contained therein in text format.

[0772] Step 3:

[0773] The server runs the extracted text data through a natural language processing (NLP) algorithm. Using a library such as TextBlob, the server extracts keywords and sentiment scores from each post. For example, from a post saying "The snow was amazing," the server extracts the keyword "snow" and a "positive" sentiment score.

[0774] Step 4:

[0775] The server classifies each post into a specific category (e.g., snow conditions, temperature, wind speed) based on the extracted keywords and sentiment score. The server stores these results in a database. For example, if there are many posts about "snow" and the sentiment score is positive, it will be recorded as "good snow conditions."

[0776] Step 5:

[0777] The server calculates the average sentiment score for each category based on the accumulated data. Using the calculated scores, the server visualizes the data in visual formats such as bar graphs and pie charts. The results are created as image files or interactive dashboards.

[0778] Step 6:

[0779] A user accesses the system using a terminal and requests the required information. For example, the user types a query such as "What are the ski conditions like today?"

[0780] Step 7:

[0781] The device sends a query to the server to obtain the latest analysis results, and the server searches for the relevant information from the stored data and provides it to the device.

[0782] Step 8:

[0783] Based on the calculations and visualizations obtained by the device, the device displays specific information to the user, such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm," and also displays graphs and dashboards when available.

[0784] This allows users to get accurate, real-time information about local weather conditions and ski resort conditions.

[0785] Example 1

[0786] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0787] There is a need to efficiently collect impressions and opinions from local users, accurately analyze them, and provide information in real time. However, conventional systems have limited the scope of data collection and have issues with analysis accuracy. Furthermore, they lack sufficient visualization methods to make the collected data easier to understand visually, and methods for effectively providing information to users. The present invention aims to solve these issues and provide more accurate and convenient information.

[0788] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0789] In this invention, the server includes data collection means for collecting impressions and opinions from local users, natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, visualization means for visually displaying the analysis results, information provision means for providing the visualized information to the user, preprocessing means for preprocessing the data collected by the terminal, and process flow handling means for controlling the flow of program processing. This makes it possible to comprehensively collect a variety of opinions from local users, analyze and visualize them with high accuracy, and effectively provide information to the user.

[0790] "Data collection methods" refers to the technology and equipment used to collect impressions and opinions of local users from the Internet. Specifically, this includes web scraping technology.

[0791] "Natural language processing means" refers to the technology and algorithms used to extract keywords and emotions from collected text data and classify and analyze them into specific categories.

[0792] "Visualization means" refers to techniques and tools for visually displaying analysis results, including means for providing data in the form of graphs, dashboards, etc.

[0793] "Information provision means" refers to the technology and interface for providing visualized information to users.

[0794] "Preprocessing means" refers to techniques such as data cleaning and tokenization to convert data collected by the terminal into an analyzable format.

[0795] "Processing flow handling means" refers to the techniques and methods for controlling and regulating the processing flow of a program from data collection to information provision.

[0796] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions. This system consists of six main components: data collection means, natural language processing means, visualization means, information provision means, preprocessing means, and processing flow handling means.

[0797] Data collection methods

[0798] To collect the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. Specifically, data is collected from social media and review sites using the Python library Beautiful Soup and Selenium. The device sends an HTTP request to receive the HTML data of the webpage, which is then analyzed to extract text data. For example, if a user posts on social media, "The snow was amazing today!", that text data is collected.

[0799] Pretreatment means

[0800] The device preprocesses the text data it receives to make it analyzable. Specifically, it removes unnecessary tags and special characters, tokenizes the text, and splits it into words. This process improves the quality of the data and prepares it for accurate analysis.

[0801] Natural language processing tools

[0802] The server analyzes the collected text data. Specifically, it uses Python's natural language processing libraries, TextBlob and NLTK, to extract keywords and sentiment from the text. The server then uses these keywords and sentiment scores to classify the data into specific categories. For example, the server extracts the keyword "snow" and positive sentiment from a post that says, "The snow was amazing today!" This information is then stored in a database.

[0803] Visualization means

[0804] The server visually displays the analysis results. Using Python visualization libraries Matplotlib and Plotly, sentiment scores and keyword frequency are displayed in graphs and dashboards. This allows users to view information in a visually easy-to-understand format. For example, if there are many positive comments about snow, the data can be displayed in a bar graph or pie chart.

[0805] Information provision means

[0806] Users access the system via their terminals to obtain the necessary information. When a user enters a query into their terminal, such as "What are the conditions at the ski resort today?", the terminal sends the request to the server. The server returns the latest analysis results, and the user receives information such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm."

[0807] Specific examples

[0808] For example, when a user visits a ski resort, they post on social media that "the snow was deep today and easy to ski on." The device collects these posts, and the server uses natural language processing to extract keywords and positive emotions related to "snow." As a result, the information that "the snow conditions are very good" is recorded in the database. This information is reflected in a graph using visualization tools, and the next time the user checks the "ski resort conditions," they can visually confirm this information on their device and use it as a reference for when to visit next.

[0809] Example prompt sentence:

[0810] "How are the ski conditions today?"

[0811] Please tell me the snow conditions at the ski resort.

[0812] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0813] Step 1:

[0814] The device sends an HTTP request to a specified URL to collect impressions and opinions from local users. The input is the URL to be collected, and the output is the HTML data of the web page. Specifically, the HTTP request is made using the requests library.

[0815] Step 2:

[0816] The Beautiful Soup library is used to parse the HTML data received by the device. The input is the HTML data obtained in step 1, and the output is text data containing impressions and opinions. Specifically, Beautiful Soup parses the HTML data and extracts text data from the specified tags and classes.

[0817] Step 3:

[0818] The text data extracted by the terminal is preprocessed and converted into an analyzable format. The input is the text data extracted in step 2, and the output is the cleaned text data. Specific operations include removing special characters and trimming spaces.

[0819] Step 4:

[0820] The terminal tokenizes the preprocessed data and splits it into words. The input is the cleaned text data obtained in step 3, and the output is the tokenized text data. Specifically, tokenization is performed using the NLTK library.

[0821] Step 5:

[0822] The server performs natural language processing to extract keywords and sentiment from the tokenized text data. The input is the tokenized text data obtained in step 4, and the output is keywords and sentiment scores. Specifically, sentiment analysis is performed using the TextBlob library to extract keywords.

[0823] Step 6:

[0824] The server saves the extracted keywords and sentiment scores in a database. The input is the keywords and sentiment scores obtained in step 5, and the output is the results saved in the database. Specifically, it writes the results to the database using SQLAlchemy.

[0825] Step 7:

[0826] The server visualizes the data based on the analysis results stored in the database. The input is the analysis results stored in the database, and the output is visual data in the form of graphs or dashboards. Specifically, the data is displayed visually using Matplotlib or Plotly.

[0827] Step 8:

[0828] A user accesses the system via a terminal and enters a query. The input is the query entered by the user, and the output is an answer based on the analysis results. Specifically, the user's query is sent to the server, which retrieves the latest analysis results from the database and returns them.

[0829] Step 9:

[0830] The terminal provides the user with the analysis results received from the server. The input is the analysis results returned from the server, and the output is the information provided to the user. Specifically, the results are formatted and displayed in a user-friendly format.

[0831] The above processing steps realize a system that efficiently collects opinions and impressions from local users, analyzes them with high accuracy, and provides information in real time.

[0832] (Application example 1)

[0833] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0834] Modern food delivery services require a method for efficiently collecting and analyzing user feedback on the quality of food and delivery in real time. Conventional systems often collect and analyze reviews manually, making it difficult to provide accurate and timely information. This makes it difficult for users to select a service based on the most up-to-date information, and it is also difficult for service providers to properly understand customer satisfaction. Therefore, there is a need to develop a system that automatically collects and analyzes reviews of food delivery services and provides information to users in an easy-to-understand manner.

[0835] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0836] In this invention, the server includes a data collection means for collecting opinions from local users, a natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, a visualization means for visualizing the analysis results, and an information provision means for providing the visualized information to users. This allows users to easily obtain the latest review information by combining the means for collecting and analyzing reviews about food and delivery with the means for generating information about food and delivery services based on the analyzed reviews.

[0837] "Data collection means" refers to means for collecting opinions from local users.

[0838] "Natural language processing means" is a means of extracting keywords and emotions from collected data and classifying and analyzing them into specific categories.

[0839] "Visualization means" refers to a means for displaying analysis results in the form of graphs or dashboards.

[0840] The "information providing means" is a means for providing visualized information to a user.

[0841] "Reviews" are impressions and opinions written by users about the quality of food and delivery of food delivery services.

[0842] "Analysis" is the act of processing collected data and extracting meaningful information.

[0843] "Food" refers to food and drink delivered by a food delivery service.

[0844] "Delivery" refers to the act of delivering ordered food to a designated location in a food delivery service.

[0845] "Services" refers to the overall assistance and support provided in food delivery.

[0846] A "natural language processing algorithm" is an algorithm for extracting linguistic features from text data.

[0847] "Web scraping" is a technique for automatically collecting specific information from websites.

[0848] The system of this invention collects and analyzes user reviews of food delivery services and provides real-time information about the quality of food and delivery. The system is mainly composed of four main components: data collection means, natural language processing means, visualization means, and information provision means.

[0849] Data collection methods

[0850] The server uses web scraping technology to collect local user reviews from the Internet. The server sends an HTTP request and receives HTML data as a response. For example, a user might post about a food delivery service, saying, "The food was hot and delicious, but the delivery was late." The server collects this post.

[0851] Natural language processing tools

[0852] The server analyzes the collected reviews. It uses natural language processing algorithms to extract keywords and sentiment from the text data. Specifically, it uses TextBlob and other NLP tools to calculate a sentiment score for each post and store it in a database along with keywords. For example, reviews are categorized as "Cooking (positive)" or "Delivery (negative)."

[0853] Visualization means

[0854] The server visualizes the data based on the analysis results. The analyzed data is displayed in graphs and dashboards, providing information in a visually easy-to-understand format for users. For example, it allows users to visually see at a glance which dishes have many positive reviews and which delivery items have many negative reviews.

[0855] Information provision means

[0856] Users access the system via their devices to obtain the information they need. For example, if a user enters a query such as "How was the food delivery service today?", the server retrieves the latest analysis results and provides detailed information via the device, such as "The food was highly rated, but the delivery was a little late." Graphs and dashboards are also displayed to help users gain a deeper understanding.

[0857] Specific examples

[0858] Suppose a user posts on social media, "How was today's dinner delivery service?" and the post states, "The food was hot and delicious, but the delivery was late." The server collects these posts and uses natural language processing to extract emotions related to "food (positive)" and "delivery (negative)." The analysis results are then displayed in a graph using visualization tools, which are then displayed to the user via their device.

[0859] Example prompts to input to a generative AI model:

[0860] Analyze the sentiment of the reviews below.

[0861] Review: The food was hot and delicious, but the delivery was late.

[0862] As a result, this system allows users to easily obtain the latest review information for food delivery services, providing reference information for users when selecting a service and enabling service providers to quickly receive feedback to improve customer satisfaction.

[0863] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0864] Step 1:

[0865] The server uses web scraping technology to collect local user reviews from the Internet. The server sends an HTTP request and analyzes the HTML data received as a response to extract the review text data.

[0866] Input: URL of online review site or social media

[0867] Output: Text list of reviews

[0868] What happens: The server accesses the specified URL, retrieves the HTML page, and uses a library such as BeautifulSoup to extract the reviews and save them as text data in a list.

[0869] Step 2:

[0870] The server analyzes the collected reviews using natural language processing (NLP) techniques, such as TextBlob and other NLP tools, to extract keywords and sentiment scores from the text data.

[0871] Input: The list of reviews in text format collected in Step 1

[0872] Output: A list of keywords and sentiment scores

[0873] Specific operation: It uses TextBlob to analyze each review and calculate the sentiment score, and at the same time, extracts important keywords and stores them in the database together with the sentiment score.

[0874] Step 3:

[0875] The server uses visualization tools to display the analysis results in the form of graphs or dashboards, for example, visually representing the number of positive / negative reviews or the frequency of specific keywords.

[0876] Input: List of keywords and sentiment scores extracted in step 2

[0877] Output: Visualized data in the form of graphs and dashboards

[0878] Specific operations: Using libraries such as matplotlib and D3.js, the frequency of keywords and sentiment scores are aggregated, and data is generated to display them in the form of bar graphs, pie charts, etc.

[0879] Step 4:

[0880] Users access the system via their terminals and obtain the necessary information. Analysis results and visualized information are provided to the user via the terminals. For example, in response to a query such as "How was the food delivery service today?", the terminal displays information based on the analysis results to the user.

[0881] Input: User query (e.g., "How was the food delivery service today?")

[0882] Output: Information based on the analysis results (e.g., "The food is highly rated, but delivery is often delayed")

[0883] Specific operation: When a user inputs a query into the system from a terminal, the server searches the latest analysis results, retrieves the relevant information, sends the retrieved information to the terminal, and displays it in a form that can be visually confirmed by the user.

[0884] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0885] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions, and also combines an emotion engine that recognizes user emotions. The system is mainly composed of five main elements: a data collection means, a natural language processing means, an emotion engine, a visualization means, and an information provision means.

[0886] Data collection methods

[0887] To gather the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. The device collects user posts from online review sites and social media. In doing so, the device sends an HTTP request and receives HTML data as a response. For example, a user post such as "The snow was amazing today!" may be obtained.

[0888] Natural language processing tools

[0889] The server analyzes the collected data. It uses natural language processing (NLP) algorithms to extract keywords from the text data. For example, it extracts the keyword "snow" from a post that says "The snow was amazing."

[0890] Emotion Engine

[0891] The server applies a sentiment engine to the collected text data to recognize emotions. The sentiment engine uses an algorithm to classify positive, negative, and neutral sentiments and calculates a sentiment score for each post. For example, a post saying "The snow was great today" would be recognized as having a positive sentiment score.

[0892] Visualization means

[0893] The server then uses the analysis results to visualize the data in graphs and dashboards. The server calculates the average sentiment score for each category and creates bar graphs, pie charts, and other visualizations to visualize the results. For example, if the snow conditions receive a lot of positive feedback, that category will be displayed as highly rated.

[0894] Information provision means

[0895] Users access the system via their terminal and request the information they need. For example, if a user types, "What are the conditions at the ski resort today?", the terminal retrieves the latest analysis results from the server and provides the user with an answer such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Visualized graphs and dashboards are also displayed to the user, allowing them to visually confirm specific information.

[0896] As a concrete example, consider the case where a user visits a ski resort and posts on social media, "It was windy and cold today, but the snow conditions were perfect." The device collects these posts, and the server analyzes them using natural language processing and an emotion engine. Keywords such as "wind," "temperature," and "snow" are extracted from the post, and an emotion score for each is calculated. As a result, the emotion for "wind" is classified as negative, the emotion for "temperature" as negative, and the emotion for "snow conditions" as positive. The results of this analysis are reflected in a graph, and the next time the user checks the "ski resort conditions," this information is provided via the device, making it useful for the user's next visit.

[0897] As described above, the system of the present invention effectively collects and analyzes the impressions and opinions of local users and provides accurate, real-time information on weather conditions and ski resort conditions. By combining it with an emotion engine, more accurate analysis results based on user emotions can be obtained.

[0898] The processing flow will be explained below.

[0899] Step 1:

[0900] The device sends an HTTP request to a specified URL to collect impressions and opinions from local users. The device accesses review sites and social media pages on the Internet and retrieves HTML data.

[0901] Step 2:

[0902] The server analyzes the HTML data received from the device. The server uses an HTML parser such as BeautifulSoup to search for specific tags within the page and extract the required text information (post content). For example, Extract the text inside the tag.

[0903] Step 3:

[0904] The server runs the extracted text data through a natural language processing (NLP) algorithm, extracts keywords from the text data, and sends them to the emotion engine. Specifically, it uses TextBlob or a similar library to analyze keywords and sentence structure within the text.

[0905] Step 4:

[0906] The server uses an emotion engine to recognize emotions from the extracted text data. The emotion engine uses an algorithm to classify emotions into positive, negative, and neutral, and calculates an emotion score for each post. For example, a post saying "The snow was amazing today" would be classified as having a positive emotion score.

[0907] Step 5:

[0908] The server classifies each post into a specific category (e.g., snow conditions, temperature, wind) based on the sentiment score and keywords obtained from the sentiment engine. This context-based classification is then stored in a database. For example, the keyword "snow" with a positive sentiment score would be classified as "snow conditions."

[0909] Step 6:

[0910] The server calculates the average sentiment score based on the accumulated data. The server aggregates the sentiment scores for each category and calculates the overall average. For example, if there are multiple posts in the same category, the sentiment scores are averaged.

[0911] Step 7:

[0912] The server visualizes the analysis results, generating information to display the data in formats such as bar graphs and pie charts. A visualization tool is used to create graphs and dashboards that visually represent the calculated average sentiment scores.

[0913] Step 8:

[0914] A user accesses the system using a terminal and requests specific information. The user types a query into the terminal, such as "What are the ski resort conditions today?"

[0915] Step 9:

[0916] The device sends the user's query to the server, which searches and retrieves the latest analysis results from the database and generates information corresponding to the request.

[0917] Step 10:

[0918] The device displays the analysis results it receives from the server to the user. For example, the device provides information in text format such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Generated graphs and dashboards are also displayed, allowing the user to check the details through visual information.

[0919] Examples:

[0920] After visiting a ski resort, a user posts on social media, "Today was windy and cold, but the snow conditions were perfect." The device collects these posts, and the server analyzes them using natural language processing and an emotion engine. A positive emotion score is assigned to the "snow conditions," and negative emotion scores are assigned to the "wind" and "temperature," and the results are stored in a database. The next time the user checks the "ski resort conditions," this information is provided via the device. The user is shown specific information such as "The snow conditions were good, but the temperature and wind were not so good." This information can be used as a reference when considering their next visit.

[0921] Example 2

[0922] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0923] Currently, there is no system that can collect and analyze accurate and useful information about weather and ski resort conditions from numerous reviews and social media posts in real time and provide it to users. Furthermore, existing systems are unable to properly analyze user emotions, which often limits the usefulness of the information. There is a need to develop a system that can quickly and appropriately provide users with the information they need.

[0924] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an information collection means for collecting impressions and opinions from local users, a natural language processing means for extracting keywords and emotions from the collected information and classifying and analyzing them into specific categories, an emotion analysis means for calculating an emotion score based on the analysis results, a display means for visually displaying the data, and an information provision means for providing the analysis results including the visualized information to the user. This makes it possible to quickly collect various opinions and impressions from local users and provide accurate information on weather conditions and ski resort conditions in real time. Furthermore, analyzing users' emotions improves the usefulness and accuracy of the information.

[0925] "Information gathering means" refers to technology for obtaining impressions and opinions from local users from specific websites and social networking sites on the Internet.

[0926] "Natural language processing means" is a means for extracting keywords and emotions from collected information and classifying and analyzing them into specific categories.

[0927] The "sentiment analysis means" is an algorithm for calculating and analyzing the sentiment score (positive, negative, neutral) for the collected text data.

[0928] "Display means" refers to software or devices for visualizing analysis results in the form of graphs or dashboards.

[0929] The "information providing means" refers to a method or system for providing the analysis results, including visualized information, to a user.

[0930] "Data collection technology" refers to technology for obtaining information from the Internet, such as review sites and social media.

[0931] A "natural language processing algorithm" is an algorithm used to extract keywords and emotions from text data.

[0932] An "emotion score" is a numerical representation of the emotions in the collected text data, classified as positive, negative, or neutral.

[0933] A "graph" is a diagram such as a bar graph or pie chart that visually displays the analysis results.

[0934] A "dashboard" is an integrated visualization tool that displays multiple analysis results so that they can be viewed at a glance.

[0935] A "user request" is a user's inquiry or request for information from the system.

[0936] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions, and also combines an emotion engine that recognizes user emotions. The system is mainly composed of five main elements: information collection means, natural language processing means, emotion analysis means, display means, and information provision means.

[0937] Hardware and software used

[0938] 1. Information collection methods:

[0939] The device retrieves data from the specified URL using web scraping technology.

[0940] Software used: Python's requests library and BeautifulSoup library are used.

[0941] Example: A user posts, "The snow was absolutely amazing today!"

[0942] 2. Natural Language Processing Tools:

[0943] The server analyzes the collected data.

[0944] Software used: The spaCy library is used to extract keywords from text data.

[0945] Example: Get the keyword "snow" from the post "The snow was amazing."

[0946] 3. Emotion analysis means:

[0947] The server applies an emotion engine to the collected text data to recognize emotions.

[0948] Software used: The NLTK library is used to calculate sentiment scores.

[0949] Example: A post saying "The snow was amazing today" is recognized as having a positive sentiment score.

[0950] 4. Display means:

[0951] Based on the analysis results, the server visualizes the data in the form of graphs and dashboards.

[0952] Software used: Uses matplotlib and seaborn libraries.

[0953] Example: If a category receives a lot of positive feedback about snow conditions, it will be displayed as highly rated.

[0954] 5. Information provision method:

[0955] A user accesses the system via a terminal and requests the required information.

[0956] Example: When a user types, "What are the conditions at the ski resort today?", the device retrieves the latest analysis results from the server and provides the user with an answer such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm."

[0957] Prompt Sentence Examples

[0958] Here is an example of a prompt to input to the generative AI model:

[0959] "Please explain in detail the steps to collect user posts through web scraping."

[0960] "Please tell me the specific method for extracting keywords using a natural language processing algorithm."

[0961] "Please explain in detail how the emotion engine calculates the emotion score."

[0962] "Please explain the visualization method and generation procedure for the collected data."

[0963] "How do you generate a response to a user's information request?"

[0964] As described above, the system of the present invention executes each process in detail, from information collection to analysis, emotion recognition, visualization, and information provision, and provides useful information to users in real time. This makes it possible to provide specific and useful weather information and ski resort condition information based on the user's emotions.

[0965] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0966] Program processing flow

[0967] Step 1: Start collecting data

[0968] The device sends an HTTP request to the URL of the specified review site or social media site.

[0969] Specific operation: Uses Python's requests library to access specific review sites and social media pages.

[0970] Input: URL of review site or social media

[0971] Output: HTML data response

[0972] Step 2: Parse the response

[0973] The terminal analyzes the HTML data received as a response.

[0974] What it does: Uses the BeautifulSoup library to parse the HTML document and extract the post content.

[0975] Input: HTML data

[0976] Output: User submitted data

[0977] Step 3: Save data

[0978] The device temporarily stores the extracted posting data.

[0979] Specific operation: Save the extracted text data in a file in JSON format.

[0980] Input: User submitted data

[0981] Output: JSON file

[0982] Step 4: Loading Data

[0983] The server reads the saved JSON file.

[0984] Specific operation: Uses Python's json library to read the file and extract the text data to be analyzed.

[0985] Input: JSON file

[0986] Output: Text data

[0987] Step 5: Applying natural language processing algorithms

[0988] The server uses natural language processing (NLP) algorithms to extract keywords from the text data.

[0989] Specific behavior: Extract specific keywords using the spaCy library.

[0990] Input: Text data

[0991] Output: Extracted keywords

[0992] Step 6: Save your keywords

[0993] The server saves the extracted keywords as a new dataset.

[0994] Specific operation: Save the extracted keywords to a file in CSV format.

[0995] Input: Extracted keywords

[0996] Output: CSV file

[0997] Step 7: Applying the Emotion Engine

[0998] The server applies an emotion engine to the keywords extracted by NLP.

[0999] Specific operation: Uses the NLTK library to calculate the sentiment score (positive, negative, neutral) for each keyword.

[1000] Input: Keyword data

[1001] Output: Sentiment score

[1002] Step 8: Storing sentiment scores

[1003] The server adds the calculated sentiment scores to the dataset.

[1004] Specific behavior: Save the new emotion score in JSON format.

[1005] Input: Sentiment score

[1006] Output: JSON file of data with sentiment scores

[1007] Step 9: Loading Data

[1008] The server loads the dataset with the saved sentiment scores.

[1009] Specific operation: Read data using Python's pandas library.

[1010] Input: JSON file of data with sentiment scores

[1011] Output: Data frame to be analyzed

[1012] Step 10: Generate visualization

[1013] Based on the analysis results, the server visualizes the data in the form of graphs and dashboards.

[1014] Specific operation: Generate bar graphs and pie charts using the matplotlib and seaborn libraries.

[1015] Input: Data to be analyzed

[1016] Output: Visualized graph

[1017] Step 11: Save the visualization

[1018] The server stores the generated visualization results.

[1019] Specific operation: Save the graph image file in PNG format on the server.

[1020] Input: A visualized graph

[1021] Output: PNG file

[1022] Step 12: Receiving a User Request

[1023] The terminal receives an information request from a user.

[1024] What happens: A user enters a natural language query such as "What are the ski conditions like today?"

[1025] Input: User request

[1026] Output: Request data

[1027] Step 13: Database Query

[1028] The server retrieves the latest analysis results from the database based on the user's request.

[1029] Specific behavior: Retrieves the latest information from the database using an SQL query.

[1030] Input: User request data

[1031] Output: Latest analysis results

[1032] Step 14: Response Generation

[1033] The server generates a response to the request.

[1034] Specific behavior: Based on the acquired data, an answer is created using a natural language generation (NLG) model.

[1035] Input: Latest analysis result data

[1036] Output: The generated response

[1037] Step 15: Provide information

[1038] The terminal provides the generated response and visualization results to the user.

[1039] Specific behavior: Display the generated text and graphs on a web page or mobile app interface.

[1040] Input: Generated response, visualized graph

[1041] Output: Information provided to the user

[1042] Through these steps, the system is able to provide accurate and useful information about weather conditions and ski resort conditions based on real-time opinions and feedback from local users.

[1043] (Application example 2)

[1044] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1045] While there are existing systems that efficiently collect, analyze, and visualize the impressions and opinions of local users, they lack the functionality to provide highlights of specific events based on the emotional data associated with the event, making it difficult to provide viewers with personalized highlights in real time during and after the event.

[1046] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1047] In this invention, the server includes a data collection means for collecting impressions and opinions from local users, a natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, a visualization means for visualizing the analysis results, an information provision means for providing the visualized information to users, and a means for providing highlights of the event based on the extracted emotion data, thereby enabling personalized highlights to be provided to viewers in real time.

[1048] A "local user" is a user who provides information related to a particular location or event.

[1049] "Means for collecting impressions and opinions" refers to means for collecting impressions and opinions from users over the Internet.

[1050] "Natural language processing means" is a means of analyzing collected text data, extracting keywords and emotions, and classifying and analyzing them into specific categories.

[1051] "Visualization means" refers to a means for visually displaying the analysis results in the form of graphs or dashboards.

[1052] The "information providing means" is a means for providing visualized information to a user.

[1053] The "means for providing event highlights" is a means for providing the user with highlights and important scenes of a particular event based on the extracted emotion data.

[1054] "Data collection means" refers to means for collecting the impressions and opinions of local users, particularly using web scraping technology.

[1055] A "natural language processing algorithm" is an algorithm used to extract keywords and emotions from text data.

[1056] An "emotion engine" is an algorithm that recognizes and classifies emotions from collected text data.

[1057] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides event highlights. It mainly consists of a data collection means, a natural language processing means, an emotion engine, a visualization means, an information provision means, and a means for providing event highlights.

[1058] Data collection methods

[1059] The server retrieves data from online review sites and social media sites to gather impressions and opinions from local users. Specifically, it uses HTTP requests to gather the necessary information from specified URLs using web scraping technology. For example, it retrieves user posts such as "I saw a lot of great goals today!"

[1060] Natural language processing tools

[1061] The server analyzes the collected data. Natural language processing algorithms are used for this analysis. Keywords and emotions are extracted from the text data, and they are classified and analyzed into specific categories. For example, the keyword "goal" is extracted from a post titled "Great goal," and the emotion score is determined to be positive.

[1062] Emotion Engine

[1063] The server applies an emotion engine to the collected text data to recognize emotions. Specifically, it uses an algorithm that classifies emotions into positive, negative, and neutral, and calculates an emotion score for each post. For example, a post saying, "I saw a lot of great goals today!" would be recognized as having a positive emotion score.

[1064] Visualization means

[1065] The server visualizes the analysis results. The analyzed data is displayed in graphs and dashboards. For example, the average sentiment score for each category is visualized in a bar graph or pie chart. For example, if a goal receives many positive comments, that category is displayed as highly rated.

[1066] Information provision means

[1067] Users can access the system via their device and request the information they need. For example, if a user types, "I want to see the highlights of today's game," the device will retrieve the latest analysis results from the server and provide the user with "highlights of goal scenes that received a lot of positive feedback." In addition, visualized graphs and dashboards are also displayed to the user, allowing them to visually confirm specific information.

[1068] A way to provide highlights of the event

[1069] The server then provides users with highlights and important scenes from a specific event based on the extracted emotion data. For example, it provides users with personalized highlight videos based on goal scenes that garnered very positive feedback or scenes that generated a large amount of negative feedback.

[1070] Specific examples

[1071] For example, if a user posts on social media during a sporting event, "I saw a lot of great goals today!", this post will be recorded as a positive emotion. If another user comments, "The referee's decisions were terrible," this will be classified as a negative emotion. The data collected and analyzed in this way will be used to create highlight videos in real time.

[1072] Example prompts to input to the generative AI model

[1073] Analyze the post "I saw a lot of great goals today!" and output a positive sentiment score.

[1074] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1075] Step 1:

[1076] Data collection

[1077] The device retrieves data from online review sites and social networking sites to collect impressions and opinions from local users. This process uses an HTTP request to retrieve the HTML data of a webpage from a specified URL, and then analyzes it to extract the required text information (impressions and opinions). The input is the URL and HTTP request, and the output is the extracted text data.

[1078] Step 2:

[1079] Natural Language Processing

[1080] The server analyzes the collected text data. In this step, natural language processing algorithms are used to extract keywords and sentiment from the text data and classify each into a specific category. The input is text data, and the output is analyzed data containing keywords and sentiment scores. Specifically, a text analysis library is used to extract nouns and adjectives and perform sentiment analysis.

[1081] Step 3:

[1082] Emotion engine applied

[1083] The server applies an emotion engine based on the analyzed data to calculate an emotion score for each post. The emotion score is classified as positive, negative, or neutral and is output. Specifically, the results of natural language processing are input into an emotion recognition algorithm to score each emotion.

[1084] Step 4:

[1085] Data Visualization

[1086] The server visualizes the sentiment scores and keyword data. This process uses a visualization tool to display the data in graph or dashboard format. The input is the sentiment scores and keyword data, and the output is a visually easy-to-understand graph or dashboard. Specifically, graph drawing libraries such as matplotlib and Plotly are used.

[1087] Step 5:

[1088] Providing information

[1089] Users access the system via a terminal and request the information they need. The server retrieves the latest analysis results and provides real-time event information and highlights to the user. The input is the user request, and the output is the analysis results and visualized data. Specifically, the system searches for appropriate information in response to the user request and displays it through a GUI.

[1090] Step 6:

[1091] Event highlights provided

[1092] The server provides users with highlights and important scenes from specific events based on the extracted emotion data. This process prioritizes scenes with high emotion scores and edits those video clips to create a highlight video. The inputs are emotion scores and event data, and the output is a highlight video. Specifically, video editing software is used to automatically edit video clips based on the emotion scores.

[1093] Example prompts to input to the generative AI model

[1094] Analyze the post "I saw a lot of great goals today!" and output a positive sentiment score.

[1095] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1096] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1097] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1098] [Fourth embodiment]

[1099] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1100] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1101] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1102] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1103] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1104] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1105] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1106] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1107] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1108] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1109] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1110] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1111] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1112] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions. The system is mainly composed of four main elements: data collection means, natural language processing means, visualization means, and information provision means.

[1113] Data collection methods

[1114] To gather the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. Specifically, the device collects user posts from online review sites and social networking services (SNS). In this case, the device sends an HTTP request and receives HTML data as a response. For example, if a local user's review says, "The snow was amazing today!", this text data is obtained.

[1115] Natural language processing tools

[1116] The server analyzes the collected data. It uses natural language processing (NLP) algorithms to extract keywords and sentiment from the collected text data and classify them into specific categories, such as "snow sentiment (positive)" and "temperature sentiment (negative)." TextBlob and other NLP tools are used to calculate a sentiment score for each post, which is then stored in a database along with the keywords.

[1117] Visualization means

[1118] The server then visualizes the data in graphs or dashboards based on the analysis results. For example, if there are many positive comments about snow conditions, the server calculates the average sentiment score for that category and displays it in the form of a bar graph or pie chart. This allows the device to provide information to users in a visually easy-to-understand format.

[1119] Information provision means

[1120] Users access the system via their terminals to obtain the information they need. For example, if a user enters a query such as "What are the conditions at the ski resort today?", the terminal retrieves the latest analysis results from the server and provides the user with an answer such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Visualized graphs and dashboards are also displayed to the user, allowing them to visually check more detailed information.

[1121] Specific examples

[1122] Below is a specific example. When a user visits a ski resort, they post on social media that "the snow was deep today and it was easy to ski." The device collects these posts, and the server uses natural language processing to extract keywords related to "snow" and "positive" emotions. As a result, the server records the "snow conditions are very good" in the database and reflects this in a graph using visualization tools. The next time the user checks the "ski resort conditions," this information is displayed on the device, and they can use it as a reference for when to visit next.

[1123] As described above, the system of the present invention effectively collects and analyzes the impressions and opinions of local users and provides accurate, real-time information on weather conditions and ski resort conditions.

[1124] The processing flow will be explained below.

[1125] Step 1:

[1126] The device collects local user impressions and opinions from a specified URL. The device sends an HTTP request and receives HTML data as a response. For example, when collecting posts from a social networking site or review site, the device accesses the required URL and downloads the data.

[1127] Step 2:

[1128] The server analyzes the HTML data it has retrieved. Using an HTML parser such as BeautifulSoup, the server extracts the necessary text information (post content). Specifically, it searches for specific HTML tags and extracts the user posts contained therein in text format.

[1129] Step 3:

[1130] The server runs the extracted text data through a natural language processing (NLP) algorithm. Using a library such as TextBlob, the server extracts keywords and sentiment scores from each post. For example, from a post saying "The snow was amazing," the server extracts the keyword "snow" and a "positive" sentiment score.

[1131] Step 4:

[1132] The server classifies each post into a specific category (e.g., snow conditions, temperature, wind speed) based on the extracted keywords and sentiment score. The server stores these results in a database. For example, if there are many posts about "snow" and the sentiment score is positive, it will be recorded as "good snow conditions."

[1133] Step 5:

[1134] The server calculates the average sentiment score for each category based on the accumulated data. Using the calculated scores, the server visualizes the data in visual formats such as bar graphs and pie charts. The results are created as image files or interactive dashboards.

[1135] Step 6:

[1136] A user accesses the system using a terminal and requests the required information. For example, the user types a query such as "What are the ski conditions like today?"

[1137] Step 7:

[1138] The device sends a query to the server to obtain the latest analysis results, and the server searches for the relevant information from the stored data and provides it to the device.

[1139] Step 8:

[1140] Based on the calculations and visualizations obtained by the device, the device displays specific information to the user, such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm," and also displays graphs and dashboards when available.

[1141] This allows users to get accurate, real-time information about local weather conditions and ski resort conditions.

[1142] Example 1

[1143] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1144] There is a need to efficiently collect impressions and opinions from local users, accurately analyze them, and provide information in real time. However, conventional systems have limited the scope of data collection and have issues with analysis accuracy. Furthermore, they lack sufficient visualization methods to make the collected data easier to understand visually, and methods for effectively providing information to users. The present invention aims to solve these issues and provide more accurate and convenient information.

[1145] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1146] In this invention, the server includes data collection means for collecting impressions and opinions from local users, natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, visualization means for visually displaying the analysis results, information provision means for providing the visualized information to the user, preprocessing means for preprocessing the data collected by the terminal, and process flow handling means for controlling the flow of program processing. This makes it possible to comprehensively collect a variety of opinions from local users, analyze and visualize them with high accuracy, and effectively provide information to the user.

[1147] "Data collection methods" refers to the technology and equipment used to collect impressions and opinions of local users from the Internet. Specifically, this includes web scraping technology.

[1148] "Natural language processing means" refers to the technology and algorithms used to extract keywords and emotions from collected text data and classify and analyze them into specific categories.

[1149] "Visualization means" refers to techniques and tools for visually displaying analysis results, including means for providing data in the form of graphs, dashboards, etc.

[1150] "Information provision means" refers to the technology and interface for providing visualized information to users.

[1151] "Preprocessing means" refers to techniques such as data cleaning and tokenization to convert data collected by the terminal into an analyzable format.

[1152] "Processing flow handling means" refers to the techniques and methods for controlling and regulating the processing flow of a program from data collection to information provision.

[1153] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions. This system consists of six main components: data collection means, natural language processing means, visualization means, information provision means, preprocessing means, and processing flow handling means.

[1154] Data collection methods

[1155] To collect the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. Specifically, data is collected from social media and review sites using the Python library Beautiful Soup and Selenium. The device sends an HTTP request to receive the HTML data of the webpage, which is then analyzed to extract text data. For example, if a user posts on social media, "The snow was amazing today!", that text data is collected.

[1156] Pretreatment means

[1157] The device preprocesses the text data it receives to make it analyzable. Specifically, it removes unnecessary tags and special characters, tokenizes the text, and splits it into words. This process improves the quality of the data and prepares it for accurate analysis.

[1158] Natural language processing tools

[1159] The server analyzes the collected text data. Specifically, it uses Python's natural language processing libraries, TextBlob and NLTK, to extract keywords and sentiment from the text. The server then uses these keywords and sentiment scores to classify the data into specific categories. For example, the server extracts the keyword "snow" and positive sentiment from a post that says, "The snow was amazing today!" This information is then stored in a database.

[1160] Visualization means

[1161] The server visually displays the analysis results. Using Python visualization libraries Matplotlib and Plotly, sentiment scores and keyword frequency are displayed in graphs and dashboards. This allows users to view information in a visually easy-to-understand format. For example, if there are many positive comments about snow, the data can be displayed in a bar graph or pie chart.

[1162] Information provision means

[1163] Users access the system via their terminals to obtain the necessary information. When a user enters a query into their terminal, such as "What are the conditions at the ski resort today?", the terminal sends the request to the server. The server returns the latest analysis results, and the user receives information such as "The snow conditions are very good, the temperature is a little cold, but the wind is calm."

[1164] Specific examples

[1165] For example, when a user visits a ski resort, they post on social media that "the snow was deep today and easy to ski on." The device collects these posts, and the server uses natural language processing to extract keywords and positive emotions related to "snow." As a result, the information that "the snow conditions are very good" is recorded in the database. This information is reflected in a graph using visualization tools, and the next time the user checks the "ski resort conditions," they can visually confirm this information on their device and use it as a reference for when to visit next.

[1166] Example prompt sentence:

[1167] "How are the ski conditions today?"

[1168] Please tell me the snow conditions at the ski resort.

[1169] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1170] Step 1:

[1171] The device sends an HTTP request to a specified URL to collect impressions and opinions from local users. The input is the URL to be collected, and the output is the HTML data of the web page. Specifically, the HTTP request is made using the requests library.

[1172] Step 2:

[1173] The Beautiful Soup library is used to parse the HTML data received by the device. The input is the HTML data obtained in step 1, and the output is text data containing impressions and opinions. Specifically, Beautiful Soup parses the HTML data and extracts text data from the specified tags and classes.

[1174] Step 3:

[1175] The text data extracted by the terminal is preprocessed and converted into an analyzable format. The input is the text data extracted in step 2, and the output is the cleaned text data. Specific operations include removing special characters and trimming spaces.

[1176] Step 4:

[1177] The terminal tokenizes the preprocessed data and splits it into words. The input is the cleaned text data obtained in step 3, and the output is the tokenized text data. Specifically, tokenization is performed using the NLTK library.

[1178] Step 5:

[1179] The server performs natural language processing to extract keywords and sentiment from the tokenized text data. The input is the tokenized text data obtained in step 4, and the output is keywords and sentiment scores. Specifically, sentiment analysis is performed using the TextBlob library to extract keywords.

[1180] Step 6:

[1181] The server saves the extracted keywords and sentiment scores in a database. The input is the keywords and sentiment scores obtained in step 5, and the output is the results saved in the database. Specifically, it writes the results to the database using SQLAlchemy.

[1182] Step 7:

[1183] The server visualizes the data based on the analysis results stored in the database. The input is the analysis results stored in the database, and the output is visual data in the form of graphs or dashboards. Specifically, the data is displayed visually using Matplotlib or Plotly.

[1184] Step 8:

[1185] A user accesses the system via a terminal and enters a query. The input is the query entered by the user, and the output is an answer based on the analysis results. Specifically, the user's query is sent to the server, which retrieves the latest analysis results from the database and returns them.

[1186] Step 9:

[1187] The terminal provides the user with the analysis results received from the server. The input is the analysis results returned from the server, and the output is the information provided to the user. Specifically, the results are formatted and displayed in a user-friendly format.

[1188] The above processing steps realize a system that efficiently collects opinions and impressions from local users, analyzes them with high accuracy, and provides information in real time.

[1189] (Application example 1)

[1190] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1191] Modern food delivery services require a method for efficiently collecting and analyzing user feedback on the quality of food and delivery in real time. Conventional systems often collect and analyze reviews manually, making it difficult to provide accurate and timely information. This makes it difficult for users to select a service based on the most up-to-date information, and it is also difficult for service providers to properly understand customer satisfaction. Therefore, there is a need to develop a system that automatically collects and analyzes reviews of food delivery services and provides information to users in an easy-to-understand manner.

[1192] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1193] In this invention, the server includes a data collection means for collecting opinions from local users, a natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, a visualization means for visualizing the analysis results, and an information provision means for providing the visualized information to users. This allows users to easily obtain the latest review information by combining the means for collecting and analyzing reviews about food and delivery with the means for generating information about food and delivery services based on the analyzed reviews.

[1194] "Data collection means" refers to means for collecting opinions from local users.

[1195] "Natural language processing means" is a means of extracting keywords and emotions from collected data and classifying and analyzing them into specific categories.

[1196] "Visualization means" refers to a means for displaying analysis results in the form of graphs or dashboards.

[1197] The "information providing means" is a means for providing visualized information to a user.

[1198] "Reviews" are impressions and opinions written by users about the quality of food and delivery of food delivery services.

[1199] "Analysis" is the act of processing collected data and extracting meaningful information.

[1200] "Food" refers to food and drink delivered by a food delivery service.

[1201] "Delivery" refers to the act of delivering ordered food to a designated location in a food delivery service.

[1202] "Services" refers to the overall assistance and support provided in food delivery.

[1203] A "natural language processing algorithm" is an algorithm for extracting linguistic features from text data.

[1204] "Web scraping" is a technique for automatically collecting specific information from websites.

[1205] The system of this invention collects and analyzes user reviews of food delivery services and provides real-time information about the quality of food and delivery. The system is mainly composed of four main components: data collection means, natural language processing means, visualization means, and information provision means.

[1206] Data collection methods

[1207] The server uses web scraping technology to collect local user reviews from the Internet. The server sends an HTTP request and receives HTML data as a response. For example, a user might post about a food delivery service, saying, "The food was hot and delicious, but the delivery was late." The server collects this post.

[1208] Natural language processing tools

[1209] The server analyzes the collected reviews. It uses natural language processing algorithms to extract keywords and sentiment from the text data. Specifically, it uses TextBlob and other NLP tools to calculate a sentiment score for each post and store it in a database along with keywords. For example, reviews are categorized as "Cooking (positive)" or "Delivery (negative)."

[1210] Visualization means

[1211] The server visualizes the data based on the analysis results. The analyzed data is displayed in graphs and dashboards, providing information in a visually easy-to-understand format for users. For example, it allows users to visually see at a glance which dishes have many positive reviews and which delivery items have many negative reviews.

[1212] Information provision means

[1213] Users access the system via their devices to obtain the information they need. For example, if a user enters a query such as "How was the food delivery service today?", the server retrieves the latest analysis results and provides detailed information via the device, such as "The food was highly rated, but the delivery was a little late." Graphs and dashboards are also displayed to help users gain a deeper understanding.

[1214] Specific examples

[1215] Suppose a user posts on social media, "How was today's dinner delivery service?" and the post states, "The food was hot and delicious, but the delivery was late." The server collects these posts and uses natural language processing to extract emotions related to "food (positive)" and "delivery (negative)." The analysis results are then displayed in a graph using visualization tools, which are then displayed to the user via their device.

[1216] Example prompts to input to a generative AI model:

[1217] Analyze the sentiment of the reviews below.

[1218] Review: The food was hot and delicious, but the delivery was late.

[1219] As a result, this system allows users to easily obtain the latest review information for food delivery services, providing reference information for users when selecting a service and enabling service providers to quickly receive feedback to improve customer satisfaction.

[1220] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1221] Step 1:

[1222] The server uses web scraping technology to collect local user reviews from the Internet. The server sends an HTTP request and analyzes the HTML data received as a response to extract the review text data.

[1223] Input: URL of online review site or social media

[1224] Output: Text list of reviews

[1225] What happens: The server accesses the specified URL, retrieves the HTML page, and uses a library such as BeautifulSoup to extract the reviews and save them as text data in a list.

[1226] Step 2:

[1227] The server analyzes the collected reviews using natural language processing (NLP) techniques, such as TextBlob and other NLP tools, to extract keywords and sentiment scores from the text data.

[1228] Input: The list of reviews in text format collected in Step 1

[1229] Output: A list of keywords and sentiment scores

[1230] Specific operation: It uses TextBlob to analyze each review and calculate the sentiment score, and at the same time, extracts important keywords and stores them in the database together with the sentiment score.

[1231] Step 3:

[1232] The server uses visualization tools to display the analysis results in the form of graphs or dashboards, for example, visually representing the number of positive / negative reviews or the frequency of specific keywords.

[1233] Input: List of keywords and sentiment scores extracted in step 2

[1234] Output: Visualized data in the form of graphs and dashboards

[1235] Specific operations: Using libraries such as matplotlib and D3.js, the frequency of keywords and sentiment scores are aggregated, and data is generated to display them in the form of bar graphs, pie charts, etc.

[1236] Step 4:

[1237] Users access the system via their terminals and obtain the necessary information. Analysis results and visualized information are provided to the user via the terminals. For example, in response to a query such as "How was the food delivery service today?", the terminal displays information based on the analysis results to the user.

[1238] Input: User query (e.g., "How was the food delivery service today?")

[1239] Output: Information based on the analysis results (e.g., "The food is highly rated, but delivery is often delayed")

[1240] Specific operation: When a user inputs a query into the system from a terminal, the server searches the latest analysis results, retrieves the relevant information, sends the retrieved information to the terminal, and displays it in a form that can be visually confirmed by the user.

[1241] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1242] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions, and also combines an emotion engine that recognizes user emotions. The system is mainly composed of five main elements: a data collection means, a natural language processing means, an emotion engine, a visualization means, and an information provision means.

[1243] Data collection methods

[1244] To gather the impressions and opinions of local users, the device uses web scraping technology to obtain data from a specified URL. The device collects user posts from online review sites and social media. In doing so, the device sends an HTTP request and receives HTML data as a response. For example, a user post such as "The snow was amazing today!" may be obtained.

[1245] Natural language processing tools

[1246] The server analyzes the collected data. It uses natural language processing (NLP) algorithms to extract keywords from the text data. For example, it extracts the keyword "snow" from a post that says "The snow was amazing."

[1247] Emotion Engine

[1248] The server applies a sentiment engine to the collected text data to recognize emotions. The sentiment engine uses an algorithm to classify positive, negative, and neutral sentiments and calculates a sentiment score for each post. For example, a post saying "The snow was great today" would be recognized as having a positive sentiment score.

[1249] Visualization means

[1250] The server then uses the analysis results to visualize the data in graphs and dashboards. The server calculates the average sentiment score for each category and creates bar graphs, pie charts, and other visualizations to visualize the results. For example, if the snow conditions receive a lot of positive feedback, that category will be displayed as highly rated.

[1251] Information provision means

[1252] Users access the system via their terminal and request the information they need. For example, if a user types, "What are the conditions at the ski resort today?", the terminal retrieves the latest analysis results from the server and provides the user with an answer such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Visualized graphs and dashboards are also displayed to the user, allowing them to visually confirm specific information.

[1253] As a concrete example, consider the case where a user visits a ski resort and posts on social media, "It was windy and cold today, but the snow conditions were perfect." The device collects these posts, and the server analyzes them using natural language processing and an emotion engine. Keywords such as "wind," "temperature," and "snow" are extracted from the post, and an emotion score for each is calculated. As a result, the emotion for "wind" is classified as negative, the emotion for "temperature" as negative, and the emotion for "snow conditions" as positive. The results of this analysis are reflected in a graph, and the next time the user checks the "ski resort conditions," this information is provided via the device, making it useful for the user's next visit.

[1254] As described above, the system of the present invention effectively collects and analyzes the impressions and opinions of local users and provides accurate, real-time information on weather conditions and ski resort conditions. By combining it with an emotion engine, more accurate analysis results based on user emotions can be obtained.

[1255] The processing flow will be explained below.

[1256] Step 1:

[1257] The device sends an HTTP request to a specified URL to collect impressions and opinions from local users. The device accesses review sites and social media pages on the Internet and retrieves HTML data.

[1258] Step 2:

[1259] The server analyzes the HTML data received from the device. The server uses an HTML parser such as BeautifulSoup to search for specific tags within the page and extract the required text information (post content). For example, Extract the text inside the tag.

[1260] Step 3:

[1261] The server runs the extracted text data through a natural language processing (NLP) algorithm, extracts keywords from the text data, and sends them to the emotion engine. Specifically, it uses TextBlob or a similar library to analyze keywords and sentence structure within the text.

[1262] Step 4:

[1263] The server uses an emotion engine to recognize emotions from the extracted text data. The emotion engine uses an algorithm to classify emotions into positive, negative, and neutral, and calculates an emotion score for each post. For example, a post saying "The snow was amazing today" would be classified as having a positive emotion score.

[1264] Step 5:

[1265] The server classifies each post into a specific category (e.g., snow conditions, temperature, wind) based on the sentiment score and keywords obtained from the sentiment engine. This context-based classification is then stored in a database. For example, the keyword "snow" with a positive sentiment score would be classified as "snow conditions."

[1266] Step 6:

[1267] The server calculates the average sentiment score based on the accumulated data. The server aggregates the sentiment scores for each category and calculates the overall average. For example, if there are multiple posts in the same category, the sentiment scores are averaged.

[1268] Step 7:

[1269] The server visualizes the analysis results, generating information to display the data in formats such as bar graphs and pie charts. A visualization tool is used to create graphs and dashboards that visually represent the calculated average sentiment scores.

[1270] Step 8:

[1271] A user accesses the system using a terminal and requests specific information. The user types a query into the terminal, such as "What are the ski resort conditions today?"

[1272] Step 9:

[1273] The device sends the user's query to the server, which searches and retrieves the latest analysis results from the database and generates information corresponding to the request.

[1274] Step 10:

[1275] The device displays the analysis results it receives from the server to the user. For example, the device provides information in text format such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm." Generated graphs and dashboards are also displayed, allowing the user to check the details through visual information.

[1276] Examples:

[1277] After visiting a ski resort, a user posts on social media, "Today was windy and cold, but the snow conditions were perfect." The device collects these posts, and the server analyzes them using natural language processing and an emotion engine. A positive emotion score is assigned to the "snow conditions," and negative emotion scores are assigned to the "wind" and "temperature," and the results are stored in a database. The next time the user checks the "ski resort conditions," this information is provided via the device. The user is shown specific information such as "The snow conditions were good, but the temperature and wind were not so good." This information can be used as a reference when considering their next visit.

[1278] Example 2

[1279] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1280] Currently, there is no system that can collect and analyze accurate and useful information about weather and ski resort conditions from numerous reviews and social media posts in real time and provide it to users. Furthermore, existing systems are unable to properly analyze user emotions, which often limits the usefulness of the information. There is a need to develop a system that can quickly and appropriately provide users with the information they need.

[1281] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an information collection means for collecting impressions and opinions from local users, a natural language processing means for extracting keywords and emotions from the collected information and classifying and analyzing them into specific categories, an emotion analysis means for calculating an emotion score based on the analysis results, a display means for visually displaying the data, and an information provision means for providing the analysis results including the visualized information to the user. This makes it possible to quickly collect various opinions and impressions from local users and provide accurate information on weather conditions and ski resort conditions in real time. Furthermore, analyzing users' emotions improves the usefulness and accuracy of the information.

[1282] "Information gathering means" refers to technology for obtaining impressions and opinions from local users from specific websites and social networking sites on the Internet.

[1283] "Natural language processing means" is a means for extracting keywords and emotions from collected information and classifying and analyzing them into specific categories.

[1284] The "sentiment analysis means" is an algorithm for calculating and analyzing the sentiment score (positive, negative, neutral) for the collected text data.

[1285] "Display means" refers to software or devices for visualizing analysis results in the form of graphs or dashboards.

[1286] The "information providing means" refers to a method or system for providing the analysis results, including visualized information, to a user.

[1287] "Data collection technology" refers to technology for obtaining information from the Internet, such as review sites and social media.

[1288] A "natural language processing algorithm" is an algorithm used to extract keywords and emotions from text data.

[1289] An "emotion score" is a numerical representation of the emotions in the collected text data, classified as positive, negative, or neutral.

[1290] A "graph" is a diagram such as a bar graph or pie chart that visually displays the analysis results.

[1291] A "dashboard" is an integrated visualization tool that displays multiple analysis results so that they can be viewed at a glance.

[1292] A "user request" is a user's inquiry or request for information from the system.

[1293] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides information on weather conditions and ski resort conditions, and also combines an emotion engine that recognizes user emotions. The system is mainly composed of five main elements: information collection means, natural language processing means, emotion analysis means, display means, and information provision means.

[1294] Hardware and software used

[1295] 1. Information collection methods:

[1296] The device retrieves data from the specified URL using web scraping technology.

[1297] Software used: Python's requests library and BeautifulSoup library are used.

[1298] Example: A user posts, "The snow was absolutely amazing today!"

[1299] 2. Natural Language Processing Tools:

[1300] The server analyzes the collected data.

[1301] Software used: The spaCy library is used to extract keywords from text data.

[1302] Example: Get the keyword "snow" from the post "The snow was amazing."

[1303] 3. Emotion analysis means:

[1304] The server applies an emotion engine to the collected text data to recognize emotions.

[1305] Software used: The NLTK library is used to calculate sentiment scores.

[1306] Example: A post saying "The snow was amazing today" is recognized as having a positive sentiment score.

[1307] 4. Display means:

[1308] Based on the analysis results, the server visualizes the data in the form of graphs and dashboards.

[1309] Software used: Uses matplotlib and seaborn libraries.

[1310] Example: If a category receives a lot of positive feedback about snow conditions, it will be displayed as highly rated.

[1311] 5. Information provision method:

[1312] A user accesses the system via a terminal and requests the required information.

[1313] Example: When a user types, "What are the conditions at the ski resort today?", the device retrieves the latest analysis results from the server and provides the user with an answer such as, "The snow conditions are very good, the temperature is a little cold, but the wind is calm."

[1314] Prompt Sentence Examples

[1315] Here is an example of a prompt to input to the generative AI model:

[1316] "Please explain in detail the steps to collect user posts through web scraping."

[1317] "Please tell me the specific method for extracting keywords using a natural language processing algorithm."

[1318] "Please explain in detail how the emotion engine calculates the emotion score."

[1319] "Please explain the visualization method and generation procedure for the collected data."

[1320] "How do you generate a response to a user's information request?"

[1321] As described above, the system of the present invention executes each process in detail, from information collection to analysis, emotion recognition, visualization, and information provision, and provides useful information to users in real time. This makes it possible to provide specific and useful weather information and ski resort condition information based on the user's emotions.

[1322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1323] Program processing flow

[1324] Step 1: Start collecting data

[1325] The device sends an HTTP request to the URL of the specified review site or social media site.

[1326] Specific operation: Uses Python's requests library to access specific review sites and social media pages.

[1327] Input: URL of review site or social media

[1328] Output: HTML data response

[1329] Step 2: Parse the response

[1330] The terminal analyzes the HTML data received as a response.

[1331] What it does: Uses the BeautifulSoup library to parse the HTML document and extract the post content.

[1332] Input: HTML data

[1333] Output: User submitted data

[1334] Step 3: Save data

[1335] The device temporarily stores the extracted posting data.

[1336] Specific operation: Save the extracted text data in a file in JSON format.

[1337] Input: User submitted data

[1338] Output: JSON file

[1339] Step 4: Loading Data

[1340] The server reads the saved JSON file.

[1341] Specific operation: Uses Python's json library to read the file and extract the text data to be analyzed.

[1342] Input: JSON file

[1343] Output: Text data

[1344] Step 5: Applying natural language processing algorithms

[1345] The server uses natural language processing (NLP) algorithms to extract keywords from the text data.

[1346] Specific behavior: Extract specific keywords using the spaCy library.

[1347] Input: Text data

[1348] Output: Extracted keywords

[1349] Step 6: Save your keywords

[1350] The server saves the extracted keywords as a new dataset.

[1351] Specific operation: Save the extracted keywords to a file in CSV format.

[1352] Input: Extracted keywords

[1353] Output: CSV file

[1354] Step 7: Applying the Emotion Engine

[1355] The server applies an emotion engine to the keywords extracted by NLP.

[1356] Specific operation: Uses the NLTK library to calculate the sentiment score (positive, negative, neutral) for each keyword.

[1357] Input: Keyword data

[1358] Output: Sentiment score

[1359] Step 8: Storing sentiment scores

[1360] The server adds the calculated sentiment scores to the dataset.

[1361] Specific behavior: Save the new emotion score in JSON format.

[1362] Input: Sentiment score

[1363] Output: JSON file of data with sentiment scores

[1364] Step 9: Loading Data

[1365] The server loads the dataset with the saved sentiment scores.

[1366] Specific operation: Read data using Python's pandas library.

[1367] Input: JSON file of data with sentiment scores

[1368] Output: Data frame to be analyzed

[1369] Step 10: Generate visualization

[1370] Based on the analysis results, the server visualizes the data in the form of graphs and dashboards.

[1371] Specific operation: Generate bar graphs and pie charts using the matplotlib and seaborn libraries.

[1372] Input: Data to be analyzed

[1373] Output: Visualized graph

[1374] Step 11: Save the visualization

[1375] The server stores the generated visualization results.

[1376] Specific operation: Save the graph image file in PNG format on the server.

[1377] Input: A visualized graph

[1378] Output: PNG file

[1379] Step 12: Receiving a User Request

[1380] The terminal receives an information request from a user.

[1381] What happens: A user enters a natural language query such as "What are the ski conditions like today?"

[1382] Input: User request

[1383] Output: Request data

[1384] Step 13: Database Query

[1385] The server retrieves the latest analysis results from the database based on the user's request.

[1386] Specific behavior: Retrieves the latest information from the database using an SQL query.

[1387] Input: User request data

[1388] Output: Latest analysis results

[1389] Step 14: Response Generation

[1390] The server generates a response to the request.

[1391] Specific behavior: Based on the acquired data, an answer is created using a natural language generation (NLG) model.

[1392] Input: Latest analysis result data

[1393] Output: The generated response

[1394] Step 15: Provide information

[1395] The terminal provides the generated response and visualization results to the user.

[1396] Specific behavior: Display the generated text and graphs on a web page or mobile app interface.

[1397] Input: Generated response, visualized graph

[1398] Output: Information provided to the user

[1399] Through these steps, the system is able to provide accurate and useful information about weather conditions and ski resort conditions based on real-time opinions and feedback from local users.

[1400] (Application example 2)

[1401] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1402] While there are existing systems that efficiently collect, analyze, and visualize the impressions and opinions of local users, they lack the functionality to provide highlights of specific events based on the emotional data associated with the event, making it difficult to provide viewers with personalized highlights in real time during and after the event.

[1403] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1404] In this invention, the server includes a data collection means for collecting impressions and opinions from local users, a natural language processing means for extracting keywords and emotions from the collected data and classifying and analyzing them into specific categories, a visualization means for visualizing the analysis results, an information provision means for providing the visualized information to users, and a means for providing highlights of the event based on the extracted emotion data, thereby enabling personalized highlights to be provided to viewers in real time.

[1405] A "local user" is a user who provides information related to a particular location or event.

[1406] "Means for collecting impressions and opinions" refers to means for collecting impressions and opinions from users over the Internet.

[1407] "Natural language processing means" is a means of analyzing collected text data, extracting keywords and emotions, and classifying and analyzing them into specific categories.

[1408] "Visualization means" refers to a means for visually displaying the analysis results in the form of graphs or dashboards.

[1409] The "information providing means" is a means for providing visualized information to a user.

[1410] The "means for providing event highlights" is a means for providing the user with highlights and important scenes of a particular event based on the extracted emotion data.

[1411] "Data collection means" refers to means for collecting the impressions and opinions of local users, particularly using web scraping technology.

[1412] A "natural language processing algorithm" is an algorithm used to extract keywords and emotions from text data.

[1413] An "emotion engine" is an algorithm that recognizes and classifies emotions from collected text data.

[1414] The system of the present invention collects impressions and opinions from local users, analyzes them, and provides event highlights. It mainly consists of a data collection means, a natural language processing means, an emotion engine, a visualization means, an information provision means, and a means for providing event highlights.

[1415] Data collection methods

[1416] The server retrieves data from online review sites and social media sites to gather impressions and opinions from local users. Specifically, it uses HTTP requests to gather the necessary information from specified URLs using web scraping technology. For example, it retrieves user posts such as "I saw a lot of great goals today!"

[1417] Natural language processing tools

[1418] The server analyzes the collected data. Natural language processing algorithms are used for this analysis. Keywords and emotions are extracted from the text data, and they are classified and analyzed into specific categories. For example, the keyword "goal" is extracted from a post titled "Great goal," and the emotion score is determined to be positive.

[1419] Emotion Engine

[1420] The server applies an emotion engine to the collected text data to recognize emotions. Specifically, it uses an algorithm that classifies emotions into positive, negative, and neutral, and calculates an emotion score for each post. For example, a post saying, "I saw a lot of great goals today!" would be recognized as having a positive emotion score.

[1421] Visualization means

[1422] The server visualizes the analysis results. The analyzed data is displayed in graphs and dashboards. For example, the average sentiment score for each category is visualized in a bar graph or pie chart. For example, if a goal receives many positive comments, that category is displayed as highly rated.

[1423] Information provision means

[1424] Users can access the system via their device and request the information they need. For example, if a user types, "I want to see the highlights of today's game," the device will retrieve the latest analysis results from the server and provide the user with "highlights of goal scenes that received a lot of positive feedback." In addition, visualized graphs and dashboards are also displayed to the user, allowing them to visually confirm specific information.

[1425] A way to provide highlights of the event

[1426] The server then provides users with highlights and important scenes from a specific event based on the extracted emotion data. For example, it provides users with personalized highlight videos based on goal scenes that garnered very positive feedback or scenes that generated a large amount of negative feedback.

[1427] Specific examples

[1428] For example, if a user posts on social media during a sporting event, "I saw a lot of great goals today!", this post will be recorded as a positive emotion. If another user comments, "The referee's decisions were terrible," this will be classified as a negative emotion. The data collected and analyzed in this way will be used to create highlight videos in real time.

[1429] Example prompts to input to the generative AI model

[1430] Analyze the post "I saw a lot of great goals today!" and output a positive sentiment score.

[1431] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1432] Step 1:

[1433] Data collection

[1434] The device retrieves data from online review sites and social networking sites to collect impressions and opinions from local users. This process uses an HTTP request to retrieve the HTML data of a webpage from a specified URL, and then analyzes it to extract the required text information (impressions and opinions). The input is the URL and HTTP request, and the output is the extracted text data.

[1435] Step 2:

[1436] Natural Language Processing

[1437] The server analyzes the collected text data. In this step, natural language processing algorithms are used to extract keywords and sentiment from the text data and classify each into a specific category. The input is text data, and the output is analyzed data containing keywords and sentiment scores. Specifically, a text analysis library is used to extract nouns and adjectives and perform sentiment analysis.

[1438] Step 3:

[1439] Emotion engine applied

[1440] The server applies an emotion engine based on the analyzed data to calculate an emotion score for each post. The emotion score is classified as positive, negative, or neutral and is output. Specifically, the results of natural language processing are input into an emotion recognition algorithm to score each emotion.

[1441] Step 4:

[1442] Data Visualization

[1443] The server visualizes the sentiment scores and keyword data. This process uses a visualization tool to display the data in graph or dashboard format. The input is the sentiment scores and keyword data, and the output is a visually easy-to-understand graph or dashboard. Specifically, graph drawing libraries such as matplotlib and Plotly are used.

[1444] Step 5:

[1445] Providing information

[1446] Users access the system via a terminal and request the information they need. The server retrieves the latest analysis results and provides real-time event information and highlights to the user. The input is the user request, and the output is the analysis results and visualized data. Specifically, the system searches for appropriate information in response to the user request and displays it through a GUI.

[1447] Step 6:

[1448] Event highlights provided

[1449] The server provides users with highlights and important scenes from specific events based on the extracted emotion data. This process prioritizes scenes with high emotion scores and edits those video clips to create a highlight video. The inputs are emotion scores and event data, and the output is a highlight video. Specifically, video editing software is used to automatically edit video clips based on the emotion scores.

[1450] Example prompts to input to the generative AI model

[1451] Analyze the post "I saw a lot of great goals today!" and output a positive sentiment score.

[1452] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1453] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1454] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1455] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1456] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1457] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1458] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1459] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1460] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1461] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1462] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1463] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1464] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1465] 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.

[1466] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1467] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1468] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1469] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1470] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1471] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1472] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1473] The following is further disclosed regarding the above embodiment.

[1474] (Claim 1)

[1475] Data collection methods to gather impressions and opinions from local users;

[1476] A natural language processing method to extract keywords and emotions from collected data and classify and analyze them into specific categories.

[1477] a visualization means for visualizing the analysis results;

[1478] an information providing means for providing the visualized information to a user;

[1479] A system including:

[1480] (Claim 2)

[1481] 2. The system of claim 1, wherein the natural language processing means uses a natural language processing algorithm to extract keywords and sentiments.

[1482] (Claim 3)

[1483] 2. The system of claim 1, wherein the data collection means uses web scraping technology to obtain local user opinions from the Internet.

[1484] "Example 1"

[1485] (Claim 1)

[1486] Data collection methods to gather impressions and opinions from local users;

[1487] A natural language processing method to extract keywords and emotions from collected data and classify and analyze them into specific categories.

[1488] a visualization means for visually displaying the analysis results;

[1489] an information providing means for providing the visualized information to a user;

[1490] preprocessing means for preprocessing data collected by the terminal;

[1491] a process flow handling means for controlling the process flow of the program;

[1492] A system including:

[1493] (Claim 2)

[1494] 2. The system of claim 1, wherein the natural language processing means includes means for using a natural language processing algorithm to extract keywords and sentiments and storing the results in a database.

[1495] (Claim 3)

[1496] The system of claim 1, wherein the data collection means includes means for acquiring data via HTTP requests and responses using web scraping technology to acquire local user opinions from the Internet.

[1497] "Application Example 1"

[1498] (Claim 1)

[1499] a data collection tool to gather feedback from local users;

[1500] A natural language processing method to extract keywords and emotions from collected data and classify and analyze them into specific categories.

[1501] a visualization means for visualizing the analysis results;

[1502] an information providing means for providing the visualized information to a user;

[1503] A system comprising:

[1504] A means to collect and analyze food and delivery reviews;

[1505] means for generating information about food and delivery services based on the analyzed reviews;

[1506] A system characterized by:

[1507] (Claim 2)

[1508] 2. The system of claim 1, wherein the natural language processing means uses a natural language processing algorithm to extract keywords and sentiments.

[1509] (Claim 3)

[1510] 2. The system of claim 1, wherein the data collection means uses web scraping technology to obtain local user opinions from the Internet.

[1511] "Example 2: Combining Emotion Engines"

[1512] (Claim 1)

[1513] A means of collecting information to gather impressions and opinions from local users;

[1514] A natural language processing method that extracts keywords and emotions from collected information and classifies and analyzes them into specific categories.

[1515] An emotion analysis means for calculating an emotion score based on the analysis result;

[1516] display means for visually displaying the data;

[1517] an information providing means for providing a user with an analysis result including visualized information;

[1518] A system including:

[1519] (Claim 2)

[1520] 2. The system of claim 1, wherein the natural language processing means uses a natural language processing algorithm to extract keywords and sentiments.

[1521] (Claim 3)

[1522] 2. The system of claim 1, wherein the information gathering means uses data gathering techniques to obtain local user opinions from the Internet.

[1523] (Claim 4)

[1524] 10. The system of claim 1, wherein the sentiment analysis means uses an algorithm to calculate a sentiment score for the collected text data.

[1525] (Claim 5)

[1526] 2. The system of claim 1, wherein the display means uses software for visualizing the analysis results in the form of graphs or dashboards.

[1527] (Claim 6)

[1528] 10. The system of claim 1, further comprising means for providing updated analysis results based on information requests from users.

[1529] "Application example 2 when combining emotion engines"

[1530] (Claim 1)

[1531] Data collection methods to gather impressions and opinions from local users;

[1532] A natural language processing method to extract keywords and emotions from collected data and classify and analyze them into specific categories.

[1533] a visualization means for visualizing the analysis results;

[1534] an information providing means for providing the visualized information to a user;

[1535] a means for providing highlights of the event based on the extracted sentiment data;

[1536] A system including:

[1537] (Claim 2)

[1538] 2. The system of claim 1, wherein the natural language processing means uses a natural language processing algorithm to extract keywords and sentiments.

[1539] (Claim 3)

[1540] 2. The system of claim 1, wherein the data collection means uses web scraping technology to obtain local user opinions from the Internet. [Explanation of symbols]

[1541] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. Data collection methods to gather impressions and opinions from local users; A natural language processing method to extract keywords and emotions from collected data and classify and analyze them into specific categories. a visualization means for visualizing the analysis results; an information providing means for providing the visualized information to a user; A system including:

2. 2. The system of claim 1, wherein the natural language processing means uses a natural language processing algorithm to extract keywords and sentiments.

3. The system of claim 1 , wherein the data collection means uses web scraping technology to obtain local user opinions from the Internet.

Images